Agent skill

Task

by mweinbach in mweinbach/agent-coworker

Hand ordinary chat off to durable Task mode when the user explicitly invokes /task or requests a managed task.

Custom licenceAuto-check: warnings

Install Task

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add mweinbach/agent-coworker --skill task -a claude-code

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

GitHub CLI
$ gh skill install mweinbach/agent-coworker task --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/mweinbach/agent-coworker.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/task .claude/skills/task && 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
task
GitHub stars
156
Token cost
~979 tokens
SKILL.md length
536 words
Files
2
Skills in repo
8
Repo updated
First seen
Licence
Custom licence

At a glance

Hand ordinary chat off to durable Task mode when the user explicitly invokes /task or requests a managed task.

  • Explicitly invokes /task
  • SKILL.md covers Decide whether to create a task, Gather enough detail, Build the initial plan and Perform the handoff
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Requests a managed task

What it does

Task is an agent skill from mweinbach/agent-coworker. Hand ordinary chat off to durable Task mode when the user explicitly invokes /task or requests a managed task. Complexity, progress tracking, or a need for a plan alone does not authorize a handoff; continue that work in the current chat.

Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: Terminal-first coworker agent (Bun + OpenTUI).

When your agent uses it

  • Explicitly invokes /task
  • Requests a managed task

Example prompts

  • “/task”

What it can do on your machine

Read from SKILL.md and the folder at commit aab9dc6. 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

Task loads about 979 tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 536 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~979

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: warnings

The automated check found patterns that need a careful read before installing.

  • WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:29
    st. If the user supplied enough detail, do not ask for confirmation before creating the task.

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 (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 536 words (~979 tokens).

“Task mode is a one-way handoff from the current chat to a managed task. A successful createTask call replaces the chat with the task workspace and locks the source chat until the task reaches completed, failed, or cancelled.”

— opening of SKILL.md by mweinbach, Custom licence
name
task

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in skills/task of mweinbach/agent-coworker.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit aab9dc6

Compare with similar skills

Task 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.

Task compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Task this skillmweinbach/agent-coworker156—~979Automated safety check: WarnCustom licence
Hand Drawn Diagramsnexu-io/open-design100k—~336Automated safety check: PassApache-2.0
Durable Test Collateralasgeirtj/system_prompts_leaks69k—~687Automated safety check: PassCC0-1.0
Durable Objectscloudflare/skills3k2 repos~1.5kAutomated safety check: PassApache-2.0
Hand Drawnthreerocks/hand-drawn-styles1.4k—~234Automated safety check: PassMIT
Twitter Hand SkillRightNow-AI/openfang18k—~2.9kAutomated safety check: PassApache-2.0

Similar skills

  • Hand Drawn Diagrams

    nexu-io/open-design

    Generate hand-drawn Excalidraw diagrams from a prompt — animated SVG, hosted edit link, and PNG export.

    100k GitHub stars~336 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Durable Test Collateral

    asgeirtj/system_prompts_leaks

    Load the body before the first implementation edit for a bug fix or behavior change, or when the user or governing specification makes reusable tests a deliverable.

    69k GitHub stars~687 tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Durable Objects

    cloudflare/skills

    Official

    Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.

    3k GitHub starsUsed in 2 repos~1.5k tokens
    Backend & APIsAuto-check passed
  • Hand Drawn

    threerocks/hand-drawn-styles

    A skill your agent uses when users ask for a hand-drawn or illustrated image prompt, name one of the repository's 18 numbered styles or the 3.1 stable variant, or mention triggers such as…

    1.4k GitHub stars~234 tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Twitter Hand Skill

    RightNow-AI/openfang

    Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking

    18k GitHub stars~2.9k tokensUpdated 3 mo ago
    Writing & ContentAuto-check passed
  • All Hands Deck

    mohitagw15856/pm-claude-skills

    Build an all-hands that lands with everyone from intern to VP — the mixed-altitude structure (the story for all, the numbers for some), the wins-with-names section done right, the hard-news slide…

    1.4k GitHub stars~1.5k tokensUpdated yesterday
    Writing & ContentAuto-check passed

More from mweinbach/agent-coworker

All 8 skills in this repo
  • AI Elements Chat Components

    mweinbach/agent-coworker

    Adds AI Elements components such as conversations, messages, tool displays and prompt inputs to a Next.js project that uses shadcn/ui.

    156 GitHub starsUsed in 5 repos~1.8k tokens
    Auto-check passed
  • Expo Brownfield Integration

    mweinbach/agent-coworker

    Helps add Expo and React Native to an existing native iOS or Android app, and choose between a prebuilt AAR or XCFramework and a fully integrated build.

    156 GitHub starsUsed in 2 repos~900 tokens
    Auto-check: notes
  • Use Dom

    mweinbach/agent-coworker

    Use Expo DOM components to run web code in a webview on native and as-is on web.

    156 GitHub starsUsed in 5 repos~2.4k tokens
    Auto-check passed
  • Bun Runtime and Toolkit

    mweinbach/agent-coworker

    Quick reference for using Bun to run TypeScript and JavaScript, install packages, bundle code, run tests and serve HTTP, with the key files and commands.

    156 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check: notes
  • Workflow

    mweinbach/agent-coworker

    Author and run a deterministic multi-agent workflow — a JavaScript script that fans out, pipelines, loops, and judges across many child agents.

    156 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed
  • Improve Animations

    mweinbach/agent-coworker

    Audit a codebase's animation and motion, produce prioritized improvement plans, and execute selected plans when requested.

    156 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

Questions about Task

What does Task do?

Hand ordinary chat off to durable Task mode when the user explicitly invokes /task or requests a managed task. Task is an agent skill from mweinbach/agent-coworker. Hand ordinary chat off to durable Task mode when the user explicitly invokes /task or requests a managed task.

When should I use Task?

Task fits situations like: explicitly invokes /task; requests a managed task.

How do I install Task in Claude Code?

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

How do I install Task in Codex?

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

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

What does Task need to run?

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

Does Task 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 Task safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Task use?

Task has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Task use?

About 979 tokens (SKILL.md is roughly 3.9k 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 Task?

Skills that share tags, products or a category with Task: Hand Drawn Diagrams (nexu-io/open-design, 100k stars), Durable Test Collateral (asgeirtj/system_prompts_leaks, 69k stars), Durable Objects (cloudflare/skills, 3k stars) and Hand Drawn (threerocks/hand-drawn-styles, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task?

mweinbach (a GitHub user) maintains it in mweinbach/agent-coworker, which has 156 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 6, 2026.

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