worker-agent

worker-agent is a skill for Claude Code from tlangridge/agent-swarm. It costs 27 tokens per session (575 once invoked), scanned A, original, MIT.

A protocol for software agents that receive assigned tasks, work on them, verify the results, and report back.

In plain words
What is it for?
Use it to pick up tasks, update branches and pull requests, share discoveries, and verify completed work.
Why use it?
It prevents an agent from starting unassigned work and gives the team a consistent way to track progress and findings.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

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 skills/tlangridge/agent-swarm/worker-agent
Any agent
npx skills add tlangridge/agent-swarm --skill worker-agent
Clone the repo
git clone --depth 1 https://github.com/tlangridge/agent-swarm

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for worker-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/tlangridge/agent-swarm/worker-agent.svg)](https://agentmods.dev/skills/tlangridge/agent-swarm/worker-agent)
Your own site
<a href="https://agentmods.dev/skills/tlangridge/agent-swarm/worker-agent"><img src="https://agentmods.dev/badge/skills/tlangridge/agent-swarm/worker-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 575 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 5.1 $0.00027 $0.00575
Opus 5 $0.00014 $0.00287
Sonnet 5 $0.00005 $0.00115
Haiku 4.5 $0.00003 $0.00057

Measured 5d ago against content hash 580572ce9cef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

worker-agent 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 5d 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.

skills/worker-agent/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Worker Agent Protocol

You are a WORKER agent. You execute tasks assigned by the lead.

Critical Rule: WAIT for Assignment

Do NOT start working on anything until you have a task assigned to you.

At shift start:

  1. Check for tasks: swarm tasks --mine
  2. If you have tasks assigned, pick one and start working
  3. If you have NO tasks: WAIT. The lead will assign you work.
  4. Do NOT explore the codebase, write code, or take any action without a task assignment.

Work Cycle

  1. Check tasks: swarm tasks --mine
  2. Read context: swarm context and swarm read findings.md for team discoveries
  3. Pick a task: swarm task pick <id> (if deps unmet, find ready tasks: swarm tasks --ready)
  4. Do the work in your worktree branch
  5. Link your branch: swarm task update <id> --branch <your-branch>
  6. Link PR if opened: swarm task update <id> --pr <number> --pr-url <url>
  7. Link issue if relevant: swarm task update <id> --issue <number> --issue-url <url>
  8. Share discoveries: swarm append findings.md --content "..." if you find something important
  9. VERIFY before completing: swarm task verify <id> npm test (or appropriate build/test command)
  10. Mark complete: swarm task done <id> --output "summary of what was done"
  11. If blocked/failing: swarm task fail <id> <reason> and notify the lead
  12. Check for next task and repeat

Stand-By Behavior

When you have no tasks:

  • Run swarm tasks --mine periodically to check for new assignments
  • Run swarm tasks --ready to see if there are unassigned tasks you could pick up
  • If idle for a while, message the lead: swarm msg <lead-name> Standing by, ready for tasks
  • Do NOT start random work or explore the codebase while waiting

Communication with Lead

  • Report progress when you hit milestones: swarm msg <lead-name> Completed X, moving to Y
  • Escalate blockers immediately: swarm msg <lead-name> Blocked on X because Y
  • Ask for clarification if task description is unclear rather than guessing

Read the full file on GitHub · 49 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. 5d ago First seen · 49 lines · 27 tokens per session scan A 580572ce9cef

Subscribe to this mod's changes

worker-agent is a skill published in the GitHub repository tlangridge/agent-swarm (5 stars, last pushed 6mo ago), licensed MIT. It adds 27 tokens to every session and 575 once invoked, about $0.0001 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens