Public recordAt risk
Software health reportschema 0.27.0 · metrics 1.13.0 · 2026-07-30 10:38 UTC
agnt-ai / agnt-node
agnt-ai/agnt-node holds a health index of 42 out of 100, placing it in the At risk band. It scores highest on AI Readiness (60/100) and lowest on Community & Adoption (24/100). It was last updated today. A single contributor accounts for most of its recent work.
42
overall / 100Software health index
Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At risk ceiling of 49. AI Readiness sits outside the overall score.
42
Excellent85-100Exemplary; meets essentially all checked criteria
Good70-84Healthy; minor gaps
Moderate50-69Acceptable with notable gaps; review recommended
At risk30-49Significant weaknesses; adoption warrants caution
Critical1-29Severe problems (abandoned, single-maintainer, no hygiene)
Score profile
Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.
Ownership
agnt-aiOrganization
0 followers1 public reposince Mar 2026
This repository is backed by an organization — shared, accountable stewardship that can outlive any single maintainer.
Package ecosystems
| Registry | Package | Version | Downloads / mo | Versions | Last publish | Tags |
|---|---|---|---|---|---|---|
| npm | @agnt-sdk/client | 0.0.2 | 483 | 2 | 146 days ago | agntapi-clienttasksai-assistanttypescript |
| npm | @agnt-sdk/config | 0.0.2 | 944 | 2 | 146 days ago | agntconfigtypescript |
| npm | @agnt-sdk/studio | 0.0.45 | 2,608 | 44 | 8 days ago | llmexecutoragentagntanthropicopenaibedrockdeepseekgooglegeminicliprompt-manifest |
Metrics by category
Vitality
Is the project alive — is code being written and are releases shipping?
44
Development activity
72Good
How it's scored
| 36/36 | Push recency — last push 0 days ago |
| 9.7/36 | Commit cadence — 14/52 weeks with commits |
| 16.4/18 | Commit volume — 66 commits in the last year |
| 10/10 | OpenSSF Scorecard: Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
Inputs used
| commits_last_year | 66 |
| human_commit_share | 1 |
| days_since_last_push | 0 |
| active_weeks_last_year | 14 |
Release discipline
1Critical
How it's scored
| 0/27 | Ships releases — no releases published |
| 0/36 | Release recency — no releases |
| 0/27 | Release cadence — no releases |
| 0/10 | OpenSSF Scorecard: Signed-Releases — no data |
Inputs used
| releases_count | 0 |
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.
Community & Adoption
Does the project have users, downloads, attention, and a welcoming setup for contributors?
24
Popularity & adoption
1Critical
How it's scored
| 0/60 | Stars — 0 stars |
| 0/25 | Forks — 0 forks |
| 0/15 | Watchers — 0 watchers |
Inputs used
| forks | 0 |
| stars | 0 |
| watchers | 0 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Community health
25Critical
How it's scored
| 22.5/22.5 | README |
| 0/22.5 | License — no license file detected |
| 0/18 | CONTRIBUTING guide |
| 0/13.5 | Code of conduct |
| 0/7.2 | Issue template |
| 0/6.3 | PR template |
Inputs used
| has_readme | yes |
| has_license | no |
| has_contributing | no |
| has_issue_template | no |
| has_code_of_conduct | no |
| has_pull_request_template | no |
Ecosystem adoption (downloads)
60Moderate
How it's scored
| 48.1/80 | Monthly downloads — 4,035 downloads/month across npm |
| 0/20 | Registry dependents — not reported by this ecosystem |
Inputs used
| packages | @agnt-sdk/client, @agnt-sdk/config, @agnt-sdk/studio |
| dependents | — |
| ecosystems | npm |
| total_downloads | — |
| monthly_downloads | 4,035 |
Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.
Sustainability & Governance
Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?
54
Maintainer resilience (bus factor)
18Critical
How it's scored
| 9/54 | Bus factor — 1 contributor(s) cover half of all commits |
| 6.5/22.5 | Commit distribution — top contributor authored 71% of commits |
| 2.7/13.5 | Contributor breadth — 2 contributors |
| 0/10 | OpenSSF Scorecard: Contributors — project has 0 contributing companies or organizations -- score normalized to 0 |
Inputs used
| bus_factor | 1 |
| contributors_sampled | 2 |
| top_contributor_share | 0.712 |
How it's scored
| 0/46.8 | Issue resolution — no issues or no data |
| 36.6/38.3 | PR acceptance — 22/23 decided PRs merged |
| 7.5/15 | OpenSSF Scorecard: Code-Review — Found 14/28 approved changesets -- score normalized to 5 |
Inputs used
| merged_prs | 22 |
| open_issues | 0 |
| closed_issues | 0 |
| issue_closed_ratio | — |
| closed_unmerged_prs | 1 |
Excluded from scoring (no data or not applicable): Issue resolution. Remaining weights renormalized.
Ownership & stewardship
33At risk
How it's scored
| 30/30 | Ownership backing — organization-owned |
| 0/20 | Verified domain |
| 0/25 | Owner reach — 0 followers of agnt-ai |
| 3/25 | Track record — 1 public repos, account ~0 yr old |
Inputs used
| followers | 0 |
| owner_type | Organization |
| is_verified | — |
| owner_login | agnt-ai |
| public_repos | 1 |
| account_age_days | 149 |
Package maintenance
100Excellent
How it's scored
| 25/25 | Published & resolvable — 3 package(s) on npm |
| 35/35 | Publish recency — latest publish 8 days ago |
| 20/20 | Version history — 44 published versions |
| 20/20 | Not deprecated — active, not deprecated or yanked |
Inputs used
| packages | @agnt-sdk/client, @agnt-sdk/config, @agnt-sdk/studio |
| ecosystems | npm |
| any_deprecated | no |
| min_days_since_publish | 8 |
Engineering Quality
Are baseline engineering and documentation practices in place?
40
Engineering practices
24Critical
How it's scored
| 0/24 | CI workflows |
| 24/24 | Tests present |
| 0/16 | Linter config |
| 0/9.6 | Pre-commit hooks |
| 0/6.4 | .editorconfig |
| 0/20 | OpenSSF Scorecard: CI-Tests — 0 out of 19 merged PRs checked by a CI test -- score normalized to 0 |
Inputs used
| has_ci | no |
| has_tests | yes |
| has_editorconfig | no |
| has_linter_config | no |
| has_precommit_config | no |
Documentation
65Moderate
How it's scored
| 30/30 | README |
| 25/25 | Documentation directory |
| 0/15 | Documentation / homepage site |
| 0/10 | Repository description |
| 0/10 | Topics |
| 10/10 | Wiki |
Inputs used
| topics | — |
| has_wiki | yes |
| homepage | — |
| has_readme | yes |
| has_docs_dir | yes |
| has_description | no |
Security
Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?
44
Security posture
30At risk
How it's scored
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — no data |
| 0/2.5 | CI-Tests — 0 out of 19 merged PRs checked by a CI test -- score normalized to 0 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 3.8/7.5 | Code-Review — Found 14/28 approved changesets -- score normalized to 5 |
| 0/2.5 | Contributors — project has 0 contributing companies or organizations -- score normalized to 0 |
| 0/10 | Dangerous-Workflow — no data |
| 0/7.5 | Dependency-Update-Tool — no update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 0/2.5 | License — license file not detected |
| 7.5/7.5 | Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| 0/5 | Packaging — no data |
| 0/5 | Pinned-Dependencies — no data |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — no data |
| 0/7.5 | Token-Permissions — no data |
| 0/7.5 | Vulnerabilities — 17 existing vulnerabilities detected |
Inputs used
| source | openssf_scorecard |
| checks_evaluated | 12 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 6 |
| scorecard_aggregate | 3 |
Excluded from scoring (no data or not applicable): branch_protection, dangerous_workflow, packaging, pinned_dependencies, signed_releases, token_permissions. Remaining weights renormalized.
Dependency advisories
100Excellent
How it's scored
| 35/35 | Direct dependencies free of known advisories — no direct dependency carries a known advisory |
| 25/25 | Indirect dependencies free of known advisories — no indirect dependency carries a known advisory |
| 0/40 | No advisories left outstanding — no advisory carries a publication date |
Inputs used
| source | osv |
| advisories | 0 |
| affected_packages | 0 |
| assessed_packages | 2 |
| unassessed_packages | 0 |
| affected_by_severity | none |
| direct_affected_packages | 0 |
Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the npm:@agnt-sdk/client@0.0.2 runtime dependency closure — what installing the published package pulls in — 2 packages. Reachability is not analyzed.
AI Readiness
How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score.
60
Agent context & guidance
40At risk
How it's scored
| 0/45 | Agent instructions — no CLAUDE.md / AGENTS.md / editor rules |
| 0/15 | Machine-readable docs (llms.txt) |
| 40/40 | Legible commit history — 66 of 66 human commits state their intent (structured subject or explanatory body) |
Inputs used
| has_llms_txt | no |
| legible_history_share | 1 |
| agent_instruction_files | — |
| agent_instruction_max_bytes | — |
Verify loop (build / test / typecheck)
59Moderate
How it's scored
| 0/18 | One-command bootstrap |
| 22/22 | Automated tests |
| 0/11 | Lint / format config |
| 11/11 | Static type checking — packages/client/tsconfig.json, packages/config/tsconfig.json, packages/studio/tsconfig.json |
| 10/10 | Reproducible environment — lockfile |
| 10/10 | Demonstrated agent practice — 55 of the last 66 commits agent-authored or agent-credited |
| 0/8 | Automated maintenance — no automated dependency updates observed |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — no data |
Inputs used
| has_nix | no |
| has_tests | yes |
| lockfiles | package-lock.json |
| has_dockerfile | no |
| typed_language | yes |
| bootstrap_files | — |
| has_devcontainer | no |
| has_linter_config | no |
| typecheck_configs | packages/client/tsconfig.json, packages/config/tsconfig.json, packages/studio/tsconfig.json |
| agent_commit_share | 0.833 |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Pinned-Dependencies. Remaining weights renormalized.
Code legibility for models
100Excellent
How it's scored
| 45/45 | Type-checkable code — TypeScript (statically typed) |
| 55/55 | Manageable file sizes — 0/79 source files over 60KB |
Inputs used
| primary_language | TypeScript |
| largest_source_bytes | 52,203 |
| source_files_sampled | 79 |
| oversized_source_files | 0 |
Key facts
0GitHub stars
2contributors
66commits, last 12 months
0days since last push
0releases
1bus factor
0open issues
npmpackage ecosystems
Data collection warnings
- GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
More detail
OpenSSF Scorecard 3.0 / 10
3.0aggregate
Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).
| 10 | Binary-Artifacts | no binaries found in the repo |
| n/a | Branch-Protection | internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md |
| 0 | CI-Tests | 0 out of 19 merged PRs checked by a CI test -- score normalized to 0 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 5 | Code-Review | Found 14/28 approved changesets -- score normalized to 5 |
| 0 | Contributors | project has 0 contributing companies or organizations -- score normalized to 0 |
| n/a | Dangerous-Workflow | no workflows found |
| 0 | Dependency-Update-Tool | no update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 0 | License | license file not detected |
| 10 | Maintained | 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| n/a | Packaging | packaging workflow not detected |
| n/a | Pinned-Dependencies | no dependencies found |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| n/a | Signed-Releases | no releases found |
| n/a | Token-Permissions | No tokens found |
| 0 | Vulnerabilities | 17 existing vulnerabilities detected |
Direct dependencies 8
| Registry | Package | Version constraint | Manifest |
|---|---|---|---|
| npm | @agnt-sdk/config | * | packages/client/package.json |
| npm | jose | ^5.9.6 | packages/client/package.json |
| npm | @agnt-sdk/config | * | packages/studio/package.json |
| npm | @anthropic-ai/sdk | ^0.112.4 | packages/studio/package.json |
| npm | @aws-sdk/client-bedrock-runtime | ^3.705.0 | packages/studio/package.json |
| npm | @google/generative-ai | ^0.24.1 | packages/studio/package.json |
| npm | commander | ^12.1.0 | packages/studio/package.json |
| npm | openai | ^4.77.3 | packages/studio/package.json |
All dependencies not collected
The resolved dependency set could not be collected for this report: GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
Dependency advisories 0
Installing npm:@agnt-sdk/client@0.0.2 pulls in 2 packages, direct and transitive: 0 carry known advisories, of which 0 are direct dependencies.
No known advisories affect the assessed dependencies.
An advisory means the version recorded in the dependency graph falls inside an advisory’s affected range. Reachability is not analysed, and the graph includes development and test pins — a finding may concern tooling rather than shipped software.
Raw JSON report machine-readable
{
"data": {
"repo": {
"topics": [],
"is_fork": false,
"size_kb": 328,
"has_wiki": true,
"homepage": null,
"languages": {
"JavaScript": 1580,
"TypeScript": 543831
},
"pushed_at": "2026-07-30T05:49:43Z",
"created_at": "2026-03-05T23:13:13Z",
"owner_type": "Organization",
"updated_at": "2026-07-21T17:48:39Z",
"description": null,
"is_archived": false,
"is_disabled": false,
"license_spdx": null,
"default_branch": "main",
"license_spdx_raw": null,
"primary_language": "TypeScript",
"significant_languages": [
"TypeScript"
]
},
"owner": {
"blog": null,
"name": null,
"type": "Organization",
"login": "agnt-ai",
"company": null,
"location": null,
"followers": 0,
"avatar_url": "https://avatars.githubusercontent.com/u/265096669?v=4",
"created_at": "2026-03-02T18:48:23Z",
"is_verified": null,
"public_repos": 1,
"account_age_days": 149
},
"license": {
"state": "absent",
"spdx_id": null,
"raw_spdx": null,
"file_present": false,
"scorecard_found": false,
"profile_has_license": false
},
"activity": {
"releases": [],
"recent_commits": [
{
"oid": "4466aa121034e6e3cff606453b465af50690e36f",
"body": "…opic (adaptive thinking/effort) [0.0.44] (#23)\n\n* feat(studio): route OpenAI reasoning family through /v1/responses [0.0.44]\n\nOpenAI's reasoning family (o1/o3/o4, gpt-5.x) is now served over the\nResponses API (/v1/responses) instead of Chat Completions. Chat\nCompletions hard-400s the one combinatio\n[…]\nupport changes.\n\nCo-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>\nCo-authored-by: Anindya Mondal <mondal.anindya91@gmail.com>",
"is_bot": false,
"headline": "feat(studio): reasoning support across OpenAI (/v1/responses) + Anthr…",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-07-21T17:47:07Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "0fea7b3d33cd3ed593c27236b6cd2c6afc160911",
"body": "Includes the Moonshot provider registration (#21) and the critical\nfallback-model-leak fix (#22).\n\nCo-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore(studio): bump @agnt-sdk/studio to 0.0.43",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-07-17T21:54:53Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "49323d9915c1bbad3f521098a53e44986c430ba7",
"body": "…back turn (#22)\n\nBaseExecutor instances are reused across every turn of a multi-turn tool\nloop. When invokeWithFallback() falls back cross-provider mid-run (e.g.\nAnthropic -> OpenAI gpt-5.4), it mutates this.primaryModelConfig/provider/\nmodel to the fallback identity for trace/cost attribution. On \n[…]\nrces a fallback that succeeds and turn 2 asserts\nthe request goes out via the original provider/model, not turn 1's\nleftover fallback identity.\n\nCo-authored-by: Claude Sonnet 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(studio): reset primary model at the start of every invokeWithFall…",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-07-17T21:35:49Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "b4a053511f2909fff4ebb93f12b823b9c597f983",
"body": "…K3) (#21)\n\nRegisters 'moonshot' in OPENAI_COMPATIBLE_BASE_URLS (api.moonshot.ai/v1),\nrouting it through the existing OpenAICompatibleExecutor with no new\nadapter. Kimi K3 always runs internal reasoning and rejects the classic\nsampling params, so it gets the same max_tokens -> max_completion_tokens\ntranslation and legacy-param stripping already used for OpenAI's\no-series/gpt-5.x reasoning family.\n\nCo-authored-by: Claude Sonnet 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(studio): add Moonshot AI as an OpenAI-compatible provider (Kimi …",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-07-17T21:23:37Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "c163ff5bbd5e26f22bb28dbf1c2b5bbc7199d68b",
"body": "…h (#20)\n\nAn unpaired surrogate (half an emoji left by upstream string truncation —\n`.slice(0, n)` / a byte cap cutting mid-pair) makes the JSON request body\ninvalid. Anthropic (and every strict JSON encoder) rejects it with a\nnon-retryable `400 invalid_request_error: \"The request body is not valid \n[…]\natch-boundary integration tests (incl. the exact incident\n shape: a title truncated to a trailing lone high surrogate)\n- bump 0.0.41 -> 0.0.42\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(studio): well-form lone UTF-16 surrogates before provider dispatc…",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-07-16T20:57:53Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "7d708d7445499bba2f5efd136026d3c11b754117",
"body": "… reasoning-family models (#19)\n\nOpenAIExecutor had zero per-model param translation: it passed an account's\nmodel-strategy metadata straight through as literal OpenAI request params.\nWhen cross-provider fallback tried openai/gpt-5.4 (whose metadata carries\nmax_tokens, mirroring the Anthropic-model \n[…]\nge.json files that pin the version and\nwill need updating separately once this is published to npm — tracked as a\nfollow-up, out of scope here.\n\nCo-authored-by: Claude Sonnet 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(studio): translate max_tokens -> max_completion_tokens for OpenAI…",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-07-16T15:33:13Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "7e273448e28f8ff293f45181aa6fb118badf7c56",
"body": "Includes #18 — rescue direct-call tool args that collapse to a\nsingle stringified params key.",
"is_bot": false,
"headline": "chore(studio): bump @agnt-sdk/studio to 0.0.40",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-07-15T00:47:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f406b41f91bf9d4e39fbd6da8ebddf4ba54d3737",
"body": "…fied params key (#18)\n\nProduction prime-agent runs show models frequently calling direct-schema\ntools (e.g. create_task) by wrapping the entire argument set inside a\nsingle non-schema `params` key holding a JSON string — mimicking the\ngeneric execute_tool({tool_name, params}) meta-tool shape — inst\n[…]\nlt falls through to normal validation, but logs a diagnostic first\nso a future failure is traceable instead of repeating the same opaque\nerror.\n\nCo-authored-by: Claude Sonnet 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(studio): rescue direct-call tool args wrapped in a single stringi…",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-07-15T00:46:35Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "3cf2a34aeff5b5cb711c001cc0a8fdae2eb1ecec",
"body": "Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore(studio): bump version to 0.0.39",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-07-08T02:51:54Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "be910669bf3a5ec4263d489286c8bcb5f69332c8",
"body": "Adds AzureFoundryExecutor, a new adapter for Azure AI Foundry's unified\nModel Inference API (OpenAI wire-compatible, but api-key/api-version auth\nscoped to a per-resource endpoint rather than a bearer token against a\nshared base URL). Wired into executorFactory under provider \"azureFoundry\".\n\nCo-authored-by: Claude Sonnet 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(studio): add Azure AI Foundry as an LLM provider (#17)",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-07-08T02:49:13Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "5711675c12743872b594fe46d2bad8b66155bb5b",
"body": "…asoning_content recovery + Gemini tool-result parse [0.0.38] (#16)\n\n* fix(studio): replay assistant tool_calls in OpenAI wire format (multi-turn tool loops)\n\n#formatMessages dropped an assistant message's tool_calls when replaying\nhistory, so on the next turn the tool result had no matching tool ca\n[…]\nkens>0 + no\ntool_calls -> retryable 502 rather than a silent empty result).\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(studio): OpenAI-compat adapter robustness — tool-call replay + re…",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-07-06T18:03:01Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "8e9fbcddd8a9015cd165e852ab89dedb0850b5e6",
"body": null,
"is_bot": false,
"headline": "chore(studio): bump version to 0.0.37",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-07-06T14:38:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3c5bb0b2014b7a1ebc66a4e9178b4d8f7e9b1f86",
"body": "…atible adapter (#15)\n\nThe console strategy editor writes temperature/maxTokens to the top-level\nV2ModelConfig fields, but every adapter reads params from metadata only — so a\ntemperature set in the console silently did nothing for openai-style providers\n(Together/Kimi/Qwen/DeepSeek/OpenAI). Source both: top-level fields feed the\ncall, metadata still overrides on a key collision. maxTokens → max_tokens.\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(studio): honor top-level temperature/maxTokens in the openai-comp…",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-07-06T14:38:25Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "4eda2cc7b1e3ee91246277c4d78f885313118fa4",
"body": "Publishes the Together/Kimi/Qwen model-routing work from #14.\n\nCo-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore(studio): bump version to 0.0.36",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-07-03T19:49:35Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "46574fe6175a2e946c01a1e2a40ace6b0e59f20a",
"body": "…er (cache capture + streaming) (#14)\n\n* feat(studio): stream model responses with an idle timeout (remove the long-response ceiling)\n\nPrime's model calls were awaited as a single non-streamed completion, so the\nSDK's per-attempt timeout measured TOTAL time-to-complete. A long-but-\nprogressing respo\n[…]\n, build clean.)\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>\nCo-authored-by: Anindya Mondal <mondal.anindya91@gmail.com>",
"is_bot": false,
"headline": "feat(studio): Together/Kimi/Qwen via a shared OpenAI-compatible adapt…",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-07-03T19:48:29Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "fe0918cdb678e15913f7d0c7252bfe80b7cdef30",
"body": "… long-response ceiling) (#13)\n\nPrime's model calls were awaited as a single non-streamed completion, so the\nSDK's per-attempt timeout measured TOTAL time-to-complete. A long-but-\nprogressing response (a full deck / report) could exceed it, get retried\n(re-sending + re-billing the whole prompt), and\n[…]\nd this carries the maxRetries 5->3 reconciliation itself, so #12 can be\nclosed. Publish + backend pin bump to take effect (same path as #1818).\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(studio): stream model responses with an idle timeout (remove the…",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-07-03T14:20:55Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "14f2bcbba014694eb78f3a18ce313d3ee12921b7",
"body": "* fix(studio): implement cross-provider model fallback (don't strand tasks when all same-provider models time out)\n\ninvokeWithFallback walked the model list but `continue`d past any model\nwhose provider differed from the current executor, logging \"cross-provider\nnot yet implemented\". In practice thi\n[…]\nresolved once upstream in\nAgntExecutor) — documented but not fixed here.\n\n---------\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>\nCo-authored-by: Anindya Mondal <mondal.anindya91@gmail.com>",
"is_bot": false,
"headline": "fix(studio): implement cross-provider model fallback (#11)",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-07-02T17:36:55Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "91cf40cae375ae7744d86fb21b58399ac5abb0b0",
"body": "…he_read=0) (#10)\n\nStaging traces showed cache_read=0 with cache_creation≈full input every turn —\nthe whole prefix (system included) re-written each turn, nothing read. Root\ncause: the default path set a TOP-LEVEL `params.cache_control`, which Anthropic\ndoes not honor (cache_control lives on content\n[…]\n_agent_run\" change — disableCache there would lose the\nprefix READ to save a negligible delta WRITE (net negative after this fix).\n\nCo-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(studio): always-on block-level Anthropic prompt caching (fix cac…",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-06-24T13:38:44Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "03b1ae2ce5a6ba9b0be8d73ff7b6d66bdf3ae982",
"body": "… + broaden isRetryableError (#9)\n\n* fix(studio): harden transient-fault retries — maxRetries + broaden isRetryableError (0.0.32)\n\nLLM calls were surfacing 529 (Anthropic overloaded) as hard errors mid-run.\nTwo layers were under-provisioned:\n\n1. Provider SDK clients were constructed with no maxRetri\n[…]\ntext) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Paul Canetti <pc@skej.com>\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>\nCo-authored-by: Anindya Mondal <mondal.anindya91@gmail.com>",
"is_bot": false,
"headline": "fix(studio): harden transient-fault retries (529 et al.) — maxRetries…",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-06-23T19:16:47Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "7d86fe26320bbd6fa53b2378eb5ca981e75093a6",
"body": "… of the cached prefix (#8)\n\n* feat(studio): RR release_after_read — keep read-once tool results out of the cached prefix (Anthropic)\n\nRUNTIME_EFFICIENCY.md Phase 2. When the agent declares a tool result will be\nread once and dropped, avoid paying the cache-write surcharge on content that's\nabout to\n[…]\n-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>\nCo-authored-by: Anindya Mondal <mondal.anindya91@gmail.com>",
"is_bot": false,
"headline": "feat(studio): RR release_after_read — keep read-once tool results out…",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-06-23T16:30:15Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "265597ab4b1e3a941c37d2544f7a9a6a426b33a3",
"body": "When the LLM calls a tool that doesn't exist directly (e.g. `search_drive`),\nBaseExecutor returned a dead-end \"Tool not found\" with no recovery path. The\nagent would fall back to unrelated tools and give up without finding the file.\n\nNow the error mirrors execute_tool's wall-hit message: it tells th\n[…]\n → agent\nfell back to AGNT internal drive and falsely told the user \"nothing in your\ndrive\" without ever searching Google Drive.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: improve unknown-tool error to hint at fetch_tools lazy-load pattern",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-19T16:35:19Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "af6a0fc328585be9a578f15d33fdeb50d9839f7d",
"body": "….30) (#7)\n\nBuilds on #6 (array/object coercion at the direct-call boundary). The LLM\nstringifies primitive args too — `limit: \"5\"`, `dryRun: \"true\"` — and tools\nthat don't self-coerce abort downstream (the dispatch executor read\n`payload.meetingId` off a raw string and killed the whole cart with a\n\n[…]\nthe lossless guards,\nbig-int preservation, loose-boolean rejection, and the string-union guard.\nFull studio suite green (129/129).\n\nCo-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(studio): extend arg normalization to number/integer/boolean (0.0…",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-06-19T14:49:52Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "ab9fd86a7ec17f48cae030ebe8da708df1f35465",
"body": "Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore: bump @agnt-sdk/studio to 0.0.29",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-18T18:08:39Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "3fb70228d8271d7a4bf50af225c4d7e64d51e0a2",
"body": "…call boundary (#6)\n\nAdd schema-aware normalizeToolArgs() in BaseExecutor.handleToolCalls so the\nLLM's stringified array/object arguments on direct tool calls get JSON-parsed\nto their declared types, matching the existing execute_tool meta-tool path.\n\nOnly coerces top-level params whose schema decla\n[…]\nfailures are left untouched for normal downstream validation. Copy-on-write so the\ncaller's args object is never mutated in place.\n\nCo-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(studio): normalize stringified array/object tool args at direct-…",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-06-18T18:07:35Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "92caca40e3a52747186a000b5919235801257e7c",
"body": "Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(executorFactory): alias 'gemini' provider to GoogleExecutor",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-16T15:29:01Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "b84e56ea679f7798eb46342bf0703f1f0f0d28e3",
"body": "feat(studio): cross-provider file (PDF) attachment support (0.0.28)",
"is_bot": false,
"headline": "Merge pull request #5 from agnt-ai/feat/cross-provider-file-attachments",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-16T15:14:18Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c58b71c8443e8fb99b879e1303610612d9fd954e",
"body": "…ders\n\nPins the cross-provider contract end to end at the adapter boundary (real\n#formatContent via invoke() with mocked SDK clients), not just the pure helpers:\n- Anthropic: image_url → image.source.base64; file → document(+title)\n- Google: image_url AND file → inlineData parts\n- OpenAI: both pass through unchanged (native)\n\nCloses the gap that the image_url path had no direct SDK test.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "test(studio): adapter-level image_url + file translation across provi…",
"author_name": "paulcanetti",
"author_login": "paulcanetti",
"committed_at": "2026-06-16T15:04:06Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "e34bb10c66e01b5587cc1d041f0bc73e21b726c0",
"body": "Provider adapters only translated `text` and `image_url` blocks, so a PDF/file\nattachment worked only on Anthropic (its adapter passes unknown blocks through\nto the native SDK). Gemini silently dropped it; OpenAI/Bedrock didn't handle it.\n\nAdd a cross-provider `file` content block — OpenAI-native sh\n[…]\ns the block as-is)\n\nWired into anthropic/google/bedrock #formatContent. 13 unit tests for the\ntranslators; full suite green (105).\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(studio): cross-provider file (PDF) attachment support — bump 0.0.28",
"author_name": "paulcanetti",
"author_login": "paulcanetti",
"committed_at": "2026-06-16T14:47:25Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "d02043a4d688df993424048ee8f7dbd45f602e68",
"body": null,
"is_bot": false,
"headline": "chore: bump @agnt-sdk/studio to 0.0.27 (parallel tool calls)",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-09T02:20:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c86bd0cb844086e9335fac03f67f5c4a41729df3",
"body": "feat(studio): allow parallel tool calls across all providers",
"is_bot": false,
"headline": "Merge pull request #4 from agnt-ai/feat/allow-parallel-tool-calls",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-09T02:17:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ae7bfe434c34c9b111850176eaf8de66fd29de94",
"body": "Audited every provider's tool_choice handling:\n- anthropic: dropped the hardcoded disable_parallel_tool_use:true (was the\n only provider actively disabling parallel).\n- openai: set parallel_tool_calls:true explicitly when tools are present (it's\n OpenAI's default, made explicit so it can't silentl\n[…]\ny model family can now emit multiple tool calls in one turn while\n'required'/'any' still forces at least one (progress preserved).\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(studio): ensure parallel tool calls across ALL providers",
"author_name": "paulcanetti",
"author_login": "paulcanetti",
"committed_at": "2026-06-08T19:46:34Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "43e5b3035408d21fa02d04f38b27b5fc4b8dcfae",
"body": "The anthropic provider hardcoded `disable_parallel_tool_use: true` for\nrequired/any tool_choice — stricter than Anthropic's own default (parallel\nallowed) and with no stated reason. It serialized every agent run to one tool\ncall per turn, even when the model wanted to fire independent calls at once\n\n[…]\nby the loop.\n\nConsumers whose per-turn logic assumed exactly one tool call should verify, but\nthe executor itself handles batches.\n\nCo-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(studio): allow parallel tool calls (anthropic provider)",
"author_name": "paulcanetti",
"author_login": "paulcanetti",
"committed_at": "2026-06-08T19:34:05Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "e939ce2830aebb7b6014305c12ea85e03de631ab",
"body": "Wrap array functionResponse.response in { result: [...] } —\nGemini proto requires the response field to be an object, not a list.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "Fix Gemini array tool result rejection",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-08T16:12:52Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "84805714846f5b270694521ad95285827fc54f03",
"body": "rawParts is a first-class field on Message for preserving raw provider\nresponse parts across turns. GoogleExecutor stores candidate parts on\nevery response and echoes them back verbatim when rebuilding history,\nsatisfying the thought_signature requirement on Gemini thinking models.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "Add rawParts to Message, fix Gemini thought_signature passthrough",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-08T15:57:51Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "334efbb7583063b632046f1aeb80958ca3d8a280",
"body": null,
"is_bot": false,
"headline": "chore: bump @agnt-sdk/studio to 0.0.23",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-07T05:06:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "da5e3f6578b330595da368434ac14e6c26c5f0a3",
"body": "Bedrock requires all tool results from parallel tool calls to be in a single\nuser message as multiple toolResult content blocks. Previously each result\nwas pushed as its own message, causing \"Expected toolResult blocks\" errors\nwhen Nova returned parallel tool calls.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(bedrock): merge consecutive tool results into one user message",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-07T05:05:56Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "322685e33bbffe7b4a5383bcd9e5fe64ca0b6a9d",
"body": "Price the four token buckets — uncached input, output, cache read, cache\nwrite — each at its own per-model rate, correctly across providers.\n\n- calculateCost: drop the Anthropic-specific cache-rate fallbacks (cacheRead\n defaulting to 0.1x input, cacheCreation to 1.25x). A null catalog rate now\n co\n[…]\n LangSmith aggregate is fixed, not regressed.\n\nTests: 92/92 (16 new across cost + provider-usage). Bump to 0.0.22 before publish.\n\nCo-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(studio): cache-aware, provider-agnostic token cost (#3)",
"author_name": "PC",
"author_login": "paulcanetti",
"committed_at": "2026-06-07T02:02:58Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "98eeb837f8734fefe3187a10308a96cecfc63bde",
"body": "…v0.0.21\n\n- Add disableCache to BaseExecutorConfig (createExecutor callers can now pass it)\n- BaseExecutor stores it, passes to invokeWithFallback on every turn\n- Both execute() invoke sites updated\n\nCombined with the InvokeOptions.disableCache added in v0.0.20, this means\ncreateExecutor({ disableCache: true }) fully skips cache_control end-to-end\nwithout any caller needing to monkey-patch the SDK client.\n\nCo-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(executor): thread disableCache through BaseExecutor.execute() — …",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-03T14:27:23Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "2802e2cee0ade564c053aa24e0bab9bafd87e271",
"body": "AnthropicExecutor skips cache_control when options.disableCache is true.\nOne-shot callers (QA, ignore checks, vision, etc.) should pass this to\navoid the 25% cache-write surcharge with no benefit. Multi-turn Prime\nruns omit it and continue to cache the system prompt.\n\nPublished as @agnt-sdk/studio@0.0.20.\n\nCo-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(executor): add disableCache option to InvokeOptions — v0.0.20",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-06-03T14:22:54Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "e350bedacb2aae16d88af26139ab7854893d6523",
"body": "feat(studio): model fallback on retryable LLM errors",
"is_bot": false,
"headline": "Merge pull request #2 from agnt-ai/feat/model-fallback-on-error",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-28T15:00:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e402afa33b3fa895bdc4ff2ee3f6243dce4907f3",
"body": "BaseExecutor had no fallback logic — selectPrimaryModel() picked one\nmodel at construction time, and both invoke() call sites in execute()\nand runToolLoop() were wrapped only by a catch-all that returned\n{ ok: false } with no retry attempt.\n\nAdd invokeWithFallback() that:\n- Sorts manifest.spec.model\n[…]\nr\n Node.js: ECONNRESET, ECONNREFUSED, ETIMEDOUT, ENOTFOUND, EAI_AGAIN\n Pattern: overloaded|rate limit|server error|timeout|connection reset\n\nCo-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(studio): model fallback on retryable LLM errors",
"author_name": "paulcanetti",
"author_login": "paulcanetti",
"committed_at": "2026-05-28T04:01:29Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "a5264b835cdc947a565cc2fdf0382befeea2cc3e",
"body": "…(0.0.18)\n\ninputTokens stays as sum-of-all-types for Trace/console display so\ntoken count correlates with cost. cacheCreationTokens and cacheReadTokens\ncarry the breakdown. Cost calculation uses breakdown to apply correct\nrates per type.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: inputTokens = total for display, breakdown fields for cost calc …",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-27T18:47:18Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "ce2ef2549ed468fa5be8dfa5cdbb6ab81ad67f35",
"body": "Usage now tracks inputTokens, cacheCreationTokens, cacheReadTokens\nseparately across tool loop turns. Final cost is calculated from the\nper-type totals with correct rates (creation=1.25x, read=0.1x) instead\nof applying flat inRate to a mixed sum — prevents 10x overcharge on\ncache-read turns. (0.0.17)\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: track cache token types separately for accurate cost calculation",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-27T18:34:26Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "1ee388ec57fd76969653e1294689048bb476fe43",
"body": "Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add cacheCreationTokens/cacheReadTokens to TracePayload (0.0.16)",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-26T22:06:59Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "fb4048072699149c6401f03fe2292055f949a1e3",
"body": "sendTurnTrace was passing turnUsage.input_tokens directly, dropping\ncache_creation_input_tokens and cache_read_input_tokens entirely.\nSystem prompt goes into cache on first call — so LangSmith was showing\nonly the user message tokens (~25) not the real total (500+).\n\nNow uses sumInputTokens() for inputTokens/totalTokens, and records\ncacheCreationTokens + cacheReadTokens as separate fields for observability.\nBumped to 0.0.15.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: include cache tokens in LangSmith trace inputTokens",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-26T21:52:54Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "0f4ac02e9bcbf6c4ffe388461a1433751b73821d",
"body": "- ModelPricing now includes cacheCreationTokensPer1M and\n cacheReadTokensPer1M (nullable for providers without cache)\n- calculateCost() reads these from the catalog instead of hardcoded\n 1.25× / 0.10× multipliers; falls back to those multipliers if not\n seeded yet\n- Bumped to 0.0.14\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: use stored cache rates from ModelPricing catalog",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-26T21:39:10Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "28b9bbd50d4e3d941b56037dd6a2d7f93662aa57",
"body": null,
"is_bot": false,
"headline": "chore: bump @agnt-sdk/studio to 0.0.13",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-26T21:35:29Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "65e5326aea450c8e67129519d994617ba97d5304",
"body": "Anthropic splits usage into input_tokens (uncached),\ncache_creation_input_tokens, and cache_read_input_tokens. System prompt\ngoes into cache — previously only uncached tokens were counted, making\nevery run appear ~25 tokens instead of the real 500+.\n\n- sumInputTokens() sums all three fields\n- calcul\n[…]\ne object with correct multipliers:\n cache creation 1.25×, cache read 0.1× input rate\n- Both no-tool and tool-loop paths updated\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: count cache_creation and cache_read tokens in input token total",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-26T21:34:55Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "b5253b90a2478c738f93f20dc230812956fe47c7",
"body": "…0.12)",
"is_bot": false,
"headline": "feat: model pricing from API — fix hardcoded Sonnet cost fallback (0.…",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-26T15:35:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "700bcc1e93be8ba18c8adeea58a2f6cde7c93a75",
"body": "Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore: bump @agnt-sdk/studio to 0.0.12",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-26T15:21:15Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "0e078890650ee16a5b91d19fac050d16f3a5f341",
"body": "BaseExecutor.ts:\n- Accept modelPricing in BaseExecutorConfig and constructor\n- calculateCost() now uses correct per-model rates when provided\n- Hardcoded Sonnet fallback ($3/$15) only fires if pricing not supplied\n\nAgntApiClient (api.ts):\n- New getModels() → GET /models — fetches account's AiModel p\n[…]\nlt.usage.totalCostUSD and POST /traces cost are now accurate for all\nmodels (Opus, Haiku, GPT-4, Gemini, etc.), not just Sonnet.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: model pricing from API — fix hardcoded Sonnet cost fallback",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-26T15:13:31Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "17a378edd4825accf71adfd67a5d31e4a5a68ec3",
"body": "Pre-existing conversation history should not count against maxMessages.\nAgents with long chat context (e.g. ignore-check on a 64-message chat)\nwere hitting the limit immediately even for one-shot checks.\n\nTrack _initialMessageCount and check (length - initial) >= maxMessages.\n\nBumps @agnt-sdk/studio 0.0.10 → 0.0.11.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "Fix BaseExecutor: maxMessages counts only new tool-turn messages",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-05-18T01:11:22Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "9e40808c6c3e020161fc2386bb4c82610e096636",
"body": null,
"is_bot": false,
"headline": "chore: bump @agnt-sdk/studio to 0.0.10",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-04-28T02:42:22Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "06e52840a18f4a54f8c23eca973436878024e27d",
"body": "* feat: add prompt caching to all provider adapters\n\n- AnthropicExecutor: top-level cache_control on every request (automatic\n caching — Anthropic handles breakpoint placement). Surfaces\n cache_read_input_tokens and cache_creation_input_tokens in usage return.\n- OpenAIExecutor: surfaces cache_read\n[…]\ny: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>\nCo-authored-by: Anindya Mondal <mondal.anindya91@gmail.com>",
"is_bot": false,
"headline": "feat: prompt caching — all provider adapters (#1)",
"author_name": "paulcanetti",
"author_login": "paulcanetti",
"committed_at": "2026-04-28T02:41:44Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "1b392efc67e410434358bc27d7a684df699c60a4",
"body": "Bedrock requires toolResult.content[].json to be a plain object.\nString and array results now use the text content type instead.\nBump to v0.0.9.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(bedrock): use text block for non-object tool results",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-26T08:26:24Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "55bc4cc8a46fa765af451da30b4dd912c4611892",
"body": "… message formatting\n\nBedrock rejects empty text fields; assistant messages with tool calls now\ninclude toolUse blocks and skip empty text content. Bump to v0.0.8.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(bedrock): handle blank text blocks and missing toolUse content in…",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-26T08:13:34Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "9a864088f077f2557edf521fcc3f6b23c532c9d1",
"body": "…ases\n\nagnt-node's BedrockExecutor uses model ID as-is (no transformation).\nBedrock system-defined inference profile format (us. prefix) is handled\nby modelAliases.mjs in the agnt backend.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(bedrock): agnostic executor — move us. prefix to backend modelAli…",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-25T19:16:52Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "5b71ca4b3465a25340d07394e7a32cac7f96882e",
"body": "…demand throughput\n\nCross-region inference profile ARNs require aws-marketplace permissions.\nRaw model IDs work with on-demand throughput in the same region without\nmarketplace subscription.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(bedrock): revert inference profile ARN — use raw model ID for on-…",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-25T18:40:30Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "922f694db10111890c7a879640f600900cefee46",
"body": "Allows callers (e.g. InternalExecutor) to register llm_output hooks via\nHookRegistry to write per-turn traces to the DB without requiring a\ntracing config to be set.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: fire llm_output hook after each LLM turn for DB tracing",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-23T01:28:32Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "1ad4a2bd527a23c62cd1a5f1914fbc63e7cfeb97",
"body": "Bedrock requires an inference profile ARN for Claude 4.x models —\ninvoking the raw model ID with on-demand throughput is not supported.\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(bedrock): wrap model ID as cross-region inference profile ARN",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-20T23:40:08Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "51669fc545cb145fc3aadd58c229170364b96624",
"body": "- Add HookRegistry class for lifecycle hooks (before_agent_start, before_tool_call, etc.)\n- Add openclawAdapter for tool result format normalization (OpenClaw ↔ AGNT)\n- Export HookRegistry, HookEvent, HookHandler from index\n- Add OpenClawToolResult type to types.ts\n- Bump version to 0.0.4\n\nCo-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: add HookRegistry, OpenClaw adapter, and bump to v0.0.4",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-18T18:15:57Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "343ac1784b235a765c3a2d35d99c62a82d097d6f",
"body": null,
"is_bot": false,
"headline": "fix: bin path and version bump to 0.0.3",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-06T16:23:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "91250af11dc57957c7e8b779be489fce8e09cc6a",
"body": "Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "test: add BaseExecutor unit tests for component resolution and logLevel",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-06T16:22:16Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "150646b1bc0d63d0bab6cff3973e1f3f4a51edc5",
"body": "- Add logLevel ('debug' | 'info' | 'silent') to BaseExecutorConfig; wire\n this.debug for verbose LLM payload logging in AnthropicExecutor\n- Fix populateTemplate to resolve inline {component.name} references\n against resolvedDependencies.components (handles mixed text + refs)\n- Fix AgntExecutor fil\n[…]\nory and create it if missing\n- Fix ChatsResource.process to normalize suppressed/ignored response shape\n- Add live test for chat process flow\n\nCo-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: logLevel config, component ref resolution, and file path fix",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-06T16:19:23Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "4aa690591d68ee519bcd235cffa40428de9ced9a",
"body": "- Add src/__tests__ to tsconfig exclude in both config and client\n packages so test files are not compiled into dist/\n- Bump config and client to 0.0.2 with clean publish\n\nCo-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: exclude __tests__ from dist, bump to 0.0.2",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-05T23:15:07Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "08e7599ad0c8f35e0897fdef91280187fffd67cc",
"body": "Introduces three packages that together form the official Node.js SDK\nfor the Agnt platform:\n\n**@agnt-sdk/config**\n- Shared AgntConfig type and agnt.config.js file-discovery loader\n- Walks up the directory tree from cwd, supports JS and TS variants\n\n**@agnt-sdk/client**\n- Typed REST client covering \n[…]\nhrough live testing, including envelope format,\n field names, and behavioral notes (e.g. primary identifier\n auto-provisioned on user sync)\n\nCo-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: initial release of @agnt-sdk monorepo (v0.0.1)",
"author_name": "Anindya Mondal",
"author_login": "Anindya91",
"committed_at": "2026-03-05T23:14:04Z",
"body_truncated": true,
"is_coding_agent": true
}
],
"releases_count": 0,
"commits_last_year": 66,
"latest_release_at": null,
"latest_release_tag": null,
"releases_from_tags": false,
"days_since_last_push": 0,
"active_weeks_last_year": 14,
"days_since_latest_release": null,
"mean_days_between_releases": null
},
"community": {
"has_readme": true,
"has_license": false,
"has_description": false,
"has_contributing": false,
"health_percentage": 12,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": [
{
"name": "@agnt-sdk/client",
"exists": true,
"license": "MIT",
"keywords": [
"agnt",
"api-client",
"tasks",
"ai-assistant",
"typescript"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@agnt-sdk/client",
"is_deprecated": false,
"latest_version": "0.0.2",
"repository_url": "https://github.com/agnt-ai/agnt-node",
"versions_count": 2,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 483,
"first_published_at": "2026-03-05T23:14:20.752000Z",
"latest_published_at": "2026-03-05T23:15:01.021000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 146
},
{
"name": "@agnt-sdk/config",
"exists": true,
"license": "MIT",
"keywords": [
"agnt",
"config",
"typescript"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@agnt-sdk/config",
"is_deprecated": false,
"latest_version": "0.0.2",
"repository_url": "https://github.com/agnt-ai/agnt-node",
"versions_count": 2,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 944,
"first_published_at": "2026-03-05T23:14:14.961000Z",
"latest_published_at": "2026-03-05T23:14:59.248000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 146
},
{
"name": "@agnt-sdk/studio",
"exists": true,
"license": "MIT",
"keywords": [
"llm",
"executor",
"agent",
"agnt",
"anthropic",
"openai",
"bedrock",
"deepseek",
"google",
"gemini",
"cli",
"prompt-manifest"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@agnt-sdk/studio",
"is_deprecated": false,
"latest_version": "0.0.45",
"repository_url": "https://github.com/agnt-ai/agnt-node",
"versions_count": 44,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 2608,
"first_published_at": "2026-03-06T16:19:57.708000Z",
"latest_published_at": "2026-07-21T17:49:42.236000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 8
}
]
},
"popularity": {
"forks": 0,
"stars": 0,
"watchers": 0,
"fork_history": {
"days": [],
"complete": true,
"collected": 0,
"total_forks": 0
},
"star_history": {
"days": [],
"complete": true,
"collected": 0,
"total_stars": 0,
"collected_at": null
},
"open_issues_and_prs": 1
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [],
"has_llms_txt": false,
"has_dockerfile": false,
"has_mcp_signal": false,
"bootstrap_files": [],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [
"packages/client/tsconfig.json",
"packages/config/tsconfig.json",
"packages/studio/tsconfig.json"
],
"toolchain_manifests": [],
"largest_source_bytes": 52203,
"source_files_sampled": 79,
"oversized_source_files": 0,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"dependencies": {
"manifests": [
"package.json"
],
"advisories": {
"error": null,
"scope": "published_package",
"source": "osv",
"findings": [],
"collected": true,
"malicious": [],
"truncated": false,
"by_severity": {},
"advisory_count": 0,
"affected_count": 0,
"assessed_count": 2,
"malicious_count": 0,
"assessed_package": "npm:@agnt-sdk/client@0.0.2",
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [
"npm"
],
"dependencies": [
{
"name": "@agnt-sdk/config",
"manifest": "packages/client/package.json",
"ecosystem": "npm",
"version_constraint": "*"
},
{
"name": "jose",
"manifest": "packages/client/package.json",
"ecosystem": "npm",
"version_constraint": "^5.9.6"
},
{
"name": "@agnt-sdk/config",
"manifest": "packages/studio/package.json",
"ecosystem": "npm",
"version_constraint": "*"
},
{
"name": "@anthropic-ai/sdk",
"manifest": "packages/studio/package.json",
"ecosystem": "npm",
"version_constraint": "^0.112.4"
},
{
"name": "@aws-sdk/client-bedrock-runtime",
"manifest": "packages/studio/package.json",
"ecosystem": "npm",
"version_constraint": "^3.705.0"
},
{
"name": "@google/generative-ai",
"manifest": "packages/studio/package.json",
"ecosystem": "npm",
"version_constraint": "^0.24.1"
},
{
"name": "commander",
"manifest": "packages/studio/package.json",
"ecosystem": "npm",
"version_constraint": "^12.1.0"
},
{
"name": "openai",
"manifest": "packages/studio/package.json",
"ecosystem": "npm",
"version_constraint": "^4.77.3"
}
],
"all_dependencies": {
"error": "GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository",
"source": null,
"packages": [],
"collected": false,
"truncated": false,
"total_count": null,
"direct_count": null,
"indirect_count": null
}
},
"maintainership": {
"issues": {
"open_prs": 1,
"merged_prs": 22,
"open_issues": 0,
"closed_ratio": null,
"closed_issues": 0,
"closed_unmerged_prs": 1
},
"bus_factor": 1,
"bot_contributors": 0,
"top_contributors": [
{
"type": "User",
"login": "Anindya91",
"commits": 47,
"avatar_url": "https://avatars.githubusercontent.com/u/8134115?v=4"
},
{
"type": "User",
"login": "paulcanetti",
"commits": 19,
"avatar_url": "https://avatars.githubusercontent.com/u/143139243?v=4"
}
],
"contributors_sampled": 2,
"top_contributor_share": 0.712
},
"quality_signals": {
"has_ci": false,
"has_tests": true,
"ci_workflows": [],
"has_docs_dir": true,
"linter_configs": [],
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [
"package-lock.json"
],
"scorecard": {
"checks": [
{
"name": "Binary-Artifacts",
"score": 10,
"reason": "no binaries found in the repo",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#binary-artifacts"
},
{
"name": "Branch-Protection",
"score": null,
"reason": "internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": 0,
"reason": "0 out of 19 merged PRs checked by a CI test -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#ci-tests"
},
{
"name": "CII-Best-Practices",
"score": 0,
"reason": "no effort to earn an OpenSSF best practices badge detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#cii-best-practices"
},
{
"name": "Code-Review",
"score": 5,
"reason": "Found 14/28 approved changesets -- score normalized to 5",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 0,
"reason": "project has 0 contributing companies or organizations -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
},
{
"name": "Dangerous-Workflow",
"score": null,
"reason": "no workflows found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
},
{
"name": "Dependency-Update-Tool",
"score": 0,
"reason": "no update tool detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
},
{
"name": "Fuzzing",
"score": 0,
"reason": "project is not fuzzed",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
},
{
"name": "License",
"score": 0,
"reason": "license file not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 10,
"reason": "30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
},
{
"name": "Packaging",
"score": null,
"reason": "packaging workflow not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
},
{
"name": "Pinned-Dependencies",
"score": null,
"reason": "no dependencies found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
},
{
"name": "SAST",
"score": 0,
"reason": "SAST tool is not run on all commits -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
},
{
"name": "Security-Policy",
"score": 0,
"reason": "security policy file not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
},
{
"name": "Signed-Releases",
"score": null,
"reason": "no releases found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
},
{
"name": "Token-Permissions",
"score": null,
"reason": "No tokens found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
},
{
"name": "Vulnerabilities",
"score": 0,
"reason": "17 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "4466aa121034e6e3cff606453b465af50690e36f",
"ran_at": "2026-07-30T10:38:14Z",
"aggregate_score": 3,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": false,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"ci_last_run_at": "2026-07-21T17:47:10Z",
"oldest_open_prs": [
{
"number": 24,
"created_at": "2026-07-30T05:51:04Z",
"last_comment_at": "2026-07-30T05:53:55Z",
"last_comment_author": "paulcanetti"
}
],
"last_merged_pr_at": "2026-07-21T17:47:08Z",
"ci_last_conclusion": null,
"oldest_open_issues": []
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/agnt-ai/agnt-node",
"host": "github.com",
"name": "agnt-node",
"owner": "agnt-ai"
},
"metrics": {
"overall": {
"key": "overall",
"band": "at_risk",
"name": "Overall health",
"note": null,
"notes": [],
"value": 42,
"inputs": {
"security": 44,
"vitality": 44,
"community": 24,
"governance": 54,
"engineering": 40
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "at_risk",
"name": "Vitality",
"value": 44,
"weight": 0.22,
"metrics": [
{
"key": "development_activity",
"band": "good",
"name": "Development activity",
"note": null,
"notes": [],
"value": 72,
"inputs": {
"commits_last_year": 66,
"human_commit_share": 1,
"days_since_last_push": 0,
"active_weeks_last_year": 14
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 0 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 0
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "14/52 weeks with commits",
"points": 9.7,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 14
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "66 commits in the last year",
"points": 16.4,
"status": "partial",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 66
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "critical",
"name": "Release discipline",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 1,
"inputs": {
"releases_count": 0
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "no releases published",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_releases_published",
"params": {}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "no releases",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_releases",
"params": {}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "no releases",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_releases",
"params": {}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
}
]
},
{
"key": "abandonment",
"band": "excellent",
"name": "Abandonment",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"cap": null,
"state": "unverified",
"guards": [],
"signals": [],
"red_flag": false,
"multiplier_pct": 100,
"declared_reason": null,
"unverified_reason": "repository_too_young",
"unanswered_open_prs": null,
"unanswered_open_issues": null,
"days_since_last_merged_pr": null,
"days_since_last_human_commit": null,
"days_since_last_human_commit_is_floor": false
},
"components": [
{
"key": "project_is_still_maintained",
"name": "Project is still maintained",
"detail": "maintenance record not established from the collected data",
"points": 100,
"status": "met",
"details": [
{
"code": "abandonment_unverified",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Is the project alive — is code being written and are releases shipping?"
},
{
"key": "community",
"band": "critical",
"name": "Community & Adoption",
"value": 24,
"weight": 0.18,
"metrics": [
{
"key": "popularity",
"band": "critical",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 1,
"inputs": {
"forks": 0,
"stars": 0,
"watchers": 0,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "0 stars",
"points": 0,
"status": "missed",
"details": [
{
"code": "stars",
"params": {
"count": 0
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "0 forks",
"points": 0,
"status": "missed",
"details": [
{
"code": "forks",
"params": {
"count": 0
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "0 watchers",
"points": 0,
"status": "missed",
"details": [
{
"code": "watchers",
"params": {
"count": 0
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "critical",
"name": "Community health",
"note": null,
"notes": [],
"value": 25,
"inputs": {
"has_readme": true,
"has_license": false,
"has_contributing": false,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "no license file detected",
"points": 0,
"status": "missed",
"details": [
{
"code": "license_absent",
"params": {}
}
],
"max_points": 22.5
},
{
"key": "contributing_guide",
"name": "CONTRIBUTING guide",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "code_of_conduct",
"name": "Code of conduct",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 13.5
},
{
"key": "issue_template",
"name": "Issue template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.2
},
{
"key": "pr_template",
"name": "PR template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.3
}
]
},
{
"key": "ecosystem_adoption",
"band": "moderate",
"name": "Ecosystem adoption (downloads)",
"note": "Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"registry_dependents"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 60,
"inputs": {
"packages": [
"@agnt-sdk/client",
"@agnt-sdk/config",
"@agnt-sdk/studio"
],
"dependents": null,
"ecosystems": "npm",
"total_downloads": null,
"monthly_downloads": 4035
},
"components": [
{
"key": "monthly_downloads",
"name": "Monthly downloads",
"detail": "4,035 downloads/month across npm",
"points": 48.1,
"status": "partial",
"details": [
{
"code": "downloads_monthly",
"params": {
"count": 4035,
"ecosystems": "npm"
}
}
],
"max_points": 80
},
{
"key": "registry_dependents",
"name": "Registry dependents",
"detail": "not reported by this ecosystem",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_reported_by_this_ecosystem",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "moderate",
"name": "Sustainability & Governance",
"value": 54,
"weight": 0.24,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 18,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 2,
"top_contributor_share": 0.712
},
"components": [
{
"key": "bus_factor",
"name": "Bus factor",
"detail": "1 contributor(s) cover half of all commits",
"points": 9,
"status": "partial",
"details": [
{
"code": "bus_factor",
"params": {
"count": 1
}
}
],
"max_points": 54
},
{
"key": "commit_distribution",
"name": "Commit distribution",
"detail": "top contributor authored 71% of commits",
"points": 6.5,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 71
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "2 contributors",
"points": 2.7,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 2
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 0 contributing companies or organizations -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "good",
"name": "Issue & PR responsiveness",
"note": "Excluded from scoring (no data or not applicable): Issue resolution. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"issue_resolution"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 83,
"inputs": {
"merged_prs": 22,
"open_issues": 0,
"closed_issues": 0,
"issue_closed_ratio": null,
"closed_unmerged_prs": 1
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "no issues or no data",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_issues_or_data",
"params": {}
}
],
"max_points": 46.75
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "22/23 decided PRs merged",
"points": 36.6,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 22,
"decided": 23
}
}
],
"max_points": 38.25
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 14/28 approved changesets -- score normalized to 5",
"points": 7.5,
"status": "partial",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "at_risk",
"name": "Ownership & stewardship",
"note": null,
"notes": [],
"value": 33,
"inputs": {
"followers": 0,
"owner_type": "Organization",
"is_verified": null,
"owner_login": "agnt-ai",
"public_repos": 1,
"account_age_days": 149
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "organization-owned",
"points": 30,
"status": "met",
"details": [
{
"code": "owner_organization",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "0 followers of agnt-ai",
"points": 0,
"status": "missed",
"details": [
{
"code": "owner_followers",
"params": {
"count": 0,
"login": "agnt-ai"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "1 public repos, account ~0 yr old",
"points": 3,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 1
}
},
{
"code": "account_age_years",
"params": {
"years": 0
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "excellent",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"@agnt-sdk/client",
"@agnt-sdk/config",
"@agnt-sdk/studio"
],
"ecosystems": "npm",
"any_deprecated": false,
"min_days_since_publish": 8
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "3 package(s) on npm",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 3,
"ecosystems": "npm"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 8 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 8
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "44 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 44
}
}
],
"max_points": 20
},
{
"key": "not_deprecated",
"name": "Not deprecated",
"detail": "active, not deprecated or yanked",
"points": 20,
"status": "met",
"details": [
{
"code": "package_not_deprecated",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
},
{
"key": "engineering",
"band": "at_risk",
"name": "Engineering Quality",
"value": 40,
"weight": 0.2,
"metrics": [
{
"key": "engineering_practices",
"band": "critical",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 24,
"inputs": {
"has_ci": false,
"has_tests": true,
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"components": [
{
"key": "ci_workflows",
"name": "CI workflows",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 24
},
{
"key": "tests_present",
"name": "Tests present",
"detail": null,
"points": 24,
"status": "met",
"details": [],
"max_points": 24
},
{
"key": "linter_config",
"name": "Linter config",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 16
},
{
"key": "pre_commit_hooks",
"name": "Pre-commit hooks",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 9.6
},
{
"key": "editorconfig",
"name": ".editorconfig",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.4
},
{
"key": "openssf_scorecard_ci_tests",
"name": "OpenSSF Scorecard: CI-Tests",
"detail": "0 out of 19 merged PRs checked by a CI test -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "moderate",
"name": "Documentation",
"note": null,
"notes": [],
"value": 65,
"inputs": {
"topics": [],
"has_wiki": true,
"homepage": null,
"has_readme": true,
"has_docs_dir": true,
"has_description": false
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 30,
"status": "met",
"details": [],
"max_points": 30
},
{
"key": "documentation_directory",
"name": "Documentation directory",
"detail": null,
"points": 25,
"status": "met",
"details": [],
"max_points": 25
},
{
"key": "documentation_homepage_site",
"name": "Documentation / homepage site",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "repository_description",
"name": "Repository description",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
},
{
"key": "topics",
"name": "Topics",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
},
{
"key": "wiki",
"name": "Wiki",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
}
],
"description": "Are baseline engineering and documentation practices in place?"
},
{
"key": "security",
"band": "at_risk",
"name": "Security",
"value": 44,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "at_risk",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): Branch-Protection, Dangerous-Workflow, Packaging, Pinned-Dependencies, Signed-Releases, Token-Permissions. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"branch_protection",
"dangerous_workflow",
"packaging",
"pinned_dependencies",
"signed_releases",
"token_permissions"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 30,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 12,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 6,
"scorecard_aggregate": 3
},
"components": [
{
"key": "binary_artifacts",
"name": "Binary-Artifacts",
"detail": "no binaries found in the repo",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "branch_protection",
"name": "Branch-Protection",
"detail": "internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "0 out of 19 merged PRs checked by a CI test -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "cii_best_practices",
"name": "CII-Best-Practices",
"detail": "no effort to earn an OpenSSF best practices badge detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "code_review",
"name": "Code-Review",
"detail": "Found 14/28 approved changesets -- score normalized to 5",
"points": 3.8,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 0 contributing companies or organizations -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "dangerous_workflow",
"name": "Dangerous-Workflow",
"detail": "no workflows found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
},
{
"key": "dependency_update_tool",
"name": "Dependency-Update-Tool",
"detail": "no update tool detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "fuzzing",
"name": "Fuzzing",
"detail": "project is not fuzzed",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "license",
"name": "License",
"detail": "license file not detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "packaging",
"name": "Packaging",
"detail": "packaging workflow not detected",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 5
},
{
"key": "pinned_dependencies",
"name": "Pinned-Dependencies",
"detail": "no dependencies found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 5
},
{
"key": "sast",
"name": "SAST",
"detail": "SAST tool is not run on all commits -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "security_policy",
"name": "Security-Policy",
"detail": "security policy file not detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "signed_releases",
"name": "Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "token_permissions",
"name": "Token-Permissions",
"detail": "No tokens found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "vulnerabilities",
"name": "Vulnerabilities",
"detail": "17 existing vulnerabilities detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "dependency_advisories",
"band": "excellent",
"name": "Dependency advisories",
"note": "Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the npm:@agnt-sdk/client@0.0.2 runtime dependency closure — what installing the published package pulls in — 2 packages. Reachability is not analyzed.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"no_advisories_left_outstanding"
]
}
},
{
"code": "weights_renormalized",
"params": {}
},
{
"code": "advisories_scope_published",
"params": {
"package": "npm:@agnt-sdk/client@0.0.2",
"assessed": 2
}
},
{
"code": "advisories_reachability",
"params": {}
}
],
"value": 100,
"inputs": {
"source": "osv",
"advisories": 0,
"affected_packages": 0,
"assessed_packages": 2,
"unassessed_packages": 0,
"affected_by_severity": "none",
"direct_affected_packages": 0
},
"components": [
{
"key": "direct_dependencies_free_of_known_advisories",
"name": "Direct dependencies free of known advisories",
"detail": "no direct dependency carries a known advisory",
"points": 35,
"status": "met",
"details": [
{
"code": "no_direct_advisories",
"params": {}
}
],
"max_points": 35
},
{
"key": "indirect_dependencies_free_of_known_advisories",
"name": "Indirect dependencies free of known advisories",
"detail": "no indirect dependency carries a known advisory",
"points": 25,
"status": "met",
"details": [
{
"code": "no_indirect_advisories",
"params": {}
}
],
"max_points": 25
},
{
"key": "no_advisories_left_outstanding",
"name": "No advisories left outstanding",
"detail": "no advisory carries a publication date",
"points": 0,
"status": "excluded",
"details": [
{
"code": "advisories_no_publication_date",
"params": {}
}
],
"max_points": 40
}
]
},
{
"key": "malicious_dependencies",
"band": "excellent",
"name": "Malicious dependencies",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"source": "osv",
"meaning": "reported as a malicious package by the OpenSSF corpus; the remedy is removal or moving off the compromised name, never an upgrade of the same artifact. Versions the registry has since pulled are listed but not scored",
"packages": [],
"red_flag": false,
"assessed_packages": 2,
"malicious_packages": 0,
"direct_malicious_packages": 0,
"withdrawn_malicious_packages": 0,
"installable_malicious_packages": 0
},
"components": [
{
"key": "no_dependency_reported_as_a_malicious_package",
"name": "No dependency reported as a malicious package",
"detail": "no dependency is reported as a malicious package",
"points": 100,
"status": "met",
"details": [
{
"code": "no_malicious_dependencies",
"params": {}
}
],
"max_points": 100
}
]
},
{
"key": "high_risk_jurisdiction_exposure",
"band": "excellent",
"name": "High-Risk Jurisdiction Exposure",
"note": "Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.",
"notes": [
{
"code": "jurisdiction_evidence_limits",
"params": {}
}
],
"value": 100,
"inputs": {
"meaning": "self-published location evidence; not nationality or citizenship",
"red_flag": false,
"exposures": [],
"policy_countries": [
"Russia",
"Iran",
"North Korea"
],
"review_only_matches": 0,
"assessed_self_published_locations": 1
},
"components": [
{
"key": "policy_exposure_multiplier",
"name": "Policy exposure multiplier",
"detail": "no confirmed policy-scope location match",
"points": 100,
"status": "met",
"details": [
{
"code": "jurisdiction_no_match",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
},
{
"key": "ai_readiness",
"band": "moderate",
"name": "AI Readiness",
"value": 60,
"weight": 0,
"metrics": [
{
"key": "ai_agent_context",
"band": "at_risk",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 40,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 1,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "no CLAUDE.md / AGENTS.md / editor rules",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_instructions",
"params": {}
}
],
"max_points": 45
},
{
"key": "machine_readable_docs_llms_txt",
"name": "Machine-readable docs (llms.txt)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "legible_commit_history",
"name": "Legible commit history",
"detail": "66 of 66 human commits state their intent (structured subject or explanatory body)",
"points": 40,
"status": "met",
"details": [
{
"code": "legible_history",
"params": {
"legible": 66,
"sampled": 66
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "moderate",
"name": "Verify loop (build / test / typecheck)",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Pinned-Dependencies. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_pinned_dependencies"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 59,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [
"package-lock.json"
],
"has_dockerfile": false,
"typed_language": true,
"bootstrap_files": [],
"has_devcontainer": false,
"has_linter_config": false,
"typecheck_configs": [
"packages/client/tsconfig.json",
"packages/config/tsconfig.json",
"packages/studio/tsconfig.json"
],
"agent_commit_share": 0.833,
"toolchain_manifests": [],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "automated_tests",
"name": "Automated tests",
"detail": null,
"points": 22,
"status": "met",
"details": [],
"max_points": 22
},
{
"key": "lint_format_config",
"name": "Lint / format config",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": "packages/client/tsconfig.json, packages/config/tsconfig.json, packages/studio/tsconfig.json",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "packages/client/tsconfig.json, packages/config/tsconfig.json, packages/studio/tsconfig.json"
}
}
],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": "lockfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "lockfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "55 of the last 66 commits agent-authored or agent-credited",
"points": 10,
"status": "met",
"details": [
{
"code": "agent_authored_commits",
"params": {
"count": 55,
"sampled": 66
}
}
],
"max_points": 10
},
{
"key": "automated_maintenance",
"name": "Automated maintenance",
"detail": "no automated dependency updates observed",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_dependency_automation",
"params": {}
}
],
"max_points": 8
},
{
"key": "openssf_scorecard_pinned_dependencies",
"name": "OpenSSF Scorecard: Pinned-Dependencies",
"detail": "no dependencies found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "excellent",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"primary_language": "TypeScript",
"largest_source_bytes": 52203,
"source_files_sampled": 79,
"oversized_source_files": 0
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "TypeScript (statically typed)",
"points": 45,
"status": "met",
"details": [
{
"code": "statically_typed_language",
"params": {
"language": "TypeScript"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "0/79 source files over 60KB",
"points": 55,
"status": "met",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 79,
"oversized": 0
}
}
],
"max_points": 55
}
]
}
],
"description": "How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score."
}
],
"metrics_version": "1.13.0"
},
"warnings": [
"GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository"
],
"report_type": "repository",
"generated_at": "2026-07-30T10:38:27.618429Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/a/agnt-ai/agnt-node.svg",
"full_name": "agnt-ai/agnt-node",
"license_state": "absent",
"license_spdx": null
}Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.
Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v1.13.0, schema v0.27.0 — full methodology · metrics wiki.
How one result sits in the wider record: aggregate statistics — npm.