agentleFS
apmantzaapmantza/pi-lens/llms.txt

pi-lens

llms.txt530 starsChanged 16 days agoMITView on GitHub

pi-lens is an extension for the pi coding agent that runs language servers, linters, formatters, and structural rules on every file an agent writes or edits, and feeds the findings back to the agent.

The file

Files
llms.txt
# pi-lens

> pi-lens is an extension for the pi coding agent that runs language servers, linters, formatters, and structural rules on every file an agent writes or edits, and feeds the findings back to the agent.

## Using pi-lens

- [Agent guide](docs/agent-guide.md): how an agent reads and responds to pi-lens findings, honesty labels, and blockers
- [Agent tools](docs/agent-tools.md): tool names, scopes, and arguments
- [Usage guide](docs/usage.md): lifecycle, on-write pipeline, runtime flags, MCP notes, and troubleshooting
- [Settings](docs/settings.md): defaults, environment variables, flags, and global versus project config
- [Features](docs/features.md): the detailed feature reference
- [Tools and commands](docs/tools.md): slash commands and the standalone CLI
- [Diagnostic dispositions](docs/dispositions.md): mark a finding false-positive, suppressed, deferred, or flagged-to-fix
- [Language coverage](docs/language-coverage.md): supported languages, runners, and formatters
- [Word index](docs/word-index.md): identifier search and the discovery funnel
- [Custom rules](docs/custom-rules.md): project ast-grep and tree-sitter rules
- [MCP server](docs/mcp.md): the experimental server for Claude Code and other MCP clients
- [Architecture](docs/architecture.md): how host events reach the findings the agent sees

## Contributing

- [AGENTS.md](AGENTS.md): the contributor contract for agents that change pi-lens itself
- [CONTRIBUTING.md](CONTRIBUTING.md): development workflow, checklists, and issue and PR conventions

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.