New: 98,000+ 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

Retinue

by jklthinking in jklthinking/retinue

Coordinate work through a local Retinue workspace using its MCP tools.

MITAuto-check passedAgent Workflows

Install Retinue

skills CLI
$ npx skills add jklthinking/retinue --skill retinue -a claude-code

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

GitHub CLI
$ gh skill install jklthinking/retinue retinue --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/jklthinking/retinue.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/retinue .claude/skills/retinue && 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
retinue
GitHub stars
115
Token cost
~279 tokens
SKILL.md length
139 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Coordinate work through a local Retinue workspace using its MCP tools.

  • Works in 6 steps: Call my_tasks before starting work. → Use task_new to create a queued card.… → If you hold a queued or handoff card,… → …
  • Asked to create
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Inspect Retinue task cards

What it does

Retinue is an agent skill from jklthinking/retinue. Coordinate work through a local Retinue workspace using its MCP tools. Use when asked to create, claim, update, hand off, complete, or inspect Retinue task cards.

Its SKILL.md is about 280 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers and Task management. It works with Model Context Protocol, SQLite, FastAPI and React. The repository describes itself as: Self-hosted coordination for AI workers: per-task graphs, device/model timelines, progress receipts, and source-aware usage. MIT. The licence is MIT.

When your agent uses it

  • Asked to create
  • Inspect Retinue task cards

Example prompts

  • “/retinue”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Call my_tasks before starting work.
  2. Use task_new to create a queued card. Give it a unique task-YYYYMMDD-NNN id, a concrete title, an honest priority, and observable…
  3. If you hold a queued or handoff card, call task_update with status="doing" and a short, factual note.
  4. Do the work and run every item in acceptance.
  5. Call task_update with status="done" only after those checks pass. Use status="handoff" plus holder when another agent must review or…
  6. Call task_receipt and report the returned receipt exactly.

What it can do on your machine

Read from SKILL.md and the folder at commit 72aff26. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Retinue loads about 279 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 139 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~279

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

The full file from jklthinking/retinue at commit 72aff26, republished under its MIT licence (© jklthinking). 139 words, ~279 tokens.

Download SKILL.mdSave it as .claude/skills/retinue/SKILL.md (or your agent's skills folder).
name
retinue
description
Coordinate work through a local Retinue workspace using its MCP tools. Use when asked to create, claim, update, hand off, complete, or inspect Retinue task cards.

Retinue coordination

Retinue task cards are the canonical record. Use the MCP tools; do not edit YAML directly.

  1. Call my_tasks before starting work.
  2. Use task_new to create a queued card. Give it a unique task-YYYYMMDD-NNN id, a concrete title, an honest priority, and observable acceptance criteria.
  3. If you hold a queued or handoff card, call task_update with status="doing" and a short, factual note.
  4. Do the work and run every item in acceptance.
  5. Call task_update with status="done" only after those checks pass. Use status="handoff" plus holder when another agent must review or continue. Use status="blocked" plus blocked_reason only for a real blocker.
  6. Call task_receipt and report the returned receipt exactly.

Only the current holder may update a card. Every status or holder change needs a receipt-quality note. Never skip from queued directly to done.

© jklthinking, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/retinue of jklthinking/retinue.

Open the folder on GitHubat commit 72aff26

Compare with similar skills

Retinue 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.

Retinue compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Retinue this skilljklthinking/retinue115—~279Automated safety check: PassMIT
Soul Interviewldbumble/taskuary138—~1.4kAutomated safety check: PassMIT
Taskuary Setupldbumble/taskuary138—~1.5kAutomated safety check: PassMIT
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
Memorywhalewuisabel-gif/MemWhale154—~765Automated safety check: PassMIT
Context7 MCP Skillholon-run/uxc116—~564Automated safety check: PassMIT

Similar skills

  • Soul Interview

    ldbumble/taskuary

    Conduct a seven-question adaptive interview and turn the answers into Taskuary's SOUL.md.

    138 GitHub stars~1.4k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Taskuary Setup

    ldbumble/taskuary

    Walk the owner through setting Taskuary up - the AI brain, where work arrives, the operator documents, reports and workflows - by reading the install's real state and using the screens that already…

    138 GitHub stars~1.5k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Memorywhale

    wuisabel-gif/MemWhale

    Query and write durable debugging memory recorded by MemoryWhale.

    154 GitHub stars~765 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Context7 MCP Skill

    holon-run/uxc

    Query up-to-date library documentation and code examples using Context7 MCP.

    116 GitHub stars~564 tokensUpdated 24 days ago
    Agent WorkflowsAuto-check passed

  • Memorywhale Evidence

    wuisabel-gif/MemWhale

    Use MemoryWhale debugging evidence when the user requests recall or a recurring failure may have relevant recorded history.

    154 GitHub stars~459 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

Works with

Categories

Questions about Retinue

What does Retinue do?

Coordinate work through a local Retinue workspace using its MCP tools. Retinue is an agent skill from jklthinking/retinue. Coordinate work through a local Retinue workspace using its MCP tools.

When should I use Retinue?

Retinue fits situations like: asked to create; inspect Retinue task cards.

How do I install Retinue in Claude Code?

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

How do I install Retinue in Codex?

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

Can I use Retinue 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 jklthinking/retinue --skill retinue -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/retinue, .gemini/skills/retinue, .github/skills/retinue and .opencode/skills/retinue in your project.

What does Retinue need to run?

SKILL.md names no scripts, command-line tools or credentials: Retinue is instructions for the agent only.

Does Retinue access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Retinue 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 Retinue use?

Retinue is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Retinue use?

About 279 tokens (SKILL.md is roughly 1.1k 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 Retinue?

Skills that share tags, products or a category with Retinue: Soul Interview (ldbumble/taskuary, 138 stars), Taskuary Setup (ldbumble/taskuary, 138 stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars) and Memorywhale (wuisabel-gif/MemWhale, 154 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Retinue?

jklthinking (a GitHub user) maintains it in jklthinking/retinue, which has 115 GitHub stars. The repository was last updated on October 8, 2026.

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