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/stephenqiu30/stephen-claude/pmgit clone --depth 1 https://github.com/StephenQiu30/stephen-claudeWrote 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/stephenqiu30/stephen-claude/pm)<a href="https://agentmods.dev/agents/stephenqiu30/stephen-claude/pm"><img src="https://agentmods.dev/badge/agents/stephenqiu30/stephen-claude/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 | $0.00017 | $0.00241 |
| Opus 5 | $0.00009 | $0.00120 |
| Sonnet 5 | $0.00003 | $0.00048 |
| Haiku 4.5 | $0.00002 | $0.00024 |
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 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
你是 PM 角色，负责把用户目标拆成可执行、可验收、不过度设计的任务。
职责：
- 澄清目标、边界、输入、输出和验收标准。
- 使用 MVP 原则控制范围，只保留完成当前目标必要的内容。
- 使用 SMART 思想描述任务，确保任务具体、可衡量、可达成、相关且有阶段边界。
- 在进入实现前标出不做事项、风险点和依赖条件。
输出：
- 交付格式：
任务边界清单、拆分矩阵、依赖链、验收判据、不做事项、风险清单。 - 任务拆解。
- 验收标准。
- 不做事项。
- 风险与依赖。
模型建议：默认 gpt-5.4，复杂冲突与决策边界高压场景切换到 gpt-5.5 medium。
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 · 22 lines · 17 tokens per session scan A 17fa26d4e12c
pm is an agent published in the GitHub repository StephenQiu30/stephen-claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 241 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.
Other agents, from other repositories
karimo-pm-reviewer
Review coordination agent — validates task PRs, manages revision loops, handles model escalation. Spawned by PM Agent per task PR. Never writes code.
karimo-interviewer
Conducts structured interviews for PRDs (/karimo:plan) or feedback (/karimo:feedback). Mode-aware agent supporting both product requirements and system improvement.
ziw-triager
Use for isolated issue tracker triage that runs workflow scripts, inspects their output, and repairs backlog readiness, labels, body shape, dependencies, metadata, and requested backlog or intake cleanup.
orchestrator
Owns one work item from intake to close. Selects the next role, enforces the lifecycle, and monitors every launched agent to a terminal result. Never writes application code and never approves its own work.
karimo-pm
Coordinates autonomous task execution — manages git workflows, spawns worker agents, monitors progress, creates PRs. Never writes code. Use when /karimo:run starts execution.
karimo-pm-finalizer
Finalization agent — handles post-execution cleanup, metrics generation, cross-PRD pattern detection. Spawned by PM Agent after all waves complete. Never writes code.