πŸ€–
AI EngineeringHTML

Coco Loop

by coco-research

Coco Loop is an AI Engineering skill for Claude Code, published by coco-research in coco.

218 stars11 forkson coco-research/cocoAdded 2026/09/04Repository updated 2026/09/03
agent-skillsagents-mdaiai-agentsclaude-codecodexcursordeveloper-toolsllm-toolsmcppm-toolsproduct-managementproductivityprompt-engineeringworkflow-automation
Install in seconds
Install Coco Loop
Copy Coco Loop 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/coco-research/coco/tree/main/skills/coco-loop ~/.claude/skills/coco-loop

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

Without Node.js

git clone https://github.com/coco-research/coco.git

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

In this catalog

Source file
skills/coco-loop/SKILL.md in coco-research/coco
Installs to
~/.claude/skills/coco-loop
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering β€” 2970 skills

What Coco Loop does

Coco Loop turns a plain-language goal into a governed, propose-only autonomous loop. Use it when you want a bounded session that proposes fixes, runs under a constitution, and never commits on its own.

Coco Loop is cataloged under AI Engineering on DirSkills. Coco Loop comes from a repository tagged agent-skills, agents-md, ai, ai-agents and claude-code.

Documentation

README

coco-loop

Turn a plain-language goal into a governed, propose-only loop. You compile the goal into a charter, the person confirms it, and the loop runs under the coco-loops framework: it proposes changes, a separate verifier judges them, and nothing is committed. The loop stops itself when its lifetime cap of active work is spent.

The framework enforces an immutable constitution underneath every charter. You cannot write a charter that disables the verifier, commits without approval, edits the constitution, sends content to raw public-cloud endpoints, or runs unattended destructive operations. The coco-loops charter command rejects any charter that tries. Do not attempt to work around it. Present the floor to the person as a feature.

Prerequisites

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

Frequently asked about Coco Loop

  • What else does coco-research publish alongside Coco Loop?

    Coco Loop is one of 25 skills that DirSkills catalogs from coco-research/coco, the repository it ships in. Its siblings there include AI Marketing Videos, AI Product Development and API Design Principles. Each one is a separate skill with its own page in this directory, installs the same way Coco Loop does, and is maintained by coco-research in that same repository. The rest of the collection is listed on the coco-research/coco page.

  • How does Coco Loop compare to other AI Engineering skills?

    Coco Loop ranks #2601 by stars among the 2970 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 Coco Loop against them. Open each page to compare what they document and how they install.

More from coco-research/coco

Coco Loop is one of 25 skills cataloged on DirSkills from coco-research/coco.

See all 25 skills β†’
🎬
2h ago

AI Marketing Videos

AI Marketing Videos creates marketing videos for ads, promos, launches, and brand content. Use it to generate product demos, explainers, social ads, testimonials, and voiceover-backed video workflows.
AI Engineering
21811
πŸ€–
2h ago

AI Product Development

AI Product Development helps ship production-grade AI features with LLM integration, RAG, prompt engineering, streaming, safety guardrails, and cost control. It is used when building AI products that need structured outputs, validation, and user trust.
AI Engineering
21811
πŸ”—
2h ago

API Design Principles

API Design Principles helps you design and review REST and GraphQL APIs with clear resources, methods, versioning, pagination, and error handling. Use it when defining API standards or improving existing endpoints.
AI Engineering
21811
⚑
2h ago

Agent Lightning

Agent Lightning trains AI agents with reinforcement learning, prompt optimization, and supervised fine-tuning. Use it to instrument agents with traces, configure LightningStore, define rewards, and run RL or APO training loops.
AI Engineering
21811
πŸ›οΈ
2h ago

Arb Review

Arb Review generates an 11-slide architecture review board deck from PRD, architecture maps, and project context. Use it to prepare a sign-off presentation with diagrams, risks, NFRs, and a decision ask.
AI Engineering
21811
πŸ—ΊοΈ
2h ago

Arch Index

Arch Index builds and validates .arch/index.json, a commit-pinned map from architectural components to the real files that implement them. It is used to find component implementation files and detect when architecture docs drift from the code.
Automation
21811