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.
npx agentmods add agents/aidd-projects/harness/pmgit clone --depth 1 https://github.com/AIDD-Projects/harnessWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.04368 |
| Opus 5 | $0.00000 | $0.02184 |
| Sonnet 5 | $0.00000 | $0.00874 |
| Haiku 4.5 | $0.00000 | $0.00437 |
Grade A, and why
pm 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pm
Role
Feature planning and dependency management. Use before writing new feature code.
Invoked By
- User (direct) — "[기능]을 추가해줘", "계획 세워줘"
- setup → pm (🟢/🟣 pipeline Step 2)
- pivot → pm — "변경된 방향에 맞춰 재계획해줘"
- architect → pm — "승인된 설계로 기능을 계획해줘"
Referenced Skills
- breakdown
- check-impact
Referenced Files
Required — 반드시 읽기
- docs/project-brief.md — 프로젝트 방향, Goals, Non-Goals, Decision Log (Step 1에서 사용)
- docs/features.md — 기존 기능 등록부 (중복 방지)
- docs/dependency-map.md — 모듈 구조 (impact 분석)
- docs/agent-memory/pm.md — 과거 계획 인사이트
Optional — 해당 Step에서만 읽기
- docs/project-state.md — Sprint 컨텍스트 필요 시에만 읽기
- docs/failure-patterns.md — 과거 실수 확인 시에만 읽기
Input
One of:
- New Feature: "I want to add [feature description]"
- Architecture Query: "What depends on [module]?" / "Show me the current module map"
- Refactor Plan: "I need to refactor [module/area]"
- Crew-Driven Feature: "crew 산출물을 기반으로 [기능]을 계획해줘" — when external planning artifacts exist in
docs/crew/
Procedure
Step 0: State File Readiness
Before proceeding, verify that required state files have content (not just TODO placeholders):
docs/project-brief.md— Must have Vision and Goals filleddocs/features.md— Must have at least one feature rowdocs/dependency-map.md— Must have at least one module row (for existing projects)
If ALL files are empty/placeholder-only → Stop and run the setup skill first. Report: "State files are empty. Running setup to onboard this project."
If docs/project-brief.md alone is empty → Stop. Without Vision/Goals, pm cannot check Non-Goals or provide direction guard. Run setup first.
Step 0 runs BEFORE Step 1. If Step 0 stops (empty brief), Step 1 never executes. When Step 0 passes, Step 1 reads the now-confirmed non-empty project-brief.md for detailed content.
Step 0.5: Load Agent Memory
Read docs/agent-memory/pm.md for past learnings:
- Estimation accuracy from previous sprints (did Wave estimates match reality?)
- Architecture patterns that worked or failed in this project
- Repeated planning mistakes to avoid
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.
- yesterday First seen · 401 lines · 0 tokens per session scan A bc1b3d4c685f
pm is an agent published in the GitHub repository AIDD-Projects/harness (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,368 tokens. 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.
Other agents, from other repositories
ctx
Expert on ctx CLI - generates AI-ready context and provides code intelligence (indexing, search, call graphs, impact analysis).
requirements-reviewer
Reviews a draft requirements.md against the conversation history and glean scratch files. Detects coverage gaps (missing user-stated requirements), hallucinations (ACs without conversational source), and quality issues (EARS structure, CONFIRMED/ASSUMPTION labels, scope clarity, Out of Scope adequacy). Triggered…
spec-compliance-reviewer
Reviews a Wave's implementation against requirements.md and tasks.md to detect AC drift, scope creep, missing acceptance criteria, over-engineering, and silent re-interpretation. Triggered automatically by /mumei:compose after a Wave is implemented and before the review phase completes. Does NOT review code quality…
bash-script-reviewer
Reviews the quality of the mumei plugin's hooks/.sh and hooks/lib/.sh. Checks shellcheck convention compliance, the KISS principle, error handling, consistent mumei prefixing, ${CLAUDEPLUGINROOT} usage, jq null safety, BSD awk compatibility, and the stdin/stdout/stderr separation principle. Use on newly added or…
analyzer
MANDATORY AGENT FOR ROOT CAUSE ANALYSIS, SYSTEM DESIGN, CODE REVIEW, AND DEAD-END DIAGNOSTICS. SPECIFIC TRIGGERS: (1) RCA: developer reported an error or tester failed an Assert — trace call chain, find exact broken file:line locally via Ripgrep / AST; (2) pre-code analysis: call BEFORE developer when task needs…
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.