Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/georgekhananaev/claude-skills-vaultnpx agentmods add commands/georgekhananaev/claude-skills-vault/git-review-prWrote 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/commands/georgekhananaev/claude-skills-vault/git-review-pr)<a href="https://agentmods.dev/commands/georgekhananaev/claude-skills-vault/git-review-pr"><img src="https://agentmods.dev/badge/commands/georgekhananaev/claude-skills-vault/git-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/commands/georgekhananaev/claude-skills-vault/git-review-pr"><img src="https://agentmods.dev/badge/commands/georgekhananaev/claude-skills-vault/git-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 | $0.00018 | $0.01487 |
| Opus 5 | $0.00009 | $0.00744 |
| Sonnet 5 | $0.00004 | $0.00297 |
| Haiku 4.5 | $0.00002 | $0.00149 |
Grade B, and why
review-pr scanned grade B with 1 finding 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 11d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
find .claude/skills -name "*.py" -exec python -m py_compile {} \; Copies of this mod
1 near-identical copy found in the catalogue:
- review-pr — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Command
IMPORTANT: Only run when invoked via /git-review-pr. Do NOT auto-run.
Goal: Review PRs for skills, commands, MCP servers.
0. Prerequisites
Check required tools:
command -v gh >/dev/null || echo "Warning: gh CLI not found - PR features unavailable"
command -v gemini >/dev/null || echo "Warning: gemini CLI not found - skip Gemini review"
If tools missing, continue w/ available features.
1. Identify Changes
git diff --name-only origin/main...HEAD # full PR delta (multi-commit)
git diff --name-only HEAD~1..HEAD # single commit only
gh pr diff --name-only # PR via GitHub CLI
| Path | Type |
|---|---|
.claude/skills/*/ |
Skill |
.claude/commands/*.md |
Command |
mcp-servers/*/ |
MCP Server |
2. Documentation Checks
CHANGELOG.md
git diff origin/main...HEAD -- CHANGELOG.md
Required: Entry under [Unreleased] w/ correct category & format - **scope**: Desc
If missing: FAIL
README.md
git diff origin/main...HEAD -- README.md
- New skills → Core/Document Skills table
- New commands → Commands table
- New MCP → appropriate section
If missing: FAIL
3. Content Quality
Skills (.claude/skills/*/SKILL.md)
Structure:
- YAML frontmatter (name, desc)
-
# Titleheading -
## When to Use - Invocation instructions
- Examples
Issues:
- No dead code/unused imports
- No hardcoded paths
- No duplicate content
- Not overly verbose
- Scripts functional
Commands (.claude/commands/*.md)
Structure:
- YAML frontmatter (name, desc, tools)
- Goal statement
- Step-by-step flow
- Safety protocols
Issues:
- No duplicate instructions
- Safe commands (no destructive defaults)
- Clear prompts
- Proper escaping
MCP Servers (mcp-servers/*/README.md)
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.
- 11d ago First seen · 245 lines · 18 tokens per session scan B a5b11916e661
review-pr is a command published in the GitHub repository georgekhananaev/claude-skills-vault (28 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,487 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
diff-review
AI-powered diff review for Solana-specific issues and code quality.
capture-patterns
Scan the existing codebase and auto-generate PATTERNS.md with detected conventions. Run once, review the output, then commit it so all agents enforce your team's patterns.
audit
Command "audit" from mantacron/manta, covering review depth, step 0 — load suppressions, step 1 — gather context, shared project map — built once, passed to every agent and step 2 — run agents in parallel.
gh-pr-fix
Fix unresolved PR review comments from Copilot or CodeRabbit.
comment-cleanup
Walk through changed code comments and pick a writing variation for each.
dependabot-merge
Interactively review and merge Dependabot PRs for a GitHub repo.