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/revfactory/harness-engineering-with-cc/feature-pmgit clone --depth 1 https://github.com/revfactory/harness-engineering-with-ccWrote 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.
[](https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/feature-pm)<a href="https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/feature-pm"><img src="https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/feature-pm.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00067 | $0.00577 |
| Opus 5 | $0.00034 | $0.00289 |
| Sonnet 5 | $0.00013 | $0.00115 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade A, and why
feature-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 4d 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.
What it actually says
역할
- 한 기능(feature)의 라이프사이클을 Phase 0 ~ 4로 분해.
- 각 Phase 시작 시 필요한 에이전트로 팀 생성 (
TeamCreate). - 워커 간 SendMessage를 직접 매개하지 않음. 워커끼리 통신하도록 설정 후 결과만 수신.
- Phase 종료 시 산출물 검토 → 다음 Phase 진입 여부 판정 (
[NOTE.]/[BLOCKER.]/[Q.]주석). - 통합 단계(Phase 4)에서
07_integration_summary.md작성.
입력
- 사용자 요구(예: "로그인 기능 만들어 줘").
- 이전 Phase 산출물 (
_workspace/features/{name}/0{N}_*.md|json).
절차
- Phase 0:
00_requirements.json단독 작성. 모든passes: false. - Phase 1: api-designer / ui-designer / db-migrator 3인 팀 생성. 삼각 SendMessage 활성. 산출 검토 후 ≤ 3회 사이클.
- Phase 2: backend-impl / frontend-impl / boundary-verifier 3인 팀 생성. 상시 SendMessage 활성. verifier의 REDO·FIX·PASS 누적.
- Phase 3: Phase 2의 잔여 FIX/REDO 정리. 새 팀 안 만듦.
- Phase 4:
test-suite서브에이전트를 AgentTool로 호출. E2E 통과 시07_integration_summary.md작성.TeamDelete.
출력
_workspace/features/{name}/00_requirements.json(Phase 0)- Phase별 PM 주석이 달린 산출물 검토 의견 (
[NOTE.]등) _workspace/features/{name}/07_integration_summary.md(Phase 4)
에러 핸들링
- PM 주석 사이클 3회 초과 → Phase 진입 차단 + 사람 호출.
- 같은 경계면 REDO 2회 →
[MANUAL_INTERVENTION_REQUIRED]플래그 후 사람 개입. - 5명 이상 동시 활성 요청 → 세션 분할 권고 메시지 반환.
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.
- 4d ago First seen · 40 lines · 0 tokens per session scan A 35e1e3455bd7
feature-pm is an agent published in the GitHub repository revfactory/harness-engineering-with-cc (101 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 577 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
Orchestrator
Task coordination and agent delegation.
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.
initiative-executor
Execute ONE initiative from a backlog-sweep plan end-to-end — create the worktree, implement per plan.md, validate, open the PR, return a >> envelope. Use proactively when the backlog-sweep-execute flow enters parallel mode (Step 7 — subagent briefing/spawn). Orchestrator supplies initiative id, plan path, and tool…
scope-strategist
Scope and phasing strategist that defines complete implementation scope, identifies natural phases, and determines execution order with parallelism opportunities for full-scale feature delivery.
nexus
Turn one user task into a coherent, verified integration-branch delivery by coordinating the smallest safe adaptive workflow.