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 skills add product-on-purpose/pm-skills --skill utility-pm-criticgit clone --depth 1 https://github.com/product-on-purpose/pm-skillsWrote 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/skills/product-on-purpose/pm-skills/utility-pm-critic)<a href="https://agentmods.dev/skills/product-on-purpose/pm-skills/utility-pm-critic"><img src="https://agentmods.dev/badge/skills/product-on-purpose/pm-skills/utility-pm-critic/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.
<a href="https://agentmods.dev/skills/product-on-purpose/pm-skills/utility-pm-critic"><img src="https://agentmods.dev/badge/skills/product-on-purpose/pm-skills/utility-pm-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 14 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 61 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 67 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 75 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Agent Snooping · line 48 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 48 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 5.1 | $0.00075 | $0.01455 |
| Opus 5 | $0.00037 | $0.00727 |
| Sonnet 5 | $0.00015 | $0.00291 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
utility-pm-critic 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Critic (Dispatch Skill)
This skill is a cross-client dispatch wrapper for the pm-critic sub-agent. It exists so that users on non-Claude clients can run adversarial review with the same intent as Claude Code users, without depending on native plugin sub-agent infrastructure.
Per master plan D11 (amended) + D30, sub-agents are a Claude Code plugin feature. Non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) cannot natively load agents/pm-critic.md. This skill bridges the gap.
When to Use
- You want adversarial review of a PM artifact (PRD, OKR set, persona, lean canvas, meeting recap, interview synthesis, problem statement, hypothesis, edge case catalog, retrospective, etc.)
- You are running on a non-Claude AI client and the
pm-criticsub-agent is not natively available - You are running on Claude Code and prefer skill-invocation semantics over sub-agent semantics (e.g., for consistency across a multi-step workflow that mixes skills and sub-agent intents)
When NOT to Use
- You want a structural lint / repo-level audit -> use
utility-pm-skill-auditor(audits skills + repo state) instead - You want to author an artifact (this skill only reviews) -> use the appropriate phase skill (deliver-prd, foundation-okr-writer, etc.)
- You want code review -> use a code-review-specific tool (this skill is for PM artifacts)
- You want to enforce style rules like em-dash sweep -> that is
pm-release-conductor's G0 gate, not this skill
Instructions
Runtime detection step. Determine which AI client is invoking this skill.
If you are running in Claude Code with the pm-skills plugin installed
Invoke @agent-pm-skills:pm-critic on the target artifact. Pass the artifact path as argument (or the most recent artifact in session context if no argument is provided). Return the sub-agent's findings to the user. No further action needed from this skill - the sub-agent handles the review natively in its own context window.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 85 lines · 75 tokens per session scan A ed3949dabae3
utility-pm-critic is a skill published in the GitHub repository product-on-purpose/pm-skills (663 stars, last pushed yesterday), licensed Apache-2.0. It adds 75 tokens to every session and 1,455 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
status-update-writer
Use when the user asks to write a status update, weekly or monthly update, stakeholder update, project update, standup, status report, or QBR. Do NOT use for writing a PRD or a retro doc — those need different structures.
stakeholder-update
Translate the same underlying project status into audience-appropriate versions (exec-brief, engineering-detail, customer-facing) without changing the underlying facts. Use when a PM needs to write a status update, especially when the same update needs to go to multiple different audiences. Pairs with…
scope-cut
Decision framework for what to cut when a spec, sprint, or launch is too big for the time or team available. Use whenever a PM says a scope needs to shrink, a deadline is fixed and the work isn't, or someone asks "what can we cut" or "what's the MVP version of this." Also trigger when reviewing a spec that feels…
escalation-judgment
Decision framework for whether a blocker, risk, or conflict is actually worth escalating to leadership versus resolving at the working level. Use when a PM is unsure whether to "loop in" a director/VP, when a team is stuck and someone suggests escalating, or when reviewing whether a past escalation was warranted. Also…
okrs
Use when asked to "set OKRs", "objectives and key results", "quarterly OKR planning", "align objectives", "measure OKR progress", or "focus priorities with OKRs". Helps teams focus on what matters most and create a cadence of progress. The OKR framework (originated by Andy Grove at Intel, popularized by John Doerr at…
shape-up
Use when asked to "shape up", "run a shaping session", "set an appetite", "scope a project without estimates", "betting table", or "ship in fixed cycles". Helps teams escape estimate-driven development and Scrum fatigue. The Shape Up method (created by Ryan Singer at Basecamp/37signals) uses fixed time boxes, variable…