Disciplined operations for Claude agents.

Keel Skills is a portable governance framework for running Claude agents without breaking things or burning tokens — a goal/method/green-light permission model, cost-aware delegation, and file-grounded context discipline. Install it, configure it per project, done.

Get started →GitHub

Keel Skills stopping an agent told to 'clean up and push': it runs the four-step check, stops at the risky zone, and proposes a scoped plan instead. — The agent got "clean it up and push." Without a rule it just does it. With Keel it hits a hot zone, stops, and proposes a scoped plan.

In plain words

AI assistants that write code can now act on their own — and sometimes they do something you can't undo, like permanently deleting work or publishing to the live system before anyone checked it. Keel Skills is a set of house rules: it lets the assistant handle the small, safe things by itself, but makes it stop and ask you first before anything risky or permanent. You stay in control without watching every step.

The core idea

A four-step check before anything that writes or changes.

Three things look like permission. Only one means go.

Most "go do it" instructions are just a goal or a method

GoalA goal"improve this", "do what's needed", "handle it"Investigate + propose
MethodA method"use a migration", "edit the config", "use a subagent"Still not permission
Green lightA green lighta clear yes to this exact action, or a recorded current decisionActs — within scope

Read-only & proposals are free · risky / outward / undoable / system-rebuilding → ask · doubt → ask

The full model — hot zones, following through, tie-breakers — is on the Permission model page, and specified runtime-neutral in the spec.

Install

Two lines in Claude Code, then scaffold your policy. Full steps in Getting started.

Claude Code

/plugin marketplace add https://github.com/quitohooded/keel-skills
/plugin install keel-skills@keel-skills

Explore the docs

Getting started

Install, scaffold an AGENT_POLICY.md, and run your first guarded session.

Permission model

Goal, method, green light; the four-step check; hot zones; following through.

AGENT_POLICY.md

The single file where your project's hot zones and sources of truth live.

Specification

The runtime-neutral spec so Keel can be reimplemented anywhere.