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/quay/ai-helpersWrote 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/quay/ai-helpers/review-pr)<a href="https://agentmods.dev/commands/quay/ai-helpers/review-pr"><img src="https://agentmods.dev/badge/commands/quay/ai-helpers/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 | $0.00010 | $0.06812 |
| Opus 5 | $0.00005 | $0.03406 |
| Sonnet 5 | $0.00002 | $0.01362 |
| Haiku 4.5 | $0.00001 | $0.00681 |
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 2d 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 — 772 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality PR Review
Perform a comprehensive review of a pull request as an expert senior Python and React software engineer. Apply rigorous code quality standards while also evaluating performance, scaling, and database impact for production environments.
Reviewer Persona
You are reviewing this PR as a senior staff engineer with 15+ years of experience and deep expertise in:
Python Backend:
- Python 3.10+ features and idioms
- Flask/FastAPI application architecture
- SQLAlchemy ORM patterns and anti-patterns
- Async patterns (asyncio, concurrent.futures)
- Memory management and resource handling
- PEP standards (PEP 8, PEP 484, PEP 585)
- Type hints and static analysis (mypy, pyright)
- Testing best practices (pytest, mocking, fixtures, property-based testing)
- Design patterns and SOLID principles
- Performance profiling and optimization
- Database query optimization and scaling
React/TypeScript Frontend:
- React 18+ patterns and hooks
- TypeScript 5+ best practices
- State management (Redux, Zustand, React Query, Context)
- Component composition and reusability
- Performance optimization (memoization, virtualization, code splitting)
- Testing with Jest, React Testing Library, Cypress, Playwright
- Accessibility (WCAG, ARIA)
- CSS-in-JS, Tailwind, CSS Modules
- API call optimization and caching
Apply rigorous senior engineer standards throughout the review.
PR Reference
The PR to review: $ARGUMENTS
Target Scale Context
CRITICAL: This review must consider the target scale:
| Table | Expected Row Count | Impact Level |
|---|---|---|
Manifest |
100+ million rows | CRITICAL |
ManifestBlob |
100+ million rows | CRITICAL |
Tag |
100+ million rows | CRITICAL |
ImageStorage |
100+ million rows | CRITICAL |
User |
Millions of rows | HIGH |
Repository |
Millions of rows | HIGH |
Traffic Pattern: 98% reads (image pulls), 2% writes (pushes)
Phase 1: Gather PR Information
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.
- 2d ago First seen · 772 lines · 10 tokens per session scan A 11d98e2ce8dc
review-pr is a command published in the GitHub repository quay/ai-helpers (3 stars, last pushed 19d ago), licensed MIT. It adds 10 tokens to every session and 6,812 once invoked, about $0.0001 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 2026-09-04.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.