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 wei63w/pm-manager --skill pm-reviewgit clone --depth 1 https://github.com/wei63w/pm-managerWrote 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/wei63w/pm-manager/pm-review)<a href="https://agentmods.dev/skills/wei63w/pm-manager/pm-review"><img src="https://agentmods.dev/badge/skills/wei63w/pm-manager/pm-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00022 | $0.00710 |
| Opus 5 | $0.00011 | $0.00355 |
| Sonnet 5 | $0.00004 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
pm-review 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 8d 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
User Input
$ARGUMENTS
Accepted extra words: confirm REV-xxx | false_positive REV-xxx | later REV-xxx | annotate REV-xxx | --cross | --path=... | --verbose.
Outline
/pm-review 是可见的质量闭环。用户以中文交互时用中文回复。未确认不改业务代码。
A. New review (no disposition words)
- Require
.pm/。缺则建议/pm-init。 - 先跑
pm gate --path <root>与pm review --path <root>。读.pm/state/review-draft.md、guard.md。无 diff 则说 没有可评的变更 并停止，不许编造通过。 - 地图优先。加载
.pm/engineering/rules.md启用规则。对照旧/新行为。碰到risk_files必须打断并单独成行。 - 只润色或补合格行（
summary+reasoning+snippet+severity+file/line）。缺推理或片段禁止落盘。 - 建议再跑
pm review --cross，对照.pm/state/cross-review.md用另一套检查单（安全 vs 完成度/文档），禁止复制初评空话、禁止同一 snippet 再标 new。 - P0 打断。P1/P2 进报告。单测缺口只警告。
- 若当前仓库为 Vue：额外核对
v-html（XSS）与v-for缺:key；结论仍须推理链 + 片段。 - 请用户回复
confirm REV-xxx/false_positive REV-xxx/later REV-xxx。回填用pm review annotate REV-xxx（只写.pm/reviews/annotations/）。
B. Disposition
confirm→pm review confirm REV-xxx（或最新 unset）。仅合格行可进rules.md。false_positive→ 不进规范。later→ 待优化，留在表里。
C. After write
刷新总览待处置数。追加审计（含推理）。Closing：_closing.md 完整档。
Done When
- 无 diff 时说了没有可评的变更
- 每条落盘发现有推理 + 片段
- 仅 confirmed 进入 rules.md
- 回填未写入业务树
- 业务代码未改，除非用户另确认修复
Shared Workflow
Map-first. Redact snippets. Confirm-before-write. Design baseline: docs/prd.md + 宪章。
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.
- 8d ago First seen · 55 lines · 22 tokens per session scan A 629134b7be00
pm-review is a skill published in the GitHub repository wei63w/pm-manager (100 stars, last pushed 8d ago), licensed MIT. It adds 22 tokens to every session and 710 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 2026-08-30.
Other skills, from other repositories
eng-workflow
Full GitLab development loop — from issue to confirmed-resolved. Covers write-issue, analyze-issue, fix-issue, review-code, create-mr, summarize-issue, triage-issue, and post-merge verification.
github-address-comments
Implements the fixes a PR review asked for — maps each thread to the code it touches, edits that code, and drafts a reply per thread for approval before anything is posted. Starts from feedback that is already understood; producing the read-only digest is pr-comments.
gh-address-comments
Implements the fixes a PR review asked for — maps each thread to the code it touches, edits that code, and drafts a reply per thread for approval before anything is posted. Starts from feedback that is already understood; producing the read-only digest is pr-comments.
code-review
Use when completing a task, implementing a feature, or before committing to verify work meets requirements and coding standards. Triggers: task completion, pre-commit check, pre-merge validation, plan alignment verification, post-refactor quality gate.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…