mauhprmauhpr/agentlint/docs/llms.txt

agentlint

llms.txt140 starsChanged 35 days agoMITView on GitHub

Local rule and heuristic checks for proposed coding-agent file changes and shell commands. Supported integrations can block errors and return actionable feedback. AgentLint is not an OS sandbox; integration coverage varies.

The file

Create a free account to mount

Files

llms.txt

# AgentLint

> Local rule and heuristic checks for proposed coding-agent file changes and shell commands. Supported integrations can block errors and return actionable feedback. AgentLint is not an OS sandbox; integration coverage varies.

## Getting started
- [Overview](https://mauhpr.github.io/agentlint/)
- [Quickstart](https://mauhpr.github.io/agentlint/quickstart/)
- [Coverage and security boundary](https://mauhpr.github.io/agentlint/coverage/)
- [Integrations](https://mauhpr.github.io/agentlint/#agents)

## Native agent guides
- [Claude Code](https://mauhpr.github.io/agentlint/agents/claude/)
- [Codex](https://mauhpr.github.io/agentlint/agents/codex/)
- [Cursor](https://mauhpr.github.io/agentlint/agents/cursor/)
- [Gemini CLI](https://mauhpr.github.io/agentlint/agents/gemini/)
- [Continue](https://mauhpr.github.io/agentlint/agents/continue/)
- [Kimi Code CLI](https://mauhpr.github.io/agentlint/agents/kimi/)
- [Grok CLI](https://mauhpr.github.io/agentlint/agents/grok/)

## Other integrations
- [OpenAI Agents SDK](https://mauhpr.github.io/agentlint/agents/openai-agents/) — attach guardrails to supported tools
- [MCP hosts](https://mauhpr.github.io/agentlint/agents/mcp-hosts/) — advisory, on-demand checks
- [Generic integration](https://mauhpr.github.io/agentlint/agents/generic/) — callers enforce returned decisions

## Task guides
- [Protect main](https://mauhpr.github.io/agentlint/guides/protect-main/)
- [Fix a false positive](https://mauhpr.github.io/agentlint/guides/fix-a-false-positive/)
- [Run linters and formatters](https://mauhpr.github.io/agentlint/guides/run-linters/)
- [Share required rules](https://mauhpr.github.io/agentlint/guides/shared-policy/)

## Reference
- [Rules](https://mauhpr.github.io/agentlint/rules/)
- [Configuration](https://mauhpr.github.io/agentlint/configuration/)
- [Approvals and evidence](https://mauhpr.github.io/agentlint/approvals-and-evidence/)
- [Diagnostics](https://mauhpr.github.io/agentlint/diagnostics/)
- [CI](https://mauhpr.github.io/agentlint/ci/)
- [CLI](https://mauhpr.github.io/agentlint/cli/)
- [Optional cloud and privacy](https://mauhpr.github.io/agentlint/agentchute/)

## Extending AgentLint
- [Custom rules](https://mauhpr.github.io/agentlint/custom-rules/)
- [Custom adapters](https://mauhpr.github.io/agentlint/custom-adapters/)
- [Architecture](https://mauhpr.github.io/agentlint/architecture/)
- [Subagent safety](https://mauhpr.github.io/agentlint/subagent-safety/)
- [Source](https://github.com/mauhpr/agentlint)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free