kodi/topchester-agent має індекс здоров’я 48 зі 100, що відповідає смузі «У зоні ризику». Найвищий показник — AI Readiness (69/100), найнижчий — Community & Adoption (24/100). Останнє оновлення було 4 дні тому. Більшість нещодавньої роботи виконує один учасник.
48
загалом / 100
У зоні ризику
Індекс здоров'я програмного забезпечення
Метрики згруповано у зважені категорії на шкалі 1–100. Загальна оцінка починається як їхнє середнє; коли публічні дані активують Політику юрисдикцій високого ризику, рейтинг коригується й отримує верхню межу 49 («Під ризиком»). Готовність до ШІ не входить до індексу.
48
Відмінний85-100Зразковий; відповідає практично всім перевіреним критеріям
Добрий70-84Здоровий; незначні прогалини
Помірний50-69Прийнятний, але з помітними прогалинами; рекомендовано перевірку
У зоні ризику30-49Суттєві слабкі місця; впровадження потребує обережності
Критичний1-29Серйозні проблеми (покинутий, єдиний мейнтейнер, без базової гігієни)
Профіль оцінок
Кожна вісь — окрема категорія. Форма важить більше, ніж середнє: здоровий об'єкт заповнює всю фігуру, тоді як профіль із піками та провалами означає, що сила в одному вимірі маскує ризик в іншому.
Наскільки репозиторій оснащений для розробки та супроводу за участі ШІ-агентів? Незалежний, експериментальний бейдж — вага 0.0, тож він подається окремо і не впливає на загальний індекс здоров'я.
GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
Докладніше
Історія зірок і форків 2 ★ / 0 ⇿
2Зірки
Коли додано кожну зірку й форк — зібрано з GitHub і згруповано за днями. Кумулятивне зростання розміщено просто над денними додаваннями, з яких воно складається, тож їх видно одне проти одного: рівномірне органічне накопичення виглядає зовсім інакше, ніж різкий короткочасний сплеск. Там, де цю різницю можна виміряти, її подано як автентичність росту.
OpenSSF Scorecard 2.5 / 10
2.5сукупно
Незалежна, не прив'язана до інструментів оцінка безпеки від відкритого проєкту OpenSSF Scorecard. Кожна перевірка винагороджує практику безпеки, а не інструмент конкретного постачальника. Перевірки, які Scorecard не зміг визначити, позначено н/д і виключено з оцінки безпеки (вони ніколи не зараховуються як нуль).Scorecard v5.5.0 · 2026-07-21 22:41 UTC
Не вдалося зібрати розв'язаний набір залежностей для цього звіту: GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
Звіт у форматі JSON машиночитний
{
"data": {
"repo": {
"topics": [],
"is_fork": false,
"size_kb": 2181,
"has_wiki": true,
"homepage": null,
"languages": {
"Python": 52119,
"JavaScript": 12643,
"TypeScript": 1860020
},
"pushed_at": "2026-07-17T14:48:21Z",
"created_at": "2026-05-10T22:46:00Z",
"owner_type": "User",
"updated_at": "2026-07-17T14:48:35Z",
"description": null,
"is_archived": false,
"is_disabled": false,
"license_spdx": "MIT",
"default_branch": "main",
"license_spdx_raw": "MIT",
"primary_language": "TypeScript",
"significant_languages": [
"TypeScript"
]
},
"owner": {
"blog": "http://bajcic.com/blog",
"name": "Dragan Bajcic",
"type": "User",
"login": "kodi",
"company": "http://bajcic.com",
"location": "Belgrade, Serbia",
"followers": 61,
"avatar_url": "https://avatars.githubusercontent.com/u/51153?v=4",
"created_at": "2009-02-02T16:27:30Z",
"is_verified": null,
"public_repos": 58,
"account_age_days": 6378
},
"license": {
"state": "standard",
"spdx_id": "MIT",
"raw_spdx": "MIT",
"file_present": true,
"scorecard_found": true,
"profile_has_license": true
},
"activity": {
"releases": [
{
"tag": "v0.18.0",
"kind": "minor",
"published_at": "2026-05-15T21:27:20Z"
}
],
"recent_commits": [
{
"oid": "ff81b6be671a81cd870155d25f8c0a731f3f98f4",
"body": "Reserve transient rows while a task plan is active so status updates don't move the footer in split-footer rendering.\n\nExpand the production test to cover plan updates, terminal output capture, and footer height stability across in-progress and completed states.",
"is_bot": false,
"headline": "fix(tui): stabilize task plan footer height",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T14:48:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "274a7d3df9aedc7663536dd12aff0aa8829782e4",
"body": "Add a comprehensive route-aware context accounting and automatic compaction plan.\n\nUpdate OpenTUI production-test coverage and normalize dialog, suggestion, and task-plan rendering to use explicit content props with improved footer sizing behavior.",
"is_bot": false,
"headline": "feat: add context accounting plan and improve TUI rendering",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T14:20:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b3f781e5fd593276a7b22584e563c692b06f40e4",
"body": "Derive and persist normalized session titles from the first user prompt, use them in restore/fork flows, and update TUI docs and tests.",
"is_bot": false,
"headline": "feat: add session titles to restore picker",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T14:09:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1e889c21f8a66f5c7076dbe0bd05bda8a19529bc",
"body": "Format KB inventory rows for OpenTUI-safe plain text rendering.\\n\\nAdd aligned status/size/path output for knowledge compile results and update tests to assert the new row layout instead of tab-separated lines.",
"is_bot": false,
"headline": "fix(kb): render knowledge status rows in plain text",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T14:09:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "58e00126f2d5b01cedd1b911f0d66eebc6a30956",
"body": "Render the composer on a background matching the app, add spacing for multiline input, and increase footer height estimation.\n\nUpdate the status bar to show workspace, parsed model details, and richer knowledge-base state with clearer icons and sync indicators.\n\nExpand the opentui production test to cover the new footer layout and knowledge status rendering.",
"is_bot": false,
"headline": "feat(tui): improve footer and status bar layout",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T14:09:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "77010295ed35adcdbbfbe8720a89cf5fdbbf7fd2",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.78.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-07-17T04:18:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "de8dcc715128c03a36006db5f416fadf9d9e3e80",
"body": "Replace the generated Topchester product KB with packaged static skills.\\n\\n- remove product-source sync/check workflow and mise tasks\\n- simplify KB search/context to project-only behavior\\n- update standalone/package checks, prompts, docs, and tests",
"is_bot": false,
"headline": "chore: remove embedded product knowledge",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T04:15:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "54556388914740a6d280f1f868812641314c1d3d",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.77.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-07-17T03:53:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9c695df9af79b11f5f94122b23e07b7fd07f16e5",
"body": "Run release checks before version bump and add formatting and validation steps for versioned product knowledge during the publish workflow.",
"is_bot": false,
"headline": "ci: tighten npm release workflow checks",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T03:50:39Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "97055ab4b70384346990c0ceca327c5f77d6b40d",
"body": "Update local CI task wiring to run tasks sequentially and make the transcript writer wait longer for scrollback settling before committing rows.",
"is_bot": false,
"headline": "fix: adjust opentui transcript settling and ci task flow",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T03:44:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a16f2f71a151a5301b36d97f3fa28cbaa06755ae",
"body": "Feat/opentui migration",
"is_bot": false,
"headline": "Merge pull request #5 from kodi/feat/opentui-migration",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T03:30:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a5b914561ed21195b37602964091007709535a4b",
"body": "Remove Intel macOS from the standalone release matrix and update CI, release docs, and generated knowledge artifacts to reflect the supported targets.",
"is_bot": false,
"headline": "chore: drop darwin x64 standalone support",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T03:28:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "804d37214b6f552f3685028420f5a8a72a7bc432",
"body": "Implement multi-platform native build, packaging, publish, and validation flow for topchester-ai.\nUpdate CI, release automation, self-update detection, and install docs for the standalone distribution.",
"is_bot": false,
"headline": "feat: add native standalone npm release workflow",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T03:17:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1c27895392c697097ba72a59cad75f2b9d76dbea",
"body": "Add standalone build scripts, package checks, and embedded asset support for Topchester.\\n\\nInclude build-time package metadata, embedded built-in skill/product knowledge loading, and documentation for the standalone distribution follow-up.",
"is_bot": false,
"headline": "feat: add standalone executable build and checks",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T02:34:29Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d560c14458b12d63be2ff94551323a19065e320e",
"body": "Update transcript markdown rendering to wrap fenced code in a themed box and apply surface background styling. Expand production test coverage to verify code block background and rendered markdown formatting.",
"is_bot": false,
"headline": "feat(opentui): render fenced code blocks with themed background",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T02:25:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a958648436c0c89dad1dadfb946ac0477c191d12",
"body": null,
"is_bot": false,
"headline": "ci: remove Windows from package matrix",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T02:09:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9867a7be7d22a19d38216dcd67824ef1b39671d9",
"body": "Add adaptive footer sizing, shared active-row marker, and markdown-aware transcript scrollback rendering.\n\nAlso wire renderer error propagation and background color setup, and extend production tests for dialog selection and transcript output.",
"is_bot": false,
"headline": "feat(opentui): improve footer and transcript rendering",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T02:07:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c5ccce4df37842a03555b6455fe705c4df166d17",
"body": null,
"is_bot": false,
"headline": "ci: split local checks from extended validation",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T01:37:39Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "563fcaad3c9ccac01d68c19494a60a2ab7efd959",
"body": null,
"is_bot": false,
"headline": "feat: migrate interactive UI to OpenTUI",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-17T01:28:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4169b372d0aedb3d833d7668a7b536b310c013b2",
"body": null,
"is_bot": false,
"headline": "chore: prepare OpenTUI migration",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-16T23:00:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "622fa1d5fda041730354eef8d5960a3d273af56e",
"body": "- Switch typecheck task from tsgo to tsc in .mise.toml and package.json\n- Update @typescript/native-preview to @typescript/native npm alias\n- Update typescript from ^6.0.3 to npm:@typescript/typescript6@^6.0.2",
"is_bot": false,
"headline": "build: replace tsgo with tsc and update TypeScript dependencies",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-15T16:26:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c5245594d8d3cfa056db8fa5e8457f13237a92e9",
"body": "Add a packaged, version-matched Topchester product knowledge source, source-aware KB search/context, and the skill_read tool.\n\nUpdate docs, CI tasks, packaging checks, smoke coverage, and tests to cover the new product source and its diagnostics.",
"is_bot": false,
"headline": "feat: add built-in topchester knowledge source",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-15T10:46:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fa47bc9c6b2f125acd95732f1ff4f6e7dfc526a2",
"body": "Add built-in product knowledge planning docs and new model configs for gpt-5.6-sol and gpt-5.6-terra.\\n\\nAlso update TUI reasoning streaming to mute each streamed row independently and add coverage for the new rendering behavior.",
"is_bot": false,
"headline": "feat: add Topchester product knowledge plan and configs",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-14T23:17:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "209d6044fdc584bad740b12b146b91fd79e879cd",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.76.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-07-14T22:10:18Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bb87286b85dfd19c568a618786546b19ebeb5500",
"body": "Document multi-line reasoning display and ephemeral busy row rendering, and update TUI tests for rolling reasoning updates.",
"is_bot": false,
"headline": "docs: describe streamed reasoning TUI updates",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-14T22:09:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2153ed8ec44224ee5471586376558e23dacbe167",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.75.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-07-14T22:03:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a1bf701a670ce5bd984912bc8ca32336d3c61cab",
"body": null,
"is_bot": false,
"headline": "ci: use npm version in publish workflow",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-14T22:02:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "258ea4d44dd7b6360b8e4bf544322f922f8c4463",
"body": "Add max to reasoning effort schema, slash command help, and provider/session handling.\\n\\nUpdate docs, changelog, and tests to reflect OpenRouter and supported model max effort.",
"is_bot": false,
"headline": "docs,config: add max reasoning effort support",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-14T21:55:22Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a847fb460521560eec74f0698d6cfe9fc322f5e9",
"body": "Retain a single selected profile slot for --config/TOPCHESTER_CONFIG, keep loaded config immutable during TUI sessions, and persist model/reasoning changes as session runtime overrides.\n\nUpdate CLI, session rehydration, runtime rebuilds, and docs to preserve selected profiles across reloads, resume, restore, fork, and new-session flows.",
"is_bot": false,
"headline": "fix(config): separate selected profile from runtime overrides",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-14T21:51:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fd396a3c1d8a3a143b36efbce6571e0ee1b84724",
"body": null,
"is_bot": false,
"headline": "fix: correct gpt-5 config JSON structure",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-14T21:18:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7e0b2025747e91ba3f577d7e282fa3fba9549525",
"body": "Use setup-vp and native Vite+ commands in GitHub Actions, route mise tasks through the unified toolchain, and update compatibility package scripts.",
"is_bot": false,
"headline": "chore: migrate CI automation to Vite+",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-13T21:48:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ea953c693cfa47a40c2de20053b5d8c9cc116e33",
"body": "Replace Lefthook with the Vite+ staged-file workflow, install hooks through the prepare lifecycle, and remove the old dependency and configuration.",
"is_bot": false,
"headline": "chore: use native Vite+ git hooks",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-13T21:28:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "79b9aa8b459fa5714c9e009a9003986a3b2847f0",
"body": "Replace the standalone formatter, linter, test, and pre-commit setup with Vite+ configuration and workspace dependencies. Migrate test imports, add editor integration, and resolve the type-aware check findings while excluding intentionally incomplete benchmark fixtures.",
"is_bot": false,
"headline": "chore: migrate development tooling to Vite+",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-13T21:21:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a58c236e5b3a2d0538bd0962c9b61a7b9416599b",
"body": null,
"is_bot": false,
"headline": "fix nightly smoke config path",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-11T18:39:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f0e89925572a154f205d8dab1530b73c02452eb6",
"body": null,
"is_bot": false,
"headline": "docs: update changelog",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-08T17:13:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3fcaa8b95969337f0625c7c5350211b5008936be",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.74.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-07-08T17:10:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9e2c19da11d72322370aad2bc105eed2553a8043",
"body": "- Add MentionRange interface to file-mentions.ts\n- Add findMentionRanges() function to find all @mention tokens in text\n- Create new mention-styles.ts module with styling functions:\n - renderMentionStyles() to apply styles to mention ranges\n - styleMentionText() to apply cyan bold styling\n - isIn\n[…]\noffset to properly handle multi-line prompts\n- Update user message rendering to highlight mentions\n- Remove @ prefix from mention suggestion display\n- Add tests for mention range detection and styling",
"is_bot": false,
"headline": "feat: add mention styling and range detection",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-08T17:10:04Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "cc84daffaf9dfc95e6d08ba83ac76cf8777fae57",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.73.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-07-08T16:55:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "05882c2415867879fd6603ce13fbc4093ffb7040",
"body": "- Implement mention token detection and completion insertion at any cursor position\n- Add cached workspace file index provider with TTL-based refresh\n- Integrate popup UI and key handling in ChatLayout for file/directory suggestions\n- Wire provider into TopchesterTuiShell and update system prompt\n- Update docs and changelog with new @-mention feature\n- Add comprehensive tests for mention parsing, provider caching, and render behavior",
"is_bot": false,
"headline": "feat: add @file path autocomplete to TUI",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-08T16:54:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4eee6a5a44190ea1fe35e062a6eb1f8165f585f3",
"body": null,
"is_bot": false,
"headline": "docs: update changelog",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-08T16:28:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c4139f650c9a084f912774dc9136cf428ab30988",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.72.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-07-08T16:08:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "58a591e4ea8ad8a7d4abe3936522641e0e5a2026",
"body": "- Fetch public HTTP(S) URLs with private-network blocking, redirect visibility, and size caps\n- Convert HTML to markdown or plain text, or return raw HTML\n- Block localhost and RFC 1918 private ranges with DNS validation\n- Strip URL credentials and surface cross-host redirects\n- Truncate responses o\n[…]\ncters with marker\n- Available to primary and general agents, not explore subagent\n- Add htmlparser2 and turndown dependencies for HTML conversion\n- Update docs and TUI labels with web_fetch visibility",
"is_bot": false,
"headline": "feat: add web_fetch tool for reading public HTTP(S) pages",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-08T16:07:34Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "7f49aaf4c076fc64035c69bab42f3f2bcfca5468",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.71.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-07-01T17:24:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c8deaeb8bb2e1f1b76f85988b8d356be553e83eb",
"body": "Add comprehensive plan for Topchester benchmark improvements following comparison with Pi agent. Document current results (both tied at 9/12), failure analysis, and five improvement slices:\n\n1. Fix validator friction for Go, Rust, TypeScript by expanding run_validator policy\n2. Investigate and reduc\n[…]\nrove bash tool prompt to prefer run_validator for strict shapes\n- Remove npx/pnpx from DANGEROUS_EXECUTABLES (now classified separately)\n- Add comprehensive policy tests for accepted/rejected commands",
"is_bot": false,
"headline": "docs: add SanityHarness agent comparison follow-up plan",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-07-01T17:23:42Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "96a4cf2c75bac84ef6d74d1ff2e93b7c2a1d2fc9",
"body": "- Add api-001-todo-state-machine and react-001-filterable-todo-panel tasks to README\n- Add OpenRouter Grok model configurations (4.3 and build-0.1)\n- Set CI=true environment variable in bootstrap and verification scripts for consistent CI behavior",
"is_bot": false,
"headline": "feat: add new tasks and improve CI environment handling",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-30T22:16:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d38254aa238d13e34b89c3defe6b9908ddf3c35a",
"body": "Fix mini-bench no-service Docker networking",
"is_bot": false,
"headline": "Merge pull request #4 from kodi/cursor/fix-mini-bench-cloud-network-796e",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-29T23:32:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "54dd12d37975e5b647d59cd7577067bda2faa085",
"body": "Co-authored-by: Dragan Bajcic <dragan@bajcic.com>",
"is_bot": false,
"headline": "fix: avoid compose network for no-service mini-bench tasks",
"author_name": "Cursor Agent",
"author_login": "cursoragent",
"committed_at": "2026-06-29T23:28:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "605bd76a590ecdb62e4c9f6cada8e202c0cff882",
"body": "Co-authored-by: Cursor Agent <cursoragent@cursor.com>",
"is_bot": false,
"headline": "docs: add Cursor Cloud setup notes to AGENTS.md (#3)",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-29T22:55:44Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "0e16ff8aaaf86f96f9ffcec4aa1ee5376b5cd963",
"body": "…ark configs\n\n- Introduces a new React-based benchmarking task for a filterable todo panel.\n- Adds supporting types, verifiers, and workspace fixtures for the React category.\n- Connects new OpenRouter models (GLM-5.2 and Kimi-K2.7-Code) for testing.",
"is_bot": false,
"headline": "feat(mini-bench): add react-001-filterable-todo-panel task and benchm…",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T15:49:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ef87f10ba26c4f1bda9effa6d842d90da91bd336",
"body": "…or verification\n\n- Add configuration for deepseek-v4-pro and gemini-3.5-flash via OpenRouter.\n- Update API verifier to use a generic structured error check instead of strict error code matching for status and not found errors.",
"is_bot": false,
"headline": "feat(bench): add OpenRouter DeepSeek and Gemini configs and relax err…",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T14:59:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "474ab0edfd374e7e43ed91ba74b2c6877e09bb78",
"body": "- Introduce a new API benchmarking task for implementing an Express-based Todo state machine.\n- Add task definition, prompt, verifier with multiple test cases, and workspace scaffolding.\n- Register the new task in the CLI fixture verification list.",
"is_bot": false,
"headline": "feat(mini-bench): add api-001-todo-state-machine task",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T14:39:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "791435190d48bfb3212ad66f21e4443fd57cfa08",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.70.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-17T14:10:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "23c2c75b195da54442f7cc8a040489f72845c6cf",
"body": "- Restrict vitest to the 'test' directory in package.json\n- Update task tool prompt to discourage subagent spawning for small context inspections",
"is_bot": false,
"headline": "test: refine tool prompt instructions and scope test directory",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T14:05:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dc617dc1322a5994bea4ce698ace357c7d23c12a",
"body": "…ed edits\n\n- Update system prompt to suggest using write_file as a fallback when apply_patch or edit_file repeatedly fail.\n- Update task tool description and prompt to discourage subagent delegation for tiny local inspections or small workspace contexts.",
"is_bot": false,
"headline": "refactor(agent): refine task tool usage and provide fallback for fail…",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T14:02:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7aa4daf0fc2e562afd8320e5dae88b4121a4284a",
"body": "- Add postgres service to docker-compose and provide DATABASE_URL to agents\n- Implement task service startup and healthcheck wait logic in runner\n- Support bootstrap scripts in task definitions\n- Add db-003-postgres-order-analytics benchmarking task",
"is_bot": false,
"headline": "feat(mini-bench): add postgres service support and order analytics task",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T13:49:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "14dc241691c803e0dfa83df6dfd21a7c737ab377",
"body": "- Adds type to track input/output/cache tokens and USD cost.\n- Implements and to parse token/cost metadata from and event streams.\n- Configures runner to enable and log level.\n- Adds aggregate run summaries showing total wall time, task time, and cumulative cost.\n- Updates verifier for with more robust balance checks.",
"is_bot": false,
"headline": "feat(mini-bench): extract token usage, cost, and turn counts",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T12:58:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dd544fa3c110d1564cc6319136c399069cfbc2a3",
"body": "- Introduce and tasks.\n- Enhance CLI with colorful table listings and progress indicators.\n- Add detailed agent performance summaries (event kinds, tool calls, message roles).\n- Improve containerized run feedback with build and execution progress.",
"is_bot": false,
"headline": "feat(mini-bench): add new benchmark tasks and enhance CLI reporting",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T12:38:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "55d9edfb7ec2e9c5784c121279ca7c6cd7637fc1",
"body": "Allow passing multiple flags to the run command. Each task is\nexecuted in order, and the process exits with a non-zero code if any\ntask fails. Includes a summary report for multi-task runs.",
"is_bot": false,
"headline": "feat(mini-bench): support running multiple tasks sequentially",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T12:16:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "99349036bff3722e8ccc90b614d5a709723ae571",
"body": "Initial implementation of the Topchester mini-bench harness for local agent\nvalidation.\n\n- Adds a host-runner CLI with commands for listing, running, and cleaning\n benchmarks.\n- Implements Docker-based agent execution with npm package isolation.\n- Introduces 'task-000-basic-ts-transform' as a harne\n[…]\nrifiers and fixtures.\n- Includes comprehensive documentation, configuration schemas, and\n reporting logic for benchmark results.\n- Adds mise tasks and project-level pnpm scripts for local ergonomics.",
"is_bot": false,
"headline": "feat(bench): add mini-bench local harness and task-000",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T12:08:41Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "812e7548baf5739adf17bf44d769c67892f0c5d7",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.69.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-17T01:08:46Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fdabe0b5f08f38f9f197c26e46fc24a04e7ef0df",
"body": "- Update tool description to explicitly forbid execution work (shell, scripts, writes)\n- Add validation to reject subagent prompts that appear to request shell execution\n- Pass through subagent manager and runtime\n- Add unit tests for shell command rejection in subagents",
"is_bot": false,
"headline": "feat: restrict task subagents to read-only research",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T01:07:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "14a1ba14ae5a110c0f1ace430b8a20d17fdb5289",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.68.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-17T00:48:44Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "814b2cbb331d75e8bfc38ef710e94b203f03a4de",
"body": "This change introduces the ability to read specific byte ranges in , implements a to deduplicate repeated reads of unchanged files, and adds stricter output limits for the profile across several tools (bash, inspect_command, run_validator).",
"is_bot": false,
"headline": "feat: add offset/limit support and caching to read_file tool",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-17T00:47:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ac6d9148f2395af46085357c4e29bfd0647fb987",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.67.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-16T23:10:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0da17460765ccc7c024dfd940226d7fba656f0df",
"body": "- Add max_tool_calls_per_turn parameter to TopchesterAgent with default 5000000\n- Support unlimited tool calls via special string values (0, off, false, unlimited, etc.)\n- Add TOPCHESTER_MAX_TOOL_CALLS_PER_TURN environment variable support\n- Improve read_file tool to skip binary and oversized files \n[…]\nh pipefail\n- Move n_agent_steps to metadata structure for consistency\n- Add tests for unlimited tool calls and binary/oversized file handling\n- Update README with max_tool_calls_per_turn documentation",
"is_bot": false,
"headline": "feat: add max_tool_calls_per_turn support and improve read_file handling",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-16T23:05:58Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "78fe07041cefa24af64233a4e2f438d9f78a8e38",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.66.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-16T22:09:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4ff98a9d07238f595902d6ee3fa8506a80549094",
"body": "…nchmark containers\n\nAdd explicit benchmark runtime profile support with terminal-bench profile for Terminal-Bench containerized runs:\n\n- New --benchmark-profile CLI option for topchester run command\n- terminal-bench profile allows broad shell commands and treats workspace-changing bash as valid tas\n[…]\n Updates bash policy to allow destructive commands in benchmark profile\n- Finish gate accepts bash mutations as workspace changes in terminal-bench mode\n- Comprehensive test coverage and documentation",
"is_bot": false,
"headline": "feat: add --benchmark-profile terminal-bench option for disposable be…",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-16T22:09:01Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c4765c67b4e3bfa182e6d9983cebcb0f87668766",
"body": "- Update benchmark mode prompt to require remaining_issues to be empty\n- Add requireFinishTask validation check in finish_task result validation\n- Reject finish_task with non-empty remaining_issues in benchmark/require-finish mode\n- Update finish_task tool description to clarify remaining_issues requirement\n- Add comprehensive test case for finish_task rejection with remaining issues\n- Update tool documentation strings across test files",
"is_bot": false,
"headline": "feat: enforce empty remaining_issues in benchmark mode finish_task",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-16T22:09:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d8d0f8412fb45c0f9cfd8bba37db0a077f425588",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.65.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-12T21:50:29Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "119cd446f928776b1f4b20c1c542fd83c7c9a177",
"body": "…uirement mode\n\n- Replace 'pnpm run' and 'pnpm exec' with node_modules/.bin/ tool calls in mise tasks\n- Add test task using vitest\n- Add TOPCHESTER_REQUIRE_FINISH_TASK environment variable support\n- Implement finish_task enforcement with repair attempts (max 3)\n- Add formatting functions for finish_\n[…]\ninstruction to require finish_task as terminal action\n- Add test case for finish_task requirement mode behavior\n- Update finish_task tool description to clarify benchmark/require-finish mode semantics",
"is_bot": false,
"headline": "feat: replace pnpm with direct tool execution and add finish_task req…",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-12T21:49:39Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "1156adcc017106f5e8a23c5e792251f0eca93fc7",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.64.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-12T20:59:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "136bfe4f43ebd82049978b5b640acdf3ab2229cb",
"body": "- Add TOPCHESTER_PLAN_TODO_MODE env var to switch between 'normal' and 'compact' modes\n- Add TOPCHESTER_MAX_PLAN_TODO_UPDATES_PER_TURN to limit plan updates per turn (default 3 in compact mode)\n- Validate plan_todo calls: reject consecutive calls, enforce update limits, skip redundant updates\n- Upda\n[…]\node-specific guidance\n- Refactor tool call loop to track and enforce plan_todo update constraints\n- Add comprehensive tests for max tool calls, consecutive plan_todo rejection, and compact mode limits",
"is_bot": false,
"headline": "feat: add plan_todo mode configuration and constraints",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-12T20:59:07Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "38492dcdf58dfc1b22f8994f57924eed885d8c86",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.63.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-12T20:21:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "69411c56c2eb8b95e7527e8fe670ff04c60ce4b6",
"body": "Add apply_patch and finish_task tools for multi-file edits and task completion.\nImplement source mutation tracking to enforce actual code changes in implementation tasks.\nAdd validation to reject finish_task and prose-only completions when source edits are required.\nUpdate agent prompts to emphasize using mutating tools for real implementation work.\nAdd repair instructions for incomplete implementation attempts with up to 2 retry attempts.",
"is_bot": false,
"headline": "feat: add implementation task validation with source mutation tracking",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-12T20:20:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d6149e84641c2aa8fbff3749486cc30a78024228",
"body": "…gurable options\n\n- Add KB inventory guard with max file limits for benchmark prewarming\n- Add configurable KB model, tool protocol, and OpenRouter routing options\n- Add code-only KB ignore paths configuration and benchmark prompt wrapper\n- Simplify OpenRouter tool routing to only apply when explici\n[…]\nr OpenRouter streaming with reasoning\n- Update provider defaults and config handling for new options\n- Add NODE_USE_ENV_PROXY and NVM path fixes\n- Update gitignore for Python artifacts and job outputs",
"is_bot": false,
"headline": "feat: enhance topchester agent with KB inventory validation and confi…",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-12T14:04:43Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "1036cc3adc2df895980706acb71c81199ecb42dd",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.62.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-12T11:48:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d630db2c25d02d9131b2ce93a61c5d55a6f27965",
"body": null,
"is_bot": false,
"headline": "chore: format fix",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-12T11:48:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "52ec300276fcdcd65773ff99912371460399a8fc",
"body": "Add explicit runtime approval mode for headless benchmark runs that auto-approve\nbash commands otherwise requiring user interaction. Includes:\n\n- New UserApprovalMode type ('interactive' | 'auto_allow') in runtime options\n- --dangerously-auto-approve flag for topchester run command\n- Auto-approval o\n[…]\nehensive tests for runtime, CLI, hooks, and bash policy integration\n- Updated CLI docs and reference with intended usage and safety boundaries\n- Benchmark harness helper script with KB prewarm support",
"is_bot": false,
"headline": "feat: add --dangerously-auto-approve flag for benchmark automation",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-12T11:48:15Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "207c12e74be0c1fe51dfb7e8f3d29c016090db1d",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.61.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-12T11:16:39Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dc99d6238ffe6de2e9320b50b66a3cda0421f6b1",
"body": "Add CLI examples and reference documentation for the new 'topchester mcp add'\ncommand that allows users to add or replace stdio MCP servers in their config.\nUpdate command overview tables and add detailed command reference with usage\nexamples, environment variable support, and config file behavior.\n\n[…]\nmmand in the CLI with proper argument parsing,\nenvironment variable collection, and config file updates. Add comprehensive\ntest coverage for adding new and updating existing MCP server configurations.",
"is_bot": false,
"headline": "docs: add topchester mcp add command documentation",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-12T11:15:43Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c5ff3abd742c7284e7e9bb27bc5f43b3b504c091",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.60.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-04T22:35:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "390eceb29bfa8b1c00958378062723a6a6830942",
"body": "This change removes the and commands from the CLI, tests, and documentation, simplifying the core command surface.",
"is_bot": false,
"headline": "refactor: remove integrations and hook stop commands",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T22:34:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b0024e14ce7ddd194376fa721fb4959a42b5a324",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.59.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-04T20:18:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6e19792b84e47a5ffafe43067e7823dfd71c9cd9",
"body": null,
"is_bot": false,
"headline": "test: update slash command suggestion scroll test for better reliability",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T20:12:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c409473cbdfdf9cbeedd2003a0cd16e18ae12c43",
"body": "Add comprehensive plan for implementing Plan mode V0, a read-only interactive planning phase in the TUI.\n\nPlan includes:\n- Shift+Tab toggle between Build and Plan modes\n- Runtime enforcement of read-only permissions (no mutations, no dynamic MCP)\n- Mode-specific system prompts\n- Approved-plan handof\n[…]\ns clarify that Plan mode is session-level execution mode with runtime enforcement,\nnot a new multi-agent system. V0 excludes mode persistence, per-project defaults, and\nmodel-callable plan_exit tools.",
"is_bot": false,
"headline": "docs: add Plan Mode V0 implementation plan",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T16:33:56Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "2869653ad688e5fa85ca940ef714efe323a238e3",
"body": "… values\n\n- Import reasoningEfforts from config and display all options in base command descriptions\n- Implement getReasoningEffortValueSuggestions() to filter and suggest effort values with trailing space\n- Support 'clear' and 'default' options to reset to provider defaults\n- Remove hardcoded /effort high and /reasoning high suggestions\n- Update documentation with new autocomplete behavior\n- Add comprehensive test cases for effort/reasoning value suggestions",
"is_bot": false,
"headline": "feat: add autocomplete suggestions for /effort and /reasoning command…",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T16:22:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "faa5cad0320683974913e0be72a90207a7da11e5",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.58.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-04T16:15:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4d7ccd8a9c6bc167112a6e8e6ed23b029aa2bf95",
"body": "- Update package dependencies: @ai-sdk/openai-compatible, @earendil-works/pi-tui, ai, commander, yaml, and dev dependencies\n- Extract model metadata resolution logic into dedicated resolveModelMetadata method\n- Refactor createHookModelPayload to use new resolveModelMetadata method\n- Add optional chaining for model metadata access in debug logging\n- Improve error handling with clearer event naming in model resolution",
"is_bot": false,
"headline": "chore: upgrade dependencies and refactor model metadata resolution",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T16:14:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f458974917753c06920584f32f4bb4dce4ea9d5c",
"body": "- Add reasoningEffort to ModelTextResult interface\n- Include reasoningEffort in model gateway response results for text and agent step generation\n- Log reasoningEffort in agent runtime debug logs for model prompts and responses\n- Update tests to verify reasoningEffort is properly returned in results",
"is_bot": false,
"headline": "feat: expose reasoningEffort in model results and logging",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T16:14:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a5fe758d042e213f51fe379c3af8f59a12499e58",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.57.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-04T15:57:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "87e49e6e1e926918f79fa12f321ea732bdee2554",
"body": "- Add reasoningEffort provider config field with values: none, minimal, low, medium, high, xhigh\n- Implement /effort and /reasoning slash commands for TUI reasoning effort management\n- Add setGlobalReasoningEffort and getConfiguredReasoningEffort config functions\n- Map reasoning effort to provider-s\n[…]\nntation for slash commands and model config\n- Include reasoning effort in startup thread and TUI status line\n- Add comprehensive tests for reasoning effort configuration and Codex provider integration",
"is_bot": false,
"headline": "feat: add reasoning effort configuration and /effort slash command",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T15:56:33Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "7ae0f80ce8a9fd39ab31a45a558f8bb97f4475d4",
"body": "…OpenAI-compatible providers\n\n- Update decision #5 to specify provider-edge mapping for Codex, OpenRouter, and generic OpenAI-compatible providers\n- Clarify scope excludes only non-Codex/non-OpenRouter providers beyond generic OpenAI-compatible fallback\n- Add ReasoningParamStyle type and provider-ed\n[…]\n case behavior for OpenRouter (nested reasoning object) vs generic fallback (reasoning_effort field)\n- Add cross-slice rule for provider-edge mapper to avoid baking provider-specific names into config",
"is_bot": false,
"headline": "docs: expand reasoning effort plan to include OpenRouter and generic …",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T15:41:45Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5c5151024edccf122ac7cc2594c04768566bdb9c",
"body": null,
"is_bot": false,
"headline": "chore: fix bad links",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T15:24:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c4d0103e119bde36af51f0ef1a82942810fb6619",
"body": null,
"is_bot": false,
"headline": "docs: update changelog",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T15:21:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "39642361fe5e65b7d679c9fecb7bef2ca6706efa",
"body": null,
"is_bot": false,
"headline": "chore: fix agents.md",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T15:19:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "81522240fd6e7ad40ec8ddd533a4c520f19c7f77",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.56.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-04T15:15:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "45da447c2ef86a8fe629cdfcc46bc42a3049c4c1",
"body": "- Document topchester integrations commands (status, install, repair, remove)\n- Clarify that integrations commands manage generated hook config for supported agents\n- Add integrations feature to changelog",
"is_bot": false,
"headline": "docs: add topchester integrations command documentation",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T15:14:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9d7f372132cadf9e6973267fee148e4d6986274b",
"body": null,
"is_bot": true,
"headline": "chore: release topchester-ai v0.55.0",
"author_name": "github-actions[bot]",
"author_login": "github-actions[bot]",
"committed_at": "2026-06-04T15:13:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "61b355e5cc20be73ae6635604ba85bc96ad6d5f1",
"body": "- Add 'topchester integrations' command group for managing agent integrations\n- Add 'topchester hook stop' low-level endpoint for installed integrations\n- Support install, repair, remove, list, and status operations for Codex\n- Update CLI documentation with new commands and examples\n- Add comprehensive integration management in integrations.ts module",
"is_bot": false,
"headline": "feat: add integrations and hook stop commands",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T15:12:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "279dead3341d5a7906d951fb4d13bfd64181f5c9",
"body": "Add comprehensive implementation plan for /effort and /reasoning slash commands\nto set Codex reasoning effort levels. Includes competitor analysis, current state,\ndesign decisions, implementation shape, and seven implementation slices covering\nconfig contract, request plumbing, config mutation, slash command surface, TUI\nhandling, status display, and documentation.",
"is_bot": false,
"headline": "docs: add codex reasoning effort slash commands plan",
"author_name": "Dragan Bajcic",
"author_login": "kodi",
"committed_at": "2026-06-04T15:00:56Z",
"body_truncated": false,
"is_coding_agent": false
}
],
"releases_count": 1,
"commits_last_year": 358,
"latest_release_at": "2026-05-15T21:27:20Z",
"latest_release_tag": "v0.18.0",
"releases_from_tags": true,
"days_since_last_push": 4,
"active_weeks_last_year": 11,
"days_since_latest_release": 67,
"mean_days_between_releases": null
},
"community": {
"has_readme": true,
"has_license": true,
"has_description": false,
"has_contributing": false,
"health_percentage": 28,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": []
},
"popularity": {
"forks": 0,
"stars": 2,
"watchers": 0,
"fork_history": {
"days": [],
"complete": true,
"collected": 0,
"total_forks": 0
},
"star_history": {
"days": [
{
"date": "2026-05-28",
"count": 1
},
{
"date": "2026-07-11",
"count": 1
}
],
"complete": true,
"collected": 2,
"total_stars": 2
},
"open_issues_and_prs": 0
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [],
"has_llms_txt": false,
"has_dockerfile": true,
"has_mcp_signal": true,
"bootstrap_files": [
".mise.toml"
],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [
"bench/mini-bench/tsconfig.json",
"tsconfig.json"
],
"toolchain_manifests": [],
"largest_source_bytes": 99572,
"source_files_sampled": 235,
"oversized_source_files": 3,
"agent_instruction_files": [
"AGENTS.md",
"docs/AGENTS.md",
"scripts/smoke/scenarios/18-project-instructions-root/template/AGENTS.md",
"scripts/smoke/scenarios/19-project-instructions-nested-edit/template/AGENTS.md",
"scripts/smoke/scenarios/19-project-instructions-nested-edit/template/src/AGENTS.md"
],
"agent_instruction_max_bytes": 7898
},
"dependencies": {
"manifests": [
"package.json"
],
"advisories": {
"error": null,
"scope": null,
"source": null,
"findings": [],
"collected": false,
"malicious": [],
"truncated": false,
"by_severity": {},
"advisory_count": 0,
"affected_count": 0,
"assessed_count": 0,
"malicious_count": 0,
"assessed_package": null,
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [
"npm"
],
"dependencies": [
{
"name": "@ai-sdk/openai-compatible",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^2.0.48"
},
{
"name": "@modelcontextprotocol/sdk",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^1.29.0"
},
{
"name": "@opentui/core",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "0.4.4"
},
{
"name": "@opentui/solid",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "0.4.4"
},
{
"name": "ai",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^6.0.196"
},
{
"name": "commander",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^15.0.0"
},
{
"name": "htmlparser2",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^12.0.0"
},
{
"name": "picomatch",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^4.0.4"
},
{
"name": "pino",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^10.3.1"
},
{
"name": "solid-js",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "1.9.12"
},
{
"name": "turndown",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^7.2.4"
},
{
"name": "uuidv7",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "1.2.1"
},
{
"name": "yaml",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^2.9.0"
},
{
"name": "zod",
"manifest": "package.json",
"ecosystem": "npm",
"version_constraint": "^4.4.3"
}
],
"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": 0,
"merged_prs": 5,
"open_issues": 0,
"closed_ratio": null,
"closed_issues": 0,
"closed_unmerged_prs": 0
},
"bus_factor": 1,
"bot_contributors": 1,
"top_contributors": [
{
"type": "User",
"login": "kodi",
"commits": 279,
"avatar_url": "https://avatars.githubusercontent.com/u/51153?v=4"
},
{
"type": "User",
"login": "cursoragent",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/199161495?v=4"
}
],
"contributors_sampled": 2,
"top_contributor_share": 0.996
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"code-quality.yml",
"nightly-smoke.yml",
"publish-npm.yml"
],
"has_docs_dir": true,
"linter_configs": [],
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [
"pnpm-lock.yaml"
],
"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": 0,
"reason": "branch protection not enabled on development/release branches",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": 10,
"reason": "1 out of 1 merged PRs checked by a CI test -- score normalized to 10",
"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": 0,
"reason": "Found 0/21 approved changesets -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 3,
"reason": "project has 1 contributing companies or organizations -- score normalized to 3",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
},
{
"name": "Dangerous-Workflow",
"score": 10,
"reason": "no dangerous workflow patterns detected",
"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": 10,
"reason": "license file detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 0,
"reason": "project was created within the last 90 days. Please review its contents carefully",
"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": 0,
"reason": "dependency not pinned by hash detected -- score normalized to 0",
"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": 0,
"reason": "detected GitHub workflow tokens with excessive permissions",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
},
{
"name": "Vulnerabilities",
"score": 0,
"reason": "14 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "ff81b6be671a81cd870155d25f8c0a731f3f98f4",
"ran_at": "2026-07-21T22:41:56Z",
"aggregate_score": 2.5,
"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": "2026-07-21T04:25:05Z",
"oldest_open_prs": [],
"last_merged_pr_at": "2026-07-17T03:30:35Z",
"ci_last_conclusion": "SUCCESS",
"oldest_open_issues": []
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/kodi/topchester-agent",
"host": "github.com",
"name": "topchester-agent",
"owner": "kodi"
},
"metrics": {
"overall": {
"key": "overall",
"band": "at_risk",
"name": "Overall health",
"note": null,
"notes": [],
"value": 48,
"inputs": {
"security": 25,
"vitality": 66,
"community": 24,
"governance": 47,
"engineering": 67
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "moderate",
"name": "Vitality",
"value": 66,
"weight": 0.22,
"metrics": [
{
"key": "development_activity",
"band": "moderate",
"name": "Development activity",
"note": null,
"notes": [],
"value": 62,
"inputs": {
"commits_last_year": 358,
"human_commit_share": 0.76,
"days_since_last_push": 4,
"active_weeks_last_year": 11
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 4 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 4
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "11/52 weeks with commits",
"points": 7.6,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 11
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "358 commits in the last year",
"points": 18,
"status": "met",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 358
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "project was created within the last 90 days. Please review its contents carefully",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "good",
"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": 72,
"inputs": {
"releases_count": 1,
"latest_release_tag": "v0.18.0",
"releases_from_tags": true,
"days_since_latest_release": 67,
"mean_days_between_releases": null
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "1 version tags (no GitHub releases)",
"points": 16.2,
"status": "partial",
"details": [
{
"code": "version_tags_no_releases",
"params": {
"count": 1
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 67 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 67
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "cadence unknown (single release)",
"points": 12.6,
"status": "partial",
"details": [
{
"code": "release_cadence_unknown",
"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": 2,
"watchers": 0,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "below_threshold"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "2 stars",
"points": 0,
"status": "missed",
"details": [
{
"code": "stars",
"params": {
"count": 2
}
}
],
"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": "moderate",
"name": "Community health",
"note": null,
"notes": [],
"value": 50,
"inputs": {
"has_readme": true,
"has_license": true,
"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": "recognized license (MIT)",
"points": 22.5,
"status": "met",
"details": [
{
"code": "license_standard",
"params": {}
},
{
"code": "license_spdx",
"params": {
"spdx": "MIT"
}
}
],
"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
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "at_risk",
"name": "Sustainability & Governance",
"value": 47,
"weight": 0.24,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 15,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 2,
"top_contributor_share": 0.996
},
"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 100% of commits",
"points": 0.1,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 100
}
}
],
"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 1 contributing companies or organizations -- score normalized to 3",
"points": 3,
"status": "partial",
"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": 72,
"inputs": {
"merged_prs": 5,
"open_issues": 0,
"closed_issues": 0,
"issue_closed_ratio": null,
"closed_unmerged_prs": 0
},
"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": "5/5 decided PRs merged",
"points": 38.2,
"status": "met",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 5,
"decided": 5
}
}
],
"max_points": 38.25
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 0/21 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "moderate",
"name": "Ownership & stewardship",
"note": "Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"verified_domain"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 60,
"inputs": {
"followers": 61,
"owner_type": "User",
"is_verified": null,
"owner_login": "kodi",
"public_repos": 58,
"account_age_days": 6378
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "personal (user) account",
"points": 10,
"status": "partial",
"details": [
{
"code": "owner_personal",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": "not applicable to user accounts",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_applicable_to_user_accounts",
"params": {}
}
],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "61 followers of kodi",
"points": 12.9,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 61,
"login": "kodi"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "58 public repos, account ~17 yr old",
"points": 24.9,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 58
}
},
{
"code": "account_age_years",
"params": {
"years": 17
}
}
],
"max_points": 25
}
]
}
],
"description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
},
{
"key": "engineering",
"band": "moderate",
"name": "Engineering Quality",
"value": 67,
"weight": 0.2,
"metrics": [
{
"key": "engineering_practices",
"band": "moderate",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 68,
"inputs": {
"has_ci": true,
"has_tests": true,
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"components": [
{
"key": "ci_workflows",
"name": "CI workflows",
"detail": "3 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 3
}
}
],
"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": "1 out of 1 merged PRs checked by a CI test -- score normalized to 10",
"points": 20,
"status": "met",
"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": "critical",
"name": "Security",
"value": 25,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "critical",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): Packaging, Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"packaging",
"signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 25,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 16,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 2,
"scorecard_aggregate": 2.5
},
"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": "branch protection not enabled on development/release branches",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "1 out of 1 merged PRs checked by a CI test -- score normalized to 10",
"points": 2.5,
"status": "met",
"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 0/21 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 0.8,
"status": "partial",
"details": [],
"max_points": 2.5
},
{
"key": "dangerous_workflow",
"name": "Dangerous-Workflow",
"detail": "no dangerous workflow patterns detected",
"points": 10,
"status": "met",
"details": [],
"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 detected",
"points": 2.5,
"status": "met",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "project was created within the last 90 days. Please review its contents carefully",
"points": 0,
"status": "missed",
"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": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"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": "detected GitHub workflow tokens with excessive permissions",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "vulnerabilities",
"name": "Vulnerabilities",
"detail": "14 existing vulnerabilities detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
}
]
},
{
"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": 2
},
"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": 69,
"weight": 0,
"metrics": [
{
"key": "ai_agent_context",
"band": "excellent",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 85,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 0.987,
"agent_instruction_files": [
"AGENTS.md",
"docs/AGENTS.md",
"scripts/smoke/scenarios/18-project-instructions-root/template/AGENTS.md",
"scripts/smoke/scenarios/19-project-instructions-nested-edit/template/AGENTS.md",
"scripts/smoke/scenarios/19-project-instructions-nested-edit/template/src/AGENTS.md"
],
"agent_instruction_max_bytes": 7898
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "AGENTS.md, docs/AGENTS.md, scripts/smoke/scenarios/18-project-instructions-root/template/AGENTS.md, scripts/smoke/scenarios/19-project-instructions-nested-edit/template/AGENTS.md, scripts/smoke/scenarios/19-project-instructions-nested-edit/template/src/AGENTS.md",
"points": 45,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "AGENTS.md, docs/AGENTS.md, scripts/smoke/scenarios/18-project-instructions-root/template/AGENTS.md, scripts/smoke/scenarios/19-project-instructions-nested-edit/template/AGENTS.md, scripts/smoke/scenarios/19-project-instructions-nested-edit/template/src/AGENTS.md"
}
}
],
"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": "75 of 76 human commits state their intent (structured subject or explanatory body)",
"points": 40,
"status": "met",
"details": [
{
"code": "legible_history",
"params": {
"legible": 75,
"sampled": 76
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "moderate",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 63,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [
"pnpm-lock.yaml"
],
"has_dockerfile": true,
"typed_language": true,
"bootstrap_files": [
".mise.toml"
],
"has_devcontainer": false,
"has_linter_config": false,
"typecheck_configs": [
"bench/mini-bench/tsconfig.json",
"tsconfig.json"
],
"agent_commit_share": 0.01,
"toolchain_manifests": [],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": ".mise.toml",
"points": 18,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": ".mise.toml"
}
}
],
"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": "bench/mini-bench/tsconfig.json, tsconfig.json",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "bench/mini-bench/tsconfig.json, tsconfig.json"
}
}
],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": "Dockerfile, lockfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "Dockerfile, lockfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "1 of the last 100 commits agent-authored or agent-credited",
"points": 2,
"status": "partial",
"details": [
{
"code": "agent_authored_commits",
"params": {
"count": 1,
"sampled": 100
}
}
],
"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": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "excellent",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 99,
"inputs": {
"primary_language": "TypeScript",
"largest_source_bytes": 99572,
"source_files_sampled": 235,
"oversized_source_files": 3
},
"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": "3/235 source files over 60KB",
"points": 54.3,
"status": "partial",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 235,
"oversized": 3
}
}
],
"max_points": 55
}
]
},
{
"key": "ai_interfaces",
"band": "critical",
"name": "Machine-readable interfaces",
"note": null,
"notes": [],
"value": 20,
"inputs": {
"example_dirs": [],
"has_mcp_signal": true,
"api_schema_files": []
},
"components": [
{
"key": "api_schema_openapi_graphql_proto",
"name": "API schema (OpenAPI/GraphQL/proto)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 40
},
{
"key": "mcp_server",
"name": "MCP server",
"detail": null,
"points": 20,
"status": "met",
"details": [],
"max_points": 20
},
{
"key": "runnable_examples",
"name": "Runnable examples",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 40
}
]
}
],
"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": "2026-07-21T22:42:04.563388Z",
"schema_version": "0.25.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/k/kodi/topchester-agent.svg",
"full_name": "kodi/topchester-agent",
"license_state": "standard",
"license_spdx": "MIT"
}
Пов’язані записи
Перевірені репозиторії, що мають спільні каталожні теги або екосистеми з kodi/topchester-agent. Читати поруч →
Оцінки — це сигнали, а не гарантії. Вони відображають публічно видимі практики на GitHub — це не аудит коду й не гарантія безпеки.
Відсутні дані виключаються, а ваги перенормовуються — нуль за відсутність ніколи не ставиться. Методологія версіонована й відкрита: метрики v1.13.0, схема v0.25.0 — повна методологія · вікі метрик.
Як окремий результат виглядає на тлі всього реєстру: сукупна статистика.
