Borrowing it
Nothing to install: this file belongs to banshee-data/velocity.report. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/banshee-data/velocity.report/main/.claude/skills/review-pr/SKILL.mdgit clone --depth 1 https://github.com/banshee-data/velocity.reportWrote 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/banshee-data/velocity.report/review-pr)<a href="https://agentmods.dev/skills/banshee-data/velocity.report/review-pr"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/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/banshee-data/velocity.report/review-pr"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/review-pr.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 | $0.00028 | $0.00958 |
| Opus 5.5 | $0.00011 | $0.00383 |
| Sonnet 5.5 | $0.00006 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: review-pr
Review a pull request, branch diff, or set of changed files for security, correctness, test coverage, and maintainability.
Usage
/review-pr 123
/review-pr feature/lidar-l7-scene
/review-pr internal/lidar/l5tracks/tracker.go
Procedure
1. Get the diff
If a PR number is given:
gh pr view <number> --json title,body,files
gh pr diff <number>
If a branch name is given:
git diff main...<branch> --stat
git diff main...<branch>
If file paths are given, read the files directly.
2. Understand context
- Read the PR description or the commit messages for intent.
- Read the test files alongside the changed code.
- Read any plan or design doc linked in the PR.
3. Security pass (malory's lens: read-only, gate classification)
Check in priority order:
- Input validation: are all external inputs validated? (radar JSON, LiDAR UDP, API request bodies, config files)
- Privacy leaks: could PII reach a log, response body, or export? Flag CRITICAL if yes.
- Injection vectors: SQL, command, path traversal, Typst/template-data injection
- Auth & access: are new API routes authenticated? Can unauthenticated users reach sensor data?
- Error messages: do error messages leak internal state or sensitive data?
- Dependencies: are new dependencies introduced? Any known CVEs?
Apply gate classification:
- CRITICAL: must fix before merge (RCE, auth bypass, PII exposure, data exfiltration)
- INFO: note for backlog (minor misconfig, stale dep, non-sensitive info disclosure)
4. Correctness pass (appius's lens)
- Are the invariants named and preserved?
- Are failure modes visible and handled?
- Are there untested joins or missing edge cases?
- Are retries bounded?
- Are migrations safe? Do they have rollback paths?
- Are logs meaningful for operators?
5. Test coverage
- Are happy path, edge path, and failure path tests present?
- Do tests exercise the actual change or just existing behaviour?
- Is test setup clear and isolated?
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 · 151 lines · 28 tokens per session scan A 39ddebc0ddc6
review-pr is a skill published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 28 tokens to every session and 958 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 2026-09-25.
review-pr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| review-prbanshee-data/velocity.report | Skill | 11 | today | Apache-2.0 | A | 28 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 17 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 945 | yesterday | MIT | A | 84 | Claude Code |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |
| asplos-writing-stylebrycewang-stanford/Awesome-Journal-Skills | Skill | 1.4k | 1mo ago | MIT | A | 65 | Claude Code |
| ring:mapping-feature-relationshipsLerianStudio/ring | Skill | 218 | 6d ago | Apache-2.0 | A | 104 | Cursor |
| connector-sdk-submitfivetran/connector_sdk_tools | Skill | 89 | yesterday | MIT | A | 45 | Claude Code |