Controllers Policy

Controllers Policy is an AI Engineering skill for Claude Code, published by Th0rgal in sandboxed.sh.

491 stars50 forkson Th0rgal/sandboxed.shAdded 2026/08/26+1% in starsRepository updated 2026/08/20

ai-agentsautonomous-agentsclaudeclaude-codecoding-assistantcontainerizationdeveloper-toolsllmmcpokxopencodeorchestrationself-hostedweb3workspace-isolationxagent-hackathon

Install in seconds

Install Controllers Policy

Copy Controllers Policy into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Th0rgal/sandboxed.sh/tree/master/skills/controllers-policy ~/.claude/skills/controllers-policy

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Th0rgal/sandboxed.sh.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/controllers-policy/SKILL.md in Th0rgal/sandboxed.sh
Installs to: ~/.claude/skills/controllers-policy
Collection: One of 8 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Controllers Policy does

Controllers Policy defines the autonomy contract, safety limits, and routing rules for autonomous project controllers. Use it to decide when to act, merge, pause, or escalate during each tick.

Controllers Policy is cataloged under AI Engineering on DirSkills. Controllers Policy comes from a repository tagged ai-agents, autonomous-agents, claude, claude-code and coding-assistant.

Documentation

README

Excerpt

Autonomous Controllers Policy

You are a controller: you own this project's forward progress. The cron prompt carries the objective and project-specific gates. THIS document is the source of truth for autonomy, safety, and process. When they conflict, apply the precedence below.

Autonomy contract

Default posture: act. There is no "awaiting authorisation" state. If a lane is READY, dispatch it. If a PR is green and in scope, merge it. If a decision has a defensible answer, take it and say which one and why. You have standing authority to dispatch missions, open and merge PRs, re-order your roadmap and re-tag your own missions, without asking first. Report decisions; do not request permission. A controller that only observes is misconfigured.

This is the opening of the README. Read the full README on GitHub.

Commands Controllers Policy provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/goal

Frequently asked about Controllers Policy

What else does Th0rgal publish alongside Controllers Policy?
Controllers Policy is one of 8 skills that DirSkills catalogs from Th0rgal/sandboxed.sh, the repository it ships in. Its siblings there include Hermes Mission Control, Library Management and Orchestrator Advisor. Each one is a separate skill with its own page in this directory, installs the same way Controllers Policy does, and is maintained by Th0rgal in that same repository. The rest of the collection is listed on the Th0rgal/sandboxed.sh page.
How does Controllers Policy compare to other AI Engineering skills?
Controllers Policy ranks #2184 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Controllers Policy against them. Open each page to compare what they document and how they install.