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.
git clone --depth 1 https://github.com/matteocervelli/llmsWrote 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/matteocervelli/llms/pr-review-merge)<a href="https://agentmods.dev/commands/matteocervelli/llms/pr-review-merge"><img src="https://agentmods.dev/badge/commands/matteocervelli/llms/pr-review-merge/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/matteocervelli/llms/pr-review-merge"><img src="https://agentmods.dev/badge/commands/matteocervelli/llms/pr-review-merge.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 | $0.00012 | $0.02721 |
| Opus 5.5 | $0.00005 | $0.01088 |
| Sonnet 5.5 | $0.00002 | $0.00544 |
| Haiku 4.5 | $0.00001 | $0.00272 |
Grade A, and why
pr-review-merge 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.
How it starts
The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Before Merge: $ARGUMENTS
Comprehensive pre-merge review to validate code quality, security, best practices, and readiness for production.
Phase 1: PR Metadata Analysis
# Get PR details
!gh pr view $ARGUMENTS --json title,body,author,reviewers,state,isDraft,mergeable,statusCheckRollup,headRefName,baseRefName
# Check review status
!gh pr reviews $ARGUMENTS
Initial Validation Checklist
- PR is not in draft status
- PR has proper title and description
- No merge conflicts
- CI/CD checks are passing
- Required approvals are present
- Target branch is correct (usually main/master)
BLOCKER: If any critical items fail, stop and report issues before continuing.
Phase 2: Changed Files Analysis
# Get PR diff
!gh pr diff $ARGUMENTS
# List changed files with stats
!gh pr view $ARGUMENTS --json files
File-Level Checks
Size Validation (per project 500-line limit):
# Check for oversized files
!gh pr diff $ARGUMENTS --name-only | while read file; do
lines=$(git show HEAD:"$file" 2>/dev/null | wc -l)
if [ "$lines" -gt 500 ]; then
echo "⚠️ WARNING: $file has $lines lines (limit: 500)"
fi
done
Modular Design:
- Each file should have single responsibility
- Check for proper separation of concerns
- Verify clean interfaces between modules
Phase 3: Code Quality Review
# Run comprehensive quality checks
!echo "🔍 Running code quality analysis..."
Language-Specific Quality Checks
Python Projects:
# Formatting
!if command -v black &> /dev/null; then echo "→ Formatting (black):" && black --check . 2>&1 | head -20; fi
# Linting
!if command -v flake8 &> /dev/null; then echo "→ Linting (flake8):" && flake8 src/ tests/ 2>&1 | head -20; fi
# Type checking
!if command -v mypy &> /dev/null; then echo "→ Type checking (mypy):" && mypy src/ 2>&1 | head -20; fi
# Test coverage
!if command -v pytest &> /dev/null; then echo "→ Test coverage:" && pytest --cov=src --cov-report=term-missing 2>&1 | tail -10; fi
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 · 367 lines · 12 tokens per session scan A 8e12e07e3a6e
pr-review-merge is a command published in the GitHub repository matteocervelli/llms (25 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 2,721 once invoked, about $0.0000 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 2026-09-01.
pr-review-merge compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pr-review-mergematteocervelli/llms | Command | 25 | 5mo ago | MIT | A | 12 | Claude Code |
| elegant-code-reviewathola/claude-night-market | Command | 348 | yesterday | MIT | A | 27 | Claude Code |
| prp-commitFmarzochi/EGC | Command | 68 | yesterday | Apache-2.0 | A | 15 | Claude Code |
| gsd:pr-branchkryptobaseddev/cleo | Command | 160 | yesterday | MIT | A | 24 | Claude Code |
| validate-pr-descriptionrjmurillo/ai-agents | Command | 49 | yesterday | MIT | A | 22 | Claude Code |
| gitazrtydxb/procoder | Command | 211 | 11d ago | Apache-2.0 | A | 20 | Claude Code |
| karpathy-checkricneves-ai/flowgrammers-skills | Command | 117 | 1mo ago | MIT | A | 0 | Claude Code |