Agent skill

Cas Worker

by codingagentsystem in codingagentsystem/cas

Factory worker guide for task execution in CAS multi-agent sessions.

MITAuto-check passedAgent Workflows

Install Cas Worker

skills CLI
$ npx skills add codingagentsystem/cas --skill cas-worker -a claude-code

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

GitHub CLI
$ gh skill install codingagentsystem/cas cas-worker --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/codingagentsystem/cas.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/cas-worker .claude/skills/cas-worker && 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
cas-worker
GitHub stars
176
Token cost
~1.2k tokens
SKILL.md length
480 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Factory worker guide for task execution in CAS multi-agent sessions.

  • Works in 5 steps: No shortcut markers → All new code is wired up → Changed signatures don't break callers → …
  • Acting as a worker to execute assigned tasks
  • SKILL.md covers Workflow, Blockers, Communication and Pre-Close Self-Verification…, plus 4 more sections
  • Calls rg, git and cargo

What it does

Cas Worker is an agent skill from codingagentsystem/cas. Factory worker guide for task execution in CAS multi-agent sessions. Use when acting as a worker to execute assigned tasks, report progress, handle blockers, and communicate with the supervisor.

Its SKILL.md is about 1.2k 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 Multi-agent orchestration. It works with Model Context Protocol. The repository describes itself as: Multi-agent orchestration for Claude Code. Persistent memory, tasks, rules, and skills that make AI agents actually coordinate. The licence is MIT.

When your agent uses it

  • Acting as a worker to execute assigned tasks
  • Report progress
  • Handle blockers
  • Communicate with the supervisor

Example prompts

  • “/cas-worker”

Workflow steps

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

  1. No shortcut markers
  2. All new code is wired up
  3. Changed signatures don't break callers
  4. Tests pass
  5. No dead code left behind

What it can do on your machine

Read from SKILL.md and the folder at commit a0a4b5a. 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:

    • rg
    • git
    • cargo

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Cas Worker loads about 1.2k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 480 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 codingagentsystem/cas at commit a0a4b5a, republished under its MIT licence (© codingagentsystem). 480 words, ~1,247 tokens.

Download SKILL.mdSave it as .claude/skills/cas-worker/SKILL.md (or your agent's skills folder).
name
cas-worker
description
Factory worker guide for task execution in CAS multi-agent sessions. Use when acting as a worker to execute assigned tasks, report progress, handle blockers, and communicate with the supervisor.
managed_by
cas

Factory Worker

You execute tasks assigned by the Supervisor. You may be working in an isolated git worktree or sharing the main working directory — check your environment with mcp__cas__coordination action=my_context.

Workflow

  1. Check assignments: mcp__cas__task action=mine
  2. Start a task: mcp__cas__task action=start id=<task-id>
  3. Read task details and understand acceptance criteria before coding: mcp__cas__task action=show id=<task-id>
  4. Implement the solution, committing after each logical unit of work
  5. Report progress: mcp__cas__task action=notes id=<task-id> notes="..." note_type=progress
  6. Close when done: mcp__cas__task action=close id=<task-id>

If close returns verification-required guidance, message the supervisor to handle it.

Blockers

Report immediately — don't spend time stuck:

mcp__cas__task action=notes id=<task-id> notes="Blocked: <reason>" note_type=blocker
mcp__cas__task action=update id=<task-id> status=blocked

Communication

Never use SendMessage. It is blocked in factory mode. Always use CAS coordination:

mcp__cas__coordination action=message target=supervisor message="<response>" summary="<brief summary>"

Use task notes for ongoing updates (note_type=progress|blocker|decision|discovery). The supervisor sees these in the TUI.

Message the supervisor when you complete a task or need help.

Pre-Close Self-Verification (REQUIRED before closing)

Before running mcp__cas__task action=close, verify your own work. The task-verifier will reject you if any of these fail — save yourself the round-trip.

1. No shortcut markers
bash
# Must return zero results in your changed files
rg 'TODO|FIXME|XXX|HACK|unimplemented!|todo!' <changed_files>
rg 'for now|temporarily|placeholder|stub|workaround' <changed_files>
2. All new code is wired up

For every new function, struct, module, route, or handler you created:

bash
# Verify it's actually called/imported somewhere outside its definition
rg 'your_new_function' src/
ast-grep --lang rust -p 'your_new_function($$$)' src/

If zero external references → you built it but didn't wire it in. Fix before closing.

Registration checklist:

  • New CLI command → added to Commands enum + match arm?
  • New MCP tool → registered in tool list?
  • New route → added to router?
  • New migration → listed in migration runner?
  • New config field → has a default, is read somewhere?
3. Changed signatures don't break callers
bash
# If you changed a function signature, verify all call sites compile
ast-grep --lang rust -p 'changed_function($$$)' src/
4. Tests pass
bash
cargo test  # or equivalent for the project
5. No dead code left behind
bash
# Check for allow(dead_code) on your new code
rg '#\[allow\(dead_code\)\]' <changed_files>

Only close after all checks pass. The verifier will catch what you miss — but rejections cost time.

Show full SKILL.md (207 more words)Show less

Task Types

Spike tasks (task_type=spike) are investigation tasks — they produce understanding, not code. When assigned a spike, your deliverable is a decision, comparison, or recommendation captured in task notes (note_type=decision). Spike acceptance criteria are question-based (e.g., "Which approach handles our constraints?").

Demo statements — If a task has a demo_statement, it describes what should be demonstrable when the task is complete. Use it to guide your implementation toward observable, verifiable outcomes.

Rules

  • One task at a time — complete current before taking another
  • Test before closing
  • No TODO/FIXME/placeholder code in completed work
  • Verify all new code is wired up before closing
  • Document important choices with note_type=decision

Syncing (Isolated Mode)

If the supervisor asks you to sync, safely rebase without losing WIP:

bash
git stash                   # save uncommitted work
git rebase <branch>         # use the branch name the supervisor gives you (e.g. master, epic/<slug>)
git stash pop               # restore WIP

Important: Use the local branch name the supervisor specifies (e.g. master, epic/<slug>), NOT origin/master. In factory mode, the supervisor merges into the local branch directly, so origin/master is stale.

If the rebase has conflicts, resolve them before popping the stash. Message the supervisor if you're stuck.

Worktree Issues (Isolated Mode)

Submodule not initialized: Worktrees don't include submodules. Symlink from the main repo:

bash
ln -s /path/to/main/repo/vendor/<submodule> vendor/<submodule>

Build errors in code you didn't touch: Another worker may be changing related files. Focus on your assigned files; report to supervisor only if truly blocked.

© codingagentsystem, 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 .claude/skills/cas-worker of codingagentsystem/cas.

Open the folder on GitHubat commit a0a4b5a

Compare with similar skills

Cas Worker 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.

Cas Worker compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cas Worker this skillcodingagentsystem/cas176—~1.2kAutomated safety check: PassMIT
Codex with ChatGPT Planning LoopXiaoDuoYa/codex-with-chatgpt7.1k—~11kAutomated safety check: NotesMIT
MemPalace Task HandoffMemPalace/mempalace59k—~1.9kAutomated safety check: PassMIT
agtx One-Shot Project Runnerfynnfluegge/agtx1.7k—~3.8kAutomated safety check: PassApache-2.0
Puppetmaster Agent Orchestrationprofessorpalmer/Puppetmaster467—~3.2kAutomated safety check: PassMIT
Agent Manager Fleet TUIYoanWai/agent-manager576—~1kAutomated safety check: PassApache-2.0

Similar skills

  • Codex with ChatGPT Planning Loop

    XiaoDuoYa/codex-with-chatgpt

    Uses ChatGPT in the browser as the planning and review brain for a Codex session, with Codex keeping all execution and ChatGPT reading the workspace through a bridge.

    7.1k GitHub stars~11k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check: notes
  • MemPalace Task Handoff

    MemPalace/mempalace

    Creates, hands off, claims, executes and closes agent tasks through the MemPalace logstream, with approval of the exact task before it is recorded.

    59k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.

    1.7k GitHub stars~3.8k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed
  • Puppetmaster Agent Orchestration

    professorpalmer/Puppetmaster

    Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs.

    467 GitHub stars~3.2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Agent Manager Fleet TUI

    YoanWai/agent-manager

    Runs several coding-agent CLIs as real tmux sessions in one terminal UI, color-coded by whether each is working, waiting, idle or blocked.

    576 GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Generate Harness Dsl

    QoderAI/better-harness

    Generate, revise, or review complete Harness as Code .harness files when a coding-agent workflow, agent role, skill, tool contract, MCP connection, runtime, or deployment must be compiler-valid and…

    2.4k GitHub stars~761 tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed

More from codingagentsystem/cas

  • Cas Search

    codingagentsystem/cas

    Search across CAS content (memories, tasks, rules, skills, code).

    176 GitHub stars~516 tokensUpdated 6 mo ago
    Auto-check passed
  • Cas Supervisor

    codingagentsystem/cas

    Factory supervisor guide for multi-agent EPIC orchestration.

    176 GitHub stars~1.8k tokensUpdated 6 mo ago
    Auto-check passed
  • Cas

    codingagentsystem/cas

    Coding Agent System - unified memory, tasks, rules, and skills.

    176 GitHub stars~723 tokensUpdated 6 mo ago
    Auto-check passed
  • Cas Memory Management

    codingagentsystem/cas

    How to store and retrieve persistent memories using CAS. An agent skill from codingagentsystem/cas.

    176 GitHub stars~255 tokensUpdated 6 mo ago
    Auto-check passed
  • Cas Supervisor Checklist

    codingagentsystem/cas

    Quick startup checklist for factory supervisors. An agent skill from codingagentsystem/cas.

    176 GitHub stars~349 tokensUpdated 6 mo ago
    Auto-check passed
  • Cas Task Tracking

    codingagentsystem/cas

    How to track work using CAS tasks instead of built-in TodoWrite.

    176 GitHub stars~279 tokensUpdated 6 mo ago
    Auto-check passed

Categories

Questions about Cas Worker

What does Cas Worker do?

Factory worker guide for task execution in CAS multi-agent sessions. Cas Worker is an agent skill from codingagentsystem/cas. Factory worker guide for task execution in CAS multi-agent sessions.

When should I use Cas Worker?

Cas Worker fits situations like: acting as a worker to execute assigned tasks; report progress; handle blockers; communicate with the supervisor.

How do I install Cas Worker in Claude Code?

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

How do I install Cas Worker in Codex?

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

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

What does Cas Worker need to run?

Going by SKILL.md and its folder, Cas Worker needs the command-line tools its instructions call (rg, git and cargo).

Does Cas Worker access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Cas Worker 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 Cas Worker use?

Cas Worker 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 Cas Worker use?

About 1.2k tokens (SKILL.md is roughly 5k 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 Cas Worker?

Skills that share tags, products or a category with Cas Worker: Codex with ChatGPT Planning Loop (XiaoDuoYa/codex-with-chatgpt, 7.1k stars), MemPalace Task Handoff (MemPalace/mempalace, 59k stars), agtx One-Shot Project Runner (fynnfluegge/agtx, 1.7k stars) and Puppetmaster Agent Orchestration (professorpalmer/Puppetmaster, 467 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cas Worker?

codingagentsystem (a GitHub organization) maintains it in codingagentsystem/cas, which has 176 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on March 12, 2026.

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