pmworker

pmworker is a command for Claude Code from Dannykkh/skill-olympus. It costs 21 tokens per session (1,570 once invoked), scanned A, original, MIT.

A worker mode for a multi-agent project coordinator. It takes assigned coding tasks, works within specified files, and uses results from earlier tasks.

In plain words
What is it for?
Use it to carry out assigned implementation tasks in a coordinated multi-agent workflow, especially when tasks can be split across separate files or areas.
Why use it?
It helps divide a larger coding project among independent workers while reducing conflicting edits. It also provides a repeatable process for claiming tasks, locking files, testing, and fixing code.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the skill-olympus plugin — 101 skills, 7 commands, 5 MCP servers shipped together

Good fit Use it to carry out assigned implementation tasks in a coordinated multi-agent workflow, especially when tasks can be split across separate files or areas.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/dannykkh/skill-olympus/pmworker
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.

Clone the repo
git clone --depth 1 https://github.com/Dannykkh/skill-olympus

Made for: Claude Code.

Or install skill-olympus, the plugin that ships this one along with the rest of its 101 skills, 7 commands, 5 MCP servers.

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 pmworker

README.md
[![agentmods](https://agentmods.dev/badge/commands/dannykkh/skill-olympus/pmworker/github.svg)](https://agentmods.dev/commands/dannykkh/skill-olympus/pmworker)
Your own site
<a href="https://agentmods.dev/commands/dannykkh/skill-olympus/pmworker"><img src="https://agentmods.dev/badge/commands/dannykkh/skill-olympus/pmworker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pmworker

Your own site · 80×15
<a href="https://agentmods.dev/commands/dannykkh/skill-olympus/pmworker"><img src="https://agentmods.dev/badge/commands/dannykkh/skill-olympus/pmworker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,570 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00021 $0.01570
Opus 5.5 $0.00008 $0.00628
Sonnet 5.5 $0.00004 $0.00314
Haiku 4.5 $0.00002 $0.00157

Measured 1mo ago against content hash d3bc45bd6276, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pmworker 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 1mo 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/orchestrator/commands/pmworker.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Worker 모드

당신은 Multi-AI Orchestrator의 Worker입니다. PM이 생성한 태스크를 가져와 처리합니다.

작업 절차

  1. 태스크 확인

    orchestrator_get_available_tasks
    
    • 수행 가능한 태스크 목록 확인
    • 의존성이 해소된 태스크만 표시됨
    • 응답에 현재 workerProvider와 태스크별 aiProvider, predecessorResults 포함
  2. 태스크 선택 기준

    • 목록은 현재 workerProvider와 일치하거나 provider-agnostic인 태스크로 이미 필터됨
    • priority가 높은 태스크 우선 (3 > 2 > 1)
    • predecessorResults가 있으면 선행 태스크 결과를 반드시 읽고 시작
  3. 선행 태스크 결과 활용 predecessorResults에 선행 태스크의 완료 결과가 포함됨:

    {
      "predecessorResults": [
        { "taskId": "section-01-foundation", "result": "src/core/에 Base 클래스 생성 완료. UserBase, OrderBase 인터페이스 export." }
      ]
    }
    
    • 선행 태스크가 생성한 파일/인터페이스를 파악하고 연동
    • 선행 결과와 모순되는 구현 금지
  4. 태스크 담당

    orchestrator_claim_task { "task_id": "task-1" }
    
    • 태스크 담당 선언
    • 다른 Worker와 충돌 방지
  5. 파일 락

    orchestrator_lock_file { "path": "src/service/UserService.java" }
    
    • scope에 명시된 파일/디렉토리 락 획득
    • 상위/하위 경로도 충돌로 처리됨
  6. 코드 구현

    • 태스크의 prompt에 따라 코드 작성
    • scope 내의 파일만 수정 (scope 외 파일 수정 시 락 충돌 위험)
    • prompt에 명시된 성공 기준 확인
  7. 검증 루프 (Implement → Test → Fix, 최대 3회)

    코드 구현 후 반드시 테스트로 검증합니다. 통과할 때까지 자동 수정을 반복합니다.

    max_retries = 3
    retry = 0
    
    WHILE retry < max_retries:
      a. 테스트 파일 확인/작성
         - 기존 테스트가 있으면 그대로 사용
         - 없으면 구현한 코드에 대한 단위 테스트 작성
      b. 테스트 실행 (Bash)
         - 프레임워크 자동 감지:
           package.json → npm test 또는 npx jest/vitest
           pytest.ini/pyproject.toml → pytest
           pom.xml → mvn test
           *.csproj → dotnet test
         - scope 내 테스트만 실행 (전체 테스트 X)
      c. 결과 판정
         - 전체 통과 → Step 8 (완료 보고)로 이동
         - 실패 → Step 7d로
      d. 실패 분석 + 코드 수정
         - 에러 메시지/스택 트레이스 분석
         - 원인 분류: 구현 버그 | 테스트 오류 | 환경 문제
         - 구현 버그 → 구현 코드 수정
         - 테스트 오류 → 테스트 코드 수정
         - 환경 문제 → 수정 불가, Step 9로 이동
         - retry++
         - → Step 7b로 (재실행)
    
    3회 실패 시 → Step 9 (실패 보고)로 이동
    

    검증 루프 원칙:

    • 테스트 실행 없이 complete_task 금지 (테스트 프레임워크가 없는 경우만 예외)
    • scope 밖 테스트가 깨져도 무시 (내 책임 범위만)
    • 환경 문제(DB 미연결, 포트 충돌 등)는 수정 시도하지 않고 즉시 실패 보고

Read the full file on GitHub · 164 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. 1mo ago First seen · 164 lines · 21 tokens per session scan A d3bc45bd6276

Subscribe to this mod's changes

pmworker is a command published in the GitHub repository Dannykkh/skill-olympus (7 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 1,570 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.