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 Leo-maomao/pm-copilot --skill review-checklistgit clone --depth 1 https://github.com/Leo-maomao/pm-copilotWrote 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/leo-maomao/pm-copilot/review-checklist)<a href="https://agentmods.dev/skills/leo-maomao/pm-copilot/review-checklist"><img src="https://agentmods.dev/badge/skills/leo-maomao/pm-copilot/review-checklist/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/leo-maomao/pm-copilot/review-checklist"><img src="https://agentmods.dev/badge/skills/leo-maomao/pm-copilot/review-checklist.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00027 | $0.00406 |
| Opus 5 | $0.00014 | $0.00203 |
| Sonnet 5 | $0.00005 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
review-checklist 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 6d 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
PRD Review
Goal
Decide whether one PRD delivery is ready for product stakeholder review. The
review covers prd.md, prd.html, assets/, and run-log.yaml; it does not
produce implementation handoffs, launch decisions, or standalone UI artifacts.
Workflow
- Check the PRD against
artifacts/prd-contract.mdand the confirmed scope. - Verify every requirement ID has one matching detail and that a revision has not changed unselected requirements.
- Verify each user-facing state has a real figure, an isolated reconstructed figure, or a controlled placeholder beside its requirement detail.
- Check that figure paths, hashes, captions, and HTML rendering match the staged PRD bytes.
- For implemented-feature PRDs, verify immutable implementation evidence, requirement coverage, and figure provenance. Do not treat generated output or local scaffolding as product evidence.
- For composed PRDs, verify every selected source requirement resolves only from its immutable source snapshot. For revisions, verify baseline and selected-scope evidence.
- Verify the controller trace records confirmation, lineage, review findings, validation results, and a truthful terminal status.
- Identify Critical, High, Medium, or Low findings. Separate blocking fixes from optional improvements and attach evidence to each finding.
Output
- Summary recommendation
- Findings by severity
- Requirement and figure coverage checklist
- Open decisions or blockers
- Validation results
- Next actions
Quality Bar
- Findings are actionable and evidence-backed.
- A Critical or High finding blocks PRD promotion until it is fixed, accepted explicitly as risk, or returned for clarification.
- A review with no Critical or High findings still records the checks performed and residual risk.
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.
- 6d ago Changed · -5 lines 0354ec275725
- 11d ago First seen · 55 lines · 27 tokens per session scan A 3b48c2f96a9b
review-checklist is a skill published in the GitHub repository Leo-maomao/pm-copilot (4 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 406 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 skills, from other repositories
patent-docket
A workflow coordinator for patent case files, from an inventor's technical disclosure to patent application documents. A patent docket is the tracked record of a patent matter, including its stage, questions, drafts, and handoffs.
merge-review
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.
workspace
Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.
decision-map
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…
unharness
Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.
wayfinder
A planning method for large or unclear work that maps the decisions needed between the current situation and a defined destination. It records the map and decision tickets in an issue tracker.