#claude-code

Φ phi — a terminal multiplexer and browser-based control center for AI coding assistants (OpenCode, Claude Code, Antigravity, Pi Coder).

Interactive question boards & HTML idea visualization for AI coding agents (Claude Code, Codex, …) — ask users structured questions in the browser, await submit, get JSON. Zero deps.

把 codex/claude 接入飞书

Put your coding agent on a kanban board: a local tracker that runs Claude Code, OpenCode or Pi on your tasks, unattended.

Call dibs on files. Coordination for parallel coding agents — file claims with expiry, enforcement hooks, and git-native lessons. One binary, no server, no database.

Local-first context gateway that helps AI coding agents read less, spend less, and stay grounded in your repo.

No repository description published.

Hermes-repo 是面向任意 Git 仓库的命令行工具，将 Hermes 式「经验 → 技能 → 自改进」学习闭环映射到文档与团队约定的工具，适合希望统一「踩坑有记录、契约能升级、 规范能进化」的研发与平台团队。

Encrypt secrets inline in your config and .env files with ENC[…] markers — local keypair or GCP/AWS/Azure KMS. Safe to commit. Ships a setup skill for AI coding agents.

CC What Have I Done (ccwhid) is a CLI tool written in Go that converts your Claude Code session transcripts into easily browsable HTML artefacts.

Prototo: the AI-native prototyping tool for designers. Describe a screen, see it render as a real native iOS app. No canvas, no IDE, no code. Works with Claude Code and Codex.

A股全栈数据工具包：行情K线·当日逐笔·研报·信号·资金面·新闻·财务·公告·打板·ETF期权·舆情·宏观利率·期货大宗(含大商所日K)·事件驱动·可转债 | 15层·87端点·34数据源·除iwencai外免Key | A-share data for AI agents: K-lines, ticks, reports, fund flow, news, financials, filings, options, macro, futures, events, convertibles | 15 layers·87 endpoints·34 sources

The fastest Claude Code statusline: context window, 5-hour, and weekly limit usage as three customizable gradient bars, rendering in about 12 ms

Provider-neutral program planning and agentic delivery workflows

No repository description published.

A desktop pet for ai clients, inspired by codex desktop pets.

A viewer for reviewing local code changes in small individual chapters. Works with any AI agent.

Proof-carrying defensive security reviews for AI-assisted software, with deterministic policy, portable evidence, and human review required.

Claude Code Skills, Agents & Plugins — UitKit

Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Direxio). Chat with your AI dev assistant from anywhere — no public IP required for most platforms.

No repository description published.

Claude Code plugin marketplace: the bitranox skill collection (82 skills) plus a self-improve Stop hook. Skills invoke as /bitranox:<skill>.

Orchestration under Claude Code on herdr: flows an agent cannot skip, jobs on a clock, threads with claims, and a forum agents search later

No repository description published.

A capability router for Claude Code — surfaces the most relevant installed skills per prompt via a local hybrid-retrieval hook. Fully local, fail-open.

Multi-CLI environment switcher for Claude Code, Codex, and OpenCode with API proxy auto-failover.

Automate and accelerate complex projects. Fast, effective, and consistently structured. MCP server, Claude Skills, CLI. JSON output available for AI agents.

Claude Code dashboard: see where your limits are headed before you hit them. Calibrated usage forecasts, live rate-limit gauges, session costs, memory browser. Single binary, zero config, plus a VS Code extension.

Carves your agent's tool outputs down to what matters. Never cuts what doesn't come back.

Local dashboard for spec-driven development: a phased OpenSpec roadmap (WHAT) and an MCP topology (HOW).