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/shandar/pwp-plugin/pwp-code-reviewnpx skills add shandar/pwp-plugin --skill pwp-code-reviewgit clone --depth 1 https://github.com/shandar/pwp-pluginWhat 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 | $0.00100 | $0.00899 |
| Opus 5 | $0.00050 | $0.00449 |
| Sonnet 5 | $0.00020 | $0.00180 |
| Haiku 4.5 | $0.00010 | $0.00090 |
Grade A, and why
pwp-code-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 2d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Skill
This skill defines how to perform a structured code review. Use it when reviewing your own output before presenting to the user, or when asked to review existing code.
Review Mindset
- You are a reviewer, not an author. Your job is to find problems, not defend choices.
- Every comment must be actionable. "This could be better" is not a review comment. "Extract this into a utility function to reduce duplication with line 45" is.
- Prioritize correctness over style. A bug matters more than a naming preference.
Review Checklist
For every code change, check the following in order:
1. Correctness
- Does the code do what it claims to do?
- Are all edge cases handled? (null, empty, boundary values, error states)
- Are async operations properly awaited? Error-handled?
- Are types correct and strict? (no
anyescapes, no type assertions without justification)
2. Security
- Is user input sanitized before rendering or database writes?
- Are secrets kept out of client code?
- Are permissions checked server-side, not just hidden in UI?
- Are dependencies from trusted sources?
3. Readability
- Can you understand the code without the author explaining it?
- Are variable and function names descriptive and consistent?
- Is the code structured logically? (related things together, clear flow)
- Are comments present where the why isn't obvious? Absent where it is?
4. Performance
- Are there unnecessary re-renders, re-fetches, or re-computations?
- Are large operations debounced or throttled?
- Are heavy modules lazy-loaded?
- Is data fetching efficient? (no N+1 queries, no over-fetching)
5. Maintainability
- Is the code DRY without being over-abstracted?
- Are there magic numbers or hardcoded values that should be constants?
- Is the change scoped correctly? (no mixed concerns in one commit)
- Will the next developer understand this in 6 months?
6. Testing
- Is the change tested? (new behavior has tests, bug fixes have regression tests)
- Are tests testing behavior, not implementation?
- Are test names descriptive?
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.
- 2d ago First seen · 91 lines · 100 tokens per session scan A 46d713659fff
pwp-code-review is a skill published in the GitHub repository shandar/pwp-plugin (1 stars, last pushed 6mo ago), licensed MIT. It adds 100 tokens to every session and 899 once invoked, about $0.0005 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
golden-rss
Use when testing the rss golden build.
design-system-builder
Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs, generate design systems, or build MVP UIs matching reference aesthetics.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.