abide plugin

Claude Code hooks that check each edit against your AGENTS.md rules and make the agent fix it. An API key is needed and edits go to an external model

  • 614 ★ on the repository
  • Last commit
  • MIT
Plugin

Extended access

Why this level

  • Edits are sent to an external model by your key
  • The init command adds hooks to agents on the machine
All reasons and checks

coldteadotai/abide

Install

Works in

Manual install

npx @coldtea/abide login

Then npx @coldtea/abide init (or init claude). An API key is needed and edits go to an external model.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Edits are sent to an external model by your key
  • The init command adds hooks to agents on the machine

This is third-party code. Review the repository files before installing.

What it does

abide installs hooks in Claude Code that check each edit or turn against the rules of your AGENTS.md and make the agent fix a violation. Installation: `npx @coldtea/abide login` (a key is pasted once), then `npx @coldtea/abide init` in the repository or `init claude` for Claude Code. A checking API key is needed: edits are sent to an external model. The key is stored in `~/.abide/.env` or in the project `.env.local`. MIT license.

Who it is for. For teams that want to automatically check that an agent follows the rules from AGENTS.md and get fixes right away.

Good fit when

  • You need automatic checking of AGENTS.md rules on each edit
  • You want the agent to fix violations itself
  • You need Claude Code hooks for rule compliance

Not a fit when

  • You cannot send edits to an external model
  • You cannot install hooks into all agents on the machine

Example request

Check the latest edit against the AGENTS.md rules and fix violations if there are any

Limitations

For checking each edit is sent to an external model by your API key, so code goes to the provider: check that it is allowed. The init command adds hooks to agents on the machine, so see what it changes. The author's figures about the violation share and speed are his measurements. Access is extended.

How to disable. Remove the skill from the agent's folder or the plugin through the plugin manager.

FAQ

What does abide do?

It checks each agent edit against the AGENTS.md rules and makes it fix violations.

Where do edits go?

To an external model by your API key.

How do I install it?

npx @coldtea/abide login, then npx @coldtea/abide init.

Discussion

No questions or reviews yet.

Plugins

A Claude Code plugin that generates and maintains CLAUDE.md: a 0 to 100 quality score, a 150-line cap and stale reference checks

PluginExtended access430Repository stars
Needs a VPN

A ready-made Claude Code setup: agents, slash commands, skills, safety hooks, rules and MCP connections in one install

PluginBroad access866Repository stars

A CLI that generates and maintains AI context files, CLAUDE.md, Cursor rules, AGENTS.md and Copilot instructions, keeping them accurate as code changes

CLIExtended access1.3KRepository stars

A Claude Code and Codex plugin with skills for code research, tests, refactoring and independent review of finished changes

PluginExtended access450Repository stars

A CLI that keeps agent instructions in one place and distributes them to the right config files for Claude Code, Cursor, Codex, Copilot and two dozen other tool

CLIExtended access3KRepository stars

Ready infrastructure for Claude Code: skill auto-activation via hooks, a skill set, agents, slash commands and a wizard that installs it into your project

SkillExtended access10KRepository stars

README in short

The README describes Claude Code hooks for checking edits against AGENTS.md with an API key and installation through npx. MIT license.

README badge

Report a problem

Foxx AIabide
Foxx AI

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.