controlloop-security

Controlloop — Development skill for Claude Code

Development community

Know what your agents can do, before they do it.

How to install Controlloop

This entry records only its repository, not the path inside it, so there is no exact command to give. Open controlloop-security/controlloop and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Controlloop does

Know what your agents can do, before they do it. A local-first scanner and CI gate that reads agent artifacts, MCP configs, Claude Code/Codex/Cursor settings, and framework code, and blocks pull requests that widen an agent’s authority.

Alternatives in Development

Haft — Engineering decisions engine that know when they're stale 1.4k ★
Stop Review Gate — You are reviewing uncommitted changes before the author finishes their turn 664 ★
Engage.Gate — Run gate validation on the current phase before proceeding 348 ★

README

[![CI](https://github.com/controlloop-security/controlloop/actions/workflows/ci.yml/badge.svg)](https://github.com/controlloop-security/controlloop/actions/workflows/ci.yml) [![License: Apache-2.0](https://img.shields.io/badge/license-Apache--2.0-blue.svg)](LICENSE) [![Python 3.12](https://img.shields.io/badge/python-3.12-blue.svg)](#requirements) [![Docs](https://img.shields.io/badge/docs-controlloop-3157d5.svg)](docs/readme.md) [![Discord](https://img.shields.io/badge/discord-join-5865F2.svg?logo=discord&logoColor=white)](https://discord.gg/Ef4VuTvUFn)

*Know what your agents can do. Before they do it.*

ControlLoop is a local-first scanner and deterministic CI gate for what your AI agents can actually do. It reads the files that define an agent, builds one graph of its capabilities, compares it to the state you approved, and fails the build when the agent's authority grows past the ceiling you declared. It never runs your code and never sends your source anywhere.

[![Play the one-minute overview: ControlLoop blocks a pull request that widens an agent's authority](docs/assets/readme/hero-poster.jpg)](https://controlloop.ai/#video)

Watch: [the gate in a minute](https://controlloop.ai/#video) · Read: [the example walkthrough](docs/guides/example-walkthrough.md)

ControlLoop CLI

An agent's real authority is spread across an agent card, an MCP config, an OpenAPI spec, an IAM policy, and, for most agents, the framework code itself: a CrewAI crew, a LangGraph graph, an OpenAI Agents SDK handoff chain. The same goes for the coding agents that work on your repository. Claude Code, Codex, Gemini CLI, Cursor, Kiro, Roo Code, and Cline are configured by committed files, and so are the workflows that run an agent in CI. No single file tells you that one pull request just gave an agent the ability to move money, or to run a script on every session start.