#agents-md

Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.

Git diff for repository instructions. Shows the blast radius of AGENTS.md and CLAUDE.md changes across Codex, Claude Code, Gemini CLI, and Copilot CLI.

all human experts into AI agents

Agile for age of agents — turn work into durable, inspectable cards that humans and LLMs can collaborate on.

Cross-agent prompt pocket: remember your most-used prompts and pick one to run. Works on Claude Code, Codex, OpenCode, Cursor, Copilot & Gemini; auto-scans Claude/Codex/OpenCode sessions for prompts you repeat 7+ times. Forged by agent-plugin-kit.

Cross-platform kit that gives AI agents (Claude Code, Codex, Cursor) persistent memory: Markdown vault + git + MCP. Local-first, hybrid search optional.

See what your AI coding agent silently drops from its instruction files. A byte-exact truncation X-ray for AGENTS.md / CLAUDE.md / .cursorrules.

Copy-in kit of config-driven agent skills, agents, and CI templates — native to Claude Code and adaptable to any AGENTS.md-reading agent.

One config for every AI coding agent — cross-tool config + a cognitive substrate (memory, blast-radius, guardrails) for Claude Code, Codex, Cursor, Gemini, Aider, and more.

✨ 管好 Claude Code 的一整套记忆机制 —— CLAUDE.md · auto-memory · .claude/rules · 磁盘，自动生成 / 体检 / 进化，不用手写不惦记维护

A drop-in CLAUDE.md starter and a guide to getting better HTML artifacts out of coding agents. HTML, not Markdown — that's the point.

Guardrails for AI coding agents. EADOS generates a governed repo - agent contract, ADRs, CI gates, SemVer - for any of 19 languages, then enforces the rules with lint. Works with Claude Code, Codex, and Gemini.

Author one AI coding harness once, project it onto Claude Code, Codex, OpenCode, Cline, Kilo Code & Pi — then let it improve itself from execution traces (arXiv:2603.28052).

Portable agent patterns: reviewers and gates that deploy to Claude Code, Codex, Cursor, or any AGENTS.md harness from one source of truth.

Run Claude Code as a teammate that owns work end to end. A maintained CLAUDE.md (works as AGENTS.md) plus a plan/execute/review skill pipeline with external verification, adversarial review, and structurally safe parallel execution. Dated changelog, updated when model behaviour changes.

AI Coding Host Context Pack AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for cline/cline.

One canonical hub for your AI agents' skills, rules & memory — shared across Claude Code, Codex, Warp, Cursor, Gemini, Grok & OpenCode via symlinks. Single-command macOS setup.

Which open-source projects have a written rule about AI-written pull requests: 703 of GitHub's top 800 repos screened. Free dataset, CC BY 4.0.

Agent Skill for using secrets from a local KeePassXC database — kp:// references, in-process resolution, env injection and output redaction. Works in Claude Code, Codex, Cursor, Gemini CLI and any AGENTS.md harness

Write AI coding-agent skills once. Compile to every tool — Claude Code, Cursor, Codex, Windsurf, Aider, OpenCode, Gemini CLI, Copilot, Continue.

Agent skill that scaffolds a repository so coding agents navigate it from committed docs — AGENTS.md doc index, docs/ standards, and commit-time gates.

LLM Eval Context Pack AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for promptfoo/promptfoo.

A Claude skill that turns a codebase into an explorable isometric diagram, with real data moving along the edges

Write your AI agent knowledge once. Compile it to every agent config format - CLAUDE.md, AGENTS.md, .cursor/rules and more.

SECS (SECurity aSsistant) turns an AI coding agent (Claude Code, Cursor, Codex) into an authorized information-security assistant - 35 security Agent Skills, a Debian/Ubuntu/Kali toolchain installer, and a local Metasploitable 3 practice lab, under strict rules of engagement.

One AGENTS.md, every AI coding agent. Sync the rules files (Claude Code, Cursor, Copilot, Windsurf, Gemini, Cline +10 more) and lint them before they rot.

Agentic template repo: hash-pinned AGENTS.md kernel, one check.sh gauntlet mirrored in CI, memory that learns from external signal and forgets on schedule. Cross-harness: Claude Code, Codex, any AGENTS.md reader.

AI Software Engineer Context Pack AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for OpenHands/OpenHands.

Interview-driven AI-coding setup: safety gates, an independent AI judge, session memory, curated skills — one command, nothing installs blindly

Stateful Agent Runtime Pack AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for langchain-ai/langgraph.

Org-wide control plane for AI coding agent configuration — one source of truth for AGENTS.md, CLAUDE.md, skills, and MCP config

MCP Framework Context Pack AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for PrefectHQ/fastmcp.

Copyable Claude Code + GitHub Copilot configuration: AGENTS.md operating manual, CLAUDE.md, copilot-instructions, rules, skills, subagents, hooks, and a gated 7-stage SDLC (spec review, self code review, PR-bot triage). Token-efficient agentic coding you vendor into your repo and adapt with /adopt.

A coding-discipline spec for OpenAI's Codex CLI, enforced by native Codex hooks + a rule-hit telemetry loop. Turns an AGENTS.md the model drifts from into a system that holds. Independent of oh-my-codex.

Code-free, multi-tool AI assistant configuration for Claude Code, GitHub Copilot, OpenAI Codex, Gemini CLI, Cursor, Windsurf, and Ollama. AGENTS.md as single source of truth, adversarial skills suite, strict token & context discipline, per-tool tactics. Drop-in via submodule or bootstrap script.