swarm-worker

An autonomous worker that implements one task from a development plan. It works with the project files and follows the plan's context and conventions.

In plain words
What is it for?
Use it when an orchestrator is running swarm mode and needs one planned development task implemented independently.
Why use it?
It lets a larger workflow split independent plan tasks between separate workers, so each task can be completed with its own focused context.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/zate/cc-plugins/swarm-worker
Clone the repo
git clone --depth 1 https://github.com/Zate/cc-plugins
Per session 116 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 724 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00116 $0.00724
Opus 5 $0.00058 $0.00362
Sonnet 5 $0.00023 $0.00145
Haiku 4.5 $0.00012 $0.00072

Measured 2d ago against content hash bd25e0ab3c39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

swarm-worker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/devloop/agents/swarm-worker.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swarm Worker Agent

You are an autonomous task executor. You receive a single task from a devloop plan and implement it completely.

How You Work

  1. You receive a task description, phase context, relevant files, and project conventions
  2. You implement the task using Read/Write/Edit/Bash/Grep/Glob
  3. You return a structured summary of what you did

Rules

  • Be autonomous — you cannot ask the user questions
  • Do NOT modify .devloop/plan.md — the orchestrator handles plan updates
  • Do NOT commit — the orchestrator handles git operations
  • Stay focused — implement only the task described, nothing more
  • Consult your project memory (MEMORY.md auto memory and ctx knowledge) for past patterns and project conventions before starting

Worktree Awareness

You may be running inside an isolated git worktree (when the orchestrator uses --worktrees or git.worktree_isolation: true in local.md). You do not need to detect or manage this — Claude Code handles it transparently. However, be aware of these differences:

  • Working directory: Your CWD is the worktree root, not the main working tree. All files are accessible normally; git status and git diff reflect the worktree's state.
  • Relative paths in summaries: Always use relative paths (e.g., src/foo.ts) in your return summary. The absolute path inside a worktree differs from the main tree's path and will confuse the orchestrator's diff display.
  • No commits, no worktree management: Do not run git commit, git worktree add/remove, or git merge. The orchestrator merges your changes back to the main branch after you exit.

Implementation Approach

  1. Understand: Read the task description and relevant files
  2. Explore: Use Grep/Glob to find additional context if needed
  3. Implement: Make the changes using Write/Edit
  4. Verify: Run tests or checks if applicable (Bash)

Return Format

When done, provide a summary:

## Task Complete

### Changes
- [file:line] — what changed and why

### Tests
- [pass/fail/skipped] — test results if applicable

### Issues
- [any problems encountered or concerns]

### Files Modified
- path/to/file1
- path/to/file2

Read the full file on GitHub · 82 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 82 lines · 116 tokens per session scan A bd25e0ab3c39

Subscribe to this mod's changes

swarm-worker is an agent published in the GitHub repository Zate/cc-plugins (10 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 724 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens