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 jmlero/claude-toolkit --skill review-prgit clone --depth 1 https://github.com/jmlero/claude-toolkitWrote 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/jmlero/claude-toolkit/review-pr)<a href="https://agentmods.dev/skills/jmlero/claude-toolkit/review-pr"><img src="https://agentmods.dev/badge/skills/jmlero/claude-toolkit/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/jmlero/claude-toolkit/review-pr"><img src="https://agentmods.dev/badge/skills/jmlero/claude-toolkit/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 | $0.00036 | $0.00536 |
| Opus 5.5 | $0.00014 | $0.00214 |
| Sonnet 5.5 | $0.00007 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00054 |
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 2mo 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
Review pull request: $ARGUMENTS
Steps
1. Gather PR Context
# Get PR details
gh pr view $ARGUMENTS
# Get the diff
gh pr diff $ARGUMENTS
# Get PR comments
gh api repos/{owner}/{repo}/pulls/$ARGUMENTS/comments
2. Review Checklist
Code Quality
- Follows existing patterns in the codebase
- No code duplication
- Functions do one thing
- Meaningful variable/function names
- No magic numbers or strings
- No commented-out code
Security (Critical)
- No secrets or credentials in code
- Auth required on mutating endpoints
- Input validated at API boundary
- No SQL injection risk
- Error messages don't leak internals
- No wildcard CORS with credentials
Testing
- Tests exist for new/changed code
- Tests cover happy path AND error cases
- Mocks used for external dependencies
- Tests are independent and isolated
Framework & Infrastructure
Apply checks relevant to the project's stack (skip what doesn't apply):
- Follows framework conventions and idioms
- Proper status codes and error responses
- Types are explicit (no
any, no untyped returns) - Infrastructure config not broken by the change
- Environment variables documented
Git
- Commits follow conventional format (feat:, fix:, etc.)
- PR is focused (not mixing unrelated changes)
- PR description explains the "why"
3. Output Format
## PR Review: #<number>
### Summary
Brief description of what the PR does.
### Verdict: APPROVE / REQUEST_CHANGES / COMMENT
### Findings
#### Must Fix (blocking)
1. [Category] Description - file:line
#### Should Fix (non-blocking)
1. [Category] Description - file:line
#### Nits (optional)
1. Description - file:line
### What's Good
- Positive observations about the PR
Be constructive. Explain WHY something should change, not just what.
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.
- 2mo ago First seen · 87 lines · 36 tokens per session scan A 3a42b0ca35cc
review-pr is a skill published in the GitHub repository jmlero/claude-toolkit (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 536 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 2026-08-31.
review-pr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| review-prjmlero/claude-toolkit | Skill | 2 | 6mo ago | Apache-2.0 | A | 36 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.5k | today | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | today | MIT | A | 48 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 947 | 2d ago | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | today | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |