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 benrben/MPGA --skill review-prgit clone --depth 1 https://github.com/benrben/MPGAWrote 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/benrben/mpga/review-pr)<a href="https://agentmods.dev/skills/benrben/mpga/review-pr"><img src="https://agentmods.dev/badge/skills/benrben/mpga/review-pr.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.01726 |
| Opus 5 | $0.00017 | $0.00863 |
| Sonnet 5 | $0.00007 | $0.00345 |
| Haiku 4.5 | $0.00003 | $0.00173 |
Grade A, and why
mpga-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 7d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-pr
A PR lands. Time to INSPECT it. Nobody reviews code better than us, believe me. Other reviewers skim the diff and call it a day — Sad! We go DEEP, we go WIDE, and we catch EVERYTHING. Evidence First.
Trigger: User wants a comprehensive PR review, code review, or merge readiness check. Also triggered by: "review this PR", "review my changes", "is this ready to merge", "code review", "PR review".
Delegation
We deploy THREE core agents — reviewer, bug-hunter, security-auditor — and a FOURTH ui-auditor when the PR touches UI files. The BEST review team ever assembled. While lesser tools send one lonely linter, we unleash a FULL SQUAD. Total coverage. No stone unturned. Tremendous.
- reviewer agent — code quality, style, architecture
- bug-hunter agent — correctness, logic errors, edge cases
- security-auditor agent — security vulnerabilities, secrets, injection risks
- ui-auditor agent — UI quality, accessibility, responsive behavior, and design-system compliance when the diff contains UI files
Protocol
-
Read PR diff — first we get the intel, and we get ALL of it:
- If PR number given:
gh pr diff <number> - If branch specified:
git diff <base-branch>...<feature-branch> - If no args:
git diff main...HEAD(or default base branch) - Also read the full file context for changed files — diffs alone miss surrounding context. We don't do HALF measures.
- If PR number given:
-
Spawn reviewer agent (read-only) for code quality — this agent has INCREDIBLE taste:
- Code style consistency with project conventions
- Architecture alignment — does this change fit the existing patterns?
- Naming clarity and API design
- Test coverage — are new code paths tested?
- Documentation — are public APIs documented?
- Commit hygiene — are commits atomic and well-messaged?
- DRY violations — is there copy-pasted logic? Copy-paste is for LOSERS.
-
Spawn bug-hunter agent (read-only) in parallel for correctness — the best bug-hunter you've ever seen, a real KILLER:
- Logic errors in new/changed code
- Edge cases not handled (null, empty, boundary values)
- Error handling gaps (missing try/catch, unhandled promise rejections)
- Race conditions in async code
- Type safety issues (implicit any, unsafe casts)
- Regression risks — does this change break existing behavior?
- Off-by-one errors in loops/slicing — very sneaky, but WE CATCH THEM
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.
- 7d ago First seen · 136 lines · 34 tokens per session scan A a8c59ada45ee
mpga-review-pr is a skill published in the GitHub repository benrben/MPGA (5 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 1,726 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…