aaditya1273/agent.md
Developer tools이 페이지는 AI로 자동 번역되었습니다. 기술적인 세부 사항은 원문을 확인하세요. 원문 보기
Your AI coding agent follows these files blindly, before it reads a line of your code.
개요
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
원문 README의 일부입니다. 원문 보기.
What it finds
Real output, on a small example repo:
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.추천 도구
다른 키워드를 입력하거나 필터를 제거해 보세요.
설치
npx skillfish add aaditya1273/agent.md