agentleFS
Sign inStart free
open-coder-aiopen-coder-ai/chock/llms.txt

chock

llms.txt10 starsChanged 32 days agoApache-2.0View on GitHub

Blocks your coding agent's wrong moves before they land. Chock compiles a policy you author once into the strongest enforcement surface each agent supports (git hook, CI gate, AGENTS.md rule, Claude Code / Cursor pre-tool-use hooks, Copilot / VS Code agent hooks, managed settings) and reports coverage per agent using an honest taxonomy (src/chock/compile/levels.py): none, best-effort, fail-to-ask, enforceable, enforced, enforced-at-commit, advisory, disabled. An enforcement level is only claimed when there is an install witness for it — never because a…

  • Installs packages

We split this llms.txt into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No agent reaches enforced.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 3,225 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# chock

> Blocks your coding agent's wrong moves before they land.

Chock compiles a policy you author once into the strongest enforcement surface each agent
supports (git hook, CI gate, `AGENTS.md` rule, Claude Code / Cursor pre-tool-use hooks,
Copilot / VS Code agent hooks, managed settings) and reports coverage per agent using an
honest taxonomy (`src/chock/compile/levels.py`): `none`, `best-effort`, `fail-to-ask`,
`enforceable`, `enforced`, `enforced-at-commit`, `advisory`, `disabled`. An enforcement level
is only claimed when there is an install witness for it — never because a rule merely compiled.
No agent reaches `enforced`; the commit and CI gates are what enforce.

Install: chock is on PyPI, but the release there (0.15.2, 30 Sep 2026) is older than the engine
this page describes. Install the frozen engine from its commit:
`pip install "chock @ git+https://github.com/open-coder-ai/chock@992711af4cf8d4fd9c4c861f10ef6e53374d75d7"`
(Python 3.11 or newer).

Chock is pre-1.0: the CLI surface, manifest schema, and compiled output can change between
MINOR releases. See Compatibility below for what is actually guaranteed today.

## Start here

- [Getting Started](https://github.com/open-coder-ai/chock/blob/main/docs/getting-started.md): install, onboard a repo, author your first policy
- [Core Concepts](https://github.com/open-coder-ai/chock/blob/main/docs/concepts.md): artifacts, manifests, surfaces, coverage
- [CLI Reference](https://github.com/open-coder-ai/chock/blob/main/docs/cli-reference.md): every command, flag, and example

## What it enforces, honestly

- [Agentic-Risk Coverage](https://github.com/open-coder-ai/chock/blob/main/docs/agentic-risk-coverage.md): problem-first index of what Chock stops, at which honest tier, and what it does not
- [Enforcement Surfaces](https://github.com/open-coder-ai/chock/blob/main/docs/enforcement-surfaces.md): the nine surfaces and the per-agent coverage matrix
- [Compatibility](https://github.com/open-coder-ai/chock/blob/main/docs/compatibility.md): pre-1.0 stability guarantees — what may change between versions, and what pinning guarantees

## Policies and catalog

- [Policies](https://github.com/open-coder-ai/chock/blob/main/docs/baseline-policies.md): what the base catalog offers, and how to install and customize it
- [Authoring Policies](https://github.com/open-coder-ai/chock/blob/main/docs/authoring-policies.md): write rules, hooks, skills, and subagents
- [Registry & Lockfile](https://github.com/open-coder-ai/chock/blob/main/docs/registry-and-lockfile.md): reproducible, hash-pinned distribution

## Other

- [Architecture](https://github.com/open-coder-ai/chock/blob/main/docs/architecture.md): the author → compile → enforce model
- [Agent Plugins](https://github.com/open-coder-ai/chock/blob/main/docs/agent-plugins.md): packaging policies for the open plugin standard, and what that does not buy
- [Contributing](https://github.com/open-coder-ai/chock/blob/main/CONTRIBUTING.md): development setup and how to propose a policy
- [Changelog](https://github.com/open-coder-ai/chock/blob/main/CHANGELOG.md)

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.

Reviews can't be read right now.

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