aaditya1273/agent.md

概览

Your AI coding agent reads CLAUDE.md, AGENTS.md, rules, skills, hooks and MCP configs before it reads a line of your code, then does what they say. Agent.md them (26 deterministic checks), the hard rules through compaction, "never" lines into real deny rules, and every install the agent runs. Any repo. Ten seconds. No account. Nothing uploaded. It reads CLAUDE.md, AGENTS.md, GEMINI.md, Cursor and Copilot rules, every SKILL.md and the scripts beside it, subagents, hooks, memory files and MCP configs, for . Free, open source, runs locally. Precision first: , every reference finding checked by hand, plus 4,292 registry files and 272 skill scripts. What it cannot see: docs/KNOWN-LIMITS.md. Every coding agent reads a rules file first, on every prompt, and trusts it more than your code. Nobody reviews those files like code, and nothing enforces what they say. In 320 runs across 40 projects, . Claude Code noticed the conflict in 79 of 80 runs and followed the file anyway.

README

以下为原文 README 节选，完整内容请查看原文。

  Agent context audit  acme-app
  2 files an agent reads · ~52 tokens loaded on every prompt

     1  secrets in files the agent reads
     1  prompt-injection signals
     1  dangerous patterns in 1 skill script
     1  references to files that no longer exist
     1  formatting rules a formatter already enforces  auto-fixable

  ERROR   .claude/skills/deploy/scripts/run.sh:2  skill-payload
          Downloads code and pipes it straight into a shell.
  ERROR   CLAUDE.md:4  secret
          Looks like an Anthropic API key. Instruction files are sent to the model on every session.
  ERROR   CLAUDE.md:6  injection
          An HTML comment carries an instruction. GitHub hides comments from reviewers but the agent reads them.

推荐工具

换一个关键词，或者移除筛选条件。

安装