IronLint runs the checks your project already trusts, so an AI coding workflow gets the same clear pass or fail result as a local command or CI job. Define the commands once in .ironlint.yml, then run them after a change or when work is ready to review.
Claude Code
> /plugin marketplace add ironlint/ironlint> /plugin install ironlint-claude-code@ironlint-marketplace
GitHub Copilot
$ copilot plugin marketplace add ironlint/ironlint$ copilot plugin install ironlint-claude-code@ironlint-marketplace
IronLint runs the checks your project already trusts, so an AI coding workflow
gets the same clear pass or fail result as a local command or CI job. Define the
commands once in .ironlint.yml, then run them after a change or when work is
ready to review.
It is for developers who want project rules to be executable instead of buried in prompts, review comments, or a checklist. IronLint does not invent rules or change files: it runs the commands you choose and reports their output.
version: 1
checks:
format:
files: ["*.rs", "Cargo.toml"]
on: [change, accept]
run: cargo fmt --all --check
tests:
run: cargo test --locked
With that policy in the project root:
ironlint validate
ironlint trust
ironlint check --event change --file src/lib.rs
ironlint check --event accept --format json
change runs the fast checks that apply to known changed paths. accept runs
every check, which makes it the command to use before treating a change as
complete. Output is human-readable by default and available as JSON for tools.
To build the version in this repository, install Rust 1.88 or newer and a POSIX
sh (Git Bash or WSL on Windows).
git clone https://github.com/ironlint/ironlint.git
cd ironlint
cargo install --locked --path crates/ironlint-cli
ironlint --version
change and accept.A policy can run arbitrary shell commands with your account's permissions.
Review it before running ironlint trust; trust records your local approval and
is renewed when the policy or a script under .ironlint/scripts/ changes. It
does not sandbox those commands, cover other files a command might invoke, or
replace protections in your hosting or CI system.
Licensed under Apache 2.0.
Stars on GitHub
Helps you take a change from a rough idea or bug report through to a tested, reviewed result, with each step handled by a focused skill. Its skills cover pinning down domain terms, designing module interfaces, diagnosing hard bugs, and reviewing changes against your repo's coding standards.
@mattpocockA development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
@obraGives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
@affaan-mDeveloper tools for working on the React codebase itself. Provides skills for extracting error messages, managing and debugging feature flags across release channels, running Flow type checks, and fixing lint and formatting issues before committing.
@facebookIronLint runs the checks your project already trusts, so an AI coding workflow gets the same clear pass or fail result as a local command or CI job. Define the commands once in .ironlint.yml, then run them after a change or when work is ready to review. Install it with the command on its page. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it