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 fpindej/netrock --skill review-prgit clone --depth 1 https://github.com/fpindej/netrockWrote 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/fpindej/netrock/review-pr)<a href="https://agentmods.dev/skills/fpindej/netrock/review-pr"><img src="https://agentmods.dev/badge/skills/fpindej/netrock/review-pr/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/fpindej/netrock/review-pr"><img src="https://agentmods.dev/badge/skills/fpindej/netrock/review-pr.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.00665 |
| Opus 5.5 | $0.00012 | $0.00266 |
| Sonnet 5.5 | $0.00006 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
review-pr 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 1mo 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviews a pull request for production-readiness before merge. Runs in the main session so the reviewer agents can be dispatched in parallel (per CLAUDE.md delegation patterns).
Argument: PR number or URL. If omitted, reviews the current branch's open PR.
Current branch: !git branch --show-current
Open PR for this branch: !gh pr view --json number,title,url --jq '"#\(.number) \(.title) - \(.url)"' 2>/dev/null || echo "(no open PR)"
Steps
- Resolve the PR:
gh pr view {number} --json number,title,headRefName,body - Get the diff and changed files:
gh pr diff {number},gh pr view {number} --json files - Dispatch reviewer agents in parallel (one message, multiple Agent calls), scoped by what changed:
backend-reviewer- ifsrc/backend/changedfrontend-reviewer- ifsrc/frontend/changedsecurity-reviewer- alwaysux-designer- if UI components or pages changed Give each the PR number and the changed-file list for its scope. They preload the convention skills - do not restate conventions in the prompt.
- While reviewers run, perform the cross-cutting checks below yourself.
Orchestrator Checks (cross-cutting)
- Intent: does the code do what the PR description says?
- Cross-stack consistency: backend DTO changes -> types regenerated (
v1.d.ts), frontend consumers updated - i18n: new keys present in ALL locale directories
- Dockerfile: new
.csprojreferenced by WebApi has a COPY line in the restore layer - Completeness: new flags/props consumed; no dead code introduced
- No em dashes (U+2014), no emojis anywhere in the diff
- Tests: behavior changes come with test changes
Verdict Synthesis
Merge the reviewer reports and your own checks into one report:
- PASS - what looks good (brief, no padding)
- FAIL - issues that MUST be fixed before merge (with file path and line, attributed to the reviewer that found them)
- WARN - suggestions, not blockers
Final verdict: REQUEST CHANGES if any reviewer reported FAIL/CRITICAL/HIGH items or your checks found blockers; APPROVE WITH SUGGESTIONS if only WARN items; otherwise APPROVE.
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.
- 1mo ago First seen · 51 lines · 29 tokens per session scan A 5eb908ff0117
review-pr is a skill published in the GitHub repository fpindej/netrock (234 stars, last pushed 5d ago), licensed MIT. It adds 29 tokens to every session and 665 once invoked, about $0.0001 per session on Opus 5.5. 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
fleet-review
Code review checklist and PR review workflow for Fleet QA agents.
api-design
Guidelines for RESTful API design, resource hierarchies, endpoint naming conventions, and standardizing JSON responses.
python
Enforces FastAPI, Dependency Injection, and general Python coding standards using uv inside the server directory.
react
Guidelines for the React frontend, TanStack ecosystem, and React 19 standards using pnpm inside web/.
project-setup
Step-by-step instructions and CLI commands to initialize a fresh fullstack clean architecture project (React 19 + Vite frontend in web/ and FastAPI + SQLAlchemy async backend in server/) using the latest package versions via pnpm and uv without cloning.
clean-code
Clean Code principles applied to this TypeScript / Next.js / React project, with a strong emphasis on eliminating duplication (DRY). Use before writing new code, during refactors, after Sonar flags duplicatedlines, or when reviewing a PR that adds similar-looking code to existing modules.