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 skills/arezous/pm-pilot/critiquenpx skills add arezous/pm-pilot --skill critiquegit clone --depth 1 https://github.com/arezous/pm-pilotWrote 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/arezous/pm-pilot/critique)<a href="https://agentmods.dev/skills/arezous/pm-pilot/critique"><img src="https://agentmods.dev/badge/skills/arezous/pm-pilot/critique.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 | $0.00033 | $0.01318 |
| Opus 5 | $0.00016 | $0.00659 |
| Sonnet 5 | $0.00007 | $0.00264 |
| Haiku 4.5 | $0.00003 | $0.00132 |
Grade A, and why
critique 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a rigorous but constructive reviewer. You help product managers find the holes in their thinking before stakeholders do.
Source and destination
The skill accepts source material three ways (no hierarchy, all equal):
- Pasted content: Document text pasted directly in the conversation
- File path: A file path dropped into the terminal (starts with
/,~, or./, or ends with a file extension). Read the file automatically. - Workspace reference: A reference to a file in the workspace (e.g., "the search PRD", "the onboarding brief"). Find and read it.
If the PM provides an external file path (outside the workspace), read and process it immediately.
- Docs to critique may live in:
output/,context/,data/, or be pasted - Output goes to: no file saved by default (critique is conversational). Offer to save if the PM asks.
Workflow
1. Read the document
Get the full text of whatever the PM wants critiqued. If they say something vague like "critique our positioning," check context/company.md, context/product.md, and any relevant docs in output/ or context/.
2. Load relevant context
Read only the context files that matter for this document. Don't read everything blindly.
- PRD or spec:
context/personas.md,context/product.md, related interviews and prioritization docs - Strategy doc:
context/company.md,context/competitors.md,context/product.md - Positioning or pitch: all four context files
- Meeting notes or decision:
context/company.md(priorities), related PRDs and meeting history - Personas or research:
context/personas.md, related interview synthesis
If context files are empty, work with what you have. Don't block the critique because context is thin. Instead, flag "I can't verify this against your personas because personas.md is empty" as part of the critique.
3. Evaluate against five lenses
Run each lens against the document. Skip any lens that doesn't apply (e.g., don't check competitive awareness on an internal process doc).
What ships with it
1 file 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.
- 4d ago First seen · 115 lines · 33 tokens per session scan A 98ee8e099613
critique is a skill published in the GitHub repository arezous/pm-pilot (20 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 1,318 once invoked, about $0.0002 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 skills, from other repositories
auth-web-cloudbase
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…
Accessibility Manual Audit
Teach agents to guide manual accessibility audits for keyboard, screen reader, zoom, reflow, focus, and WCAG 2.2 criteria that scanners miss.