New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Coco Loop

by coco-research in coco-research/coco

Start a safe, governed autonomous loop from a plain-language goal.

ProprietaryAuto-check passedAgent Workflows

Install Coco Loop

skills CLI
$ npx skills add coco-research/coco --skill coco-loop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install coco-research/coco coco-loop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/coco-research/coco.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/coco-loop .claude/skills/coco-loop && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
coco-loop
GitHub stars
473
Token cost
~1.4k tokens
SKILL.md length
695 words
Files
2
Skills in repo
60
Repo updated
First seen
Licence
Proprietary

At a glance

Start a safe, governed autonomous loop from a plain-language goal.

  • Works in 6 steps: Understand the goal → Compile the charter → Show the charter and confirm → …
  • The user says /coco-loop
  • SKILL.md covers Prerequisites, Flow and What to tell the person
  • Calls git and pip; reaches github.com

What it does

Coco Loop is an agent skill from coco-research/coco. Start a safe, governed autonomous loop from a plain-language goal. Use when the user says /coco-loop, "run an autonomous loop", "keep my build green for N hours", "work on X autonomously for a while", or wants a bounded self-improving loop that proposes fixes and never commits on its own. Turns a vague goal into a readable charter the user confirms, then arms and runs the loop propose-only under the coco-loops governance framework.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in Agent Workflows, covering Autonomous loops and Plain language and style rules. The repository describes itself as: CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 226 skills, 386 commands…

When your agent uses it

  • The user says /coco-loop
  • Run an autonomous loop
  • Keep my build green for N hours
  • Work on X autonomously for a while

Example prompts

  • “run an autonomous loop”
  • “keep my build green for N hours”
  • “work on X autonomously for a while”
  • “/coco-loop”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Understand the goal
  2. Compile the charter
  3. Show the charter and confirm
  4. Install and arm
  5. Give it work and run it
  6. Monitor and hand back

What it can do on your machine

Read from SKILL.md and the folder at commit 6036e9c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Coco Loop loads about 1.4k tokens when it runs. Until then it costs about 111 tokens; SKILL.md has 695 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~111
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Proprietary) doesn't allow us to republish the file, so here is its outline and opening line. It has 695 words (~1,445 tokens).

“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…”

— opening of SKILL.md by coco-research, Proprietary
name
coco-loop
domain
meta

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in skills/coco-loop of coco-research/coco.

  • SKILL.md
  • LICENSE

Open the folder on GitHubat commit 6036e9c

Compare with similar skills

Coco Loop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Coco Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Coco Loop this skillcoco-research/coco473—~1.4kAutomated safety check: PassProprietary
Audit Session Metricscentminmod/my-claude-code-setup2.7k—~2kAutomated safety check: PassMIT
Ponylang Prose Reviewponylang/ponylang-website160—~2.9kAutomated safety check: PassBSD-2-Clause
Make A Planpenpot/penpot61k—~1.6kAutomated safety check: PassMPL-2.0
Inherit Legacy Styleaffaan-m/ECC274k1 repos~2.1kAutomated safety check: NotesMIT
Talk Normalhexiecs/talk-normal1.9k—~784Automated safety check: PassMIT

Similar skills

  • Audit Session Metrics

    centminmod/my-claude-code-setup

    Audit a session-metrics JSON export for token-usage waste and produce a plain-English findings report.

    2.7k GitHub stars~2k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed

  • Ponylang Prose Review

    ponylang/ponylang-website

    Ensemble review of ponylang blog and Last Week in Pony prose.

    160 GitHub stars~2.9k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • Make A Plan

    penpot/penpot

    Planning flow — research the subject of this session, produce an implementation plan with the planner skill, resolve open questions with the user in plain language, and save the final plan to…

    61k GitHub stars~1.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Inherit Legacy Style

    affaan-m/ECC

    Prevent AI style drift on legacy projects by scanning the codebase for implicit conventions, resolving conflicts with the operator one at a time, and writing an enforceable .ai-style-rules.md…

    274k GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check: notes

  • Talk Normal

    hexiecs/talk-normal

    Installs an always-on set of rules into your agent's workspace config that cuts filler, hedging and padded closings from its replies.

    1.9k GitHub stars~784 tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

  • Caveman Mode

    JuliusBrussee/caveman

    Switches the agent to a terse reply style that gives the answer first, drops filler, and keeps every technical fact, command and number exact.

    110k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from coco-research/coco

All 60 skills in this repo

  • Coco Ads

    coco-research/coco

    Turn the project you just shipped into a short, polished, shareable launch video (an "ad") using HyperFrames.

    473 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Arch Index

    coco-research/coco

    Build and validate .arch/index.json — a committed map from each architectural component of this repository to the real directories and files that implement it, pinned to a git commit, with every…

    473 GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • Skill Evolution

    coco-research/coco

    A skill your agent uses when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one…

    473 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Coco Diagram

    coco-research/coco

    A skill your agent uses for architecture, current-state, process, data-flow, medallion, or DP diagrams, including redrawing .drawio and Mermaid sources.

    473 GitHub stars~9.2k tokensUpdated today
    Auto-check passed

  • Brain

    coco-research/coco

    A skill your agent uses when the user says brain, project knowledge, what do we know about, open tasks, or recent decisions, or runs /brain or /brain-update.

    473 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • M0

    coco-research/coco

    A skill your agent uses when the user says 'm0', 'm0 status', 'start m0', 'cross-tool memory', 'operational thread', or 'where is my memory stored', or when the M0 daemon or MCP wiring needs…

    473 GitHub stars~755 tokensUpdated today
    Auto-check passed

Categories

Questions about Coco Loop

What does Coco Loop do?

Start a safe, governed autonomous loop from a plain-language goal. Coco Loop is an agent skill from coco-research/coco. Start a safe, governed autonomous loop from a plain-language goal.

When should I use Coco Loop?

Coco Loop fits situations like: the user says /coco-loop; run an autonomous loop; keep my build green for N hours; work on X autonomously for a while.

How do I install Coco Loop in Claude Code?

Run `npx skills add coco-research/coco --skill coco-loop -a claude-code`. Or copy the skill folder (skills/coco-loop in coco-research/coco) into .claude/skills/coco-loop in your project. Claude Code loads it when a task matches its description.

How do I install Coco Loop in Codex?

Run `npx skills add coco-research/coco --skill coco-loop -a codex`. Or copy the skill folder (skills/coco-loop in coco-research/coco) into .agents/skills/coco-loop in your project. Codex loads it when a task matches its description.

Can I use Coco Loop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add coco-research/coco --skill coco-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/coco-loop, .gemini/skills/coco-loop, .github/skills/coco-loop and .opencode/skills/coco-loop in your project.

What does Coco Loop need to run?

Going by SKILL.md and its folder, Coco Loop needs the command-line tools its instructions call (git and pip). Our summary lists: Python 3.

Does Coco Loop access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Coco Loop safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Coco Loop use?

Coco Loop carries a proprietary licence (from the LICENSE file in the skill folder). It is published on GitHub, but it is not open source: read the licence file before using or sharing it.

How many tokens does Coco Loop use?

About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Coco Loop?

Skills that share tags, products or a category with Coco Loop: Audit Session Metrics (centminmod/my-claude-code-setup, 2.7k stars), Ponylang Prose Review (ponylang/ponylang-website, 160 stars), Make A Plan (penpot/penpot, 61k stars) and Inherit Legacy Style (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Coco Loop?

coco-research (a GitHub user) maintains it in coco-research/coco, which has 473 GitHub stars. The repository holds 60 skills in this directory. The repository was last updated on October 7, 2026.

Source: coco-research/coco on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.