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/agent37-platform/agent37-skills-collectionWrote 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/agent37-platform/agent37-skills-collection/local-review)<a href="https://agentmods.dev/commands/agent37-platform/agent37-skills-collection/local-review"><img src="https://agentmods.dev/badge/commands/agent37-platform/agent37-skills-collection/local-review/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/agent37-platform/agent37-skills-collection/local-review"><img src="https://agentmods.dev/badge/commands/agent37-platform/agent37-skills-collection/local-review.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 | $0.00007 | $0.01721 |
| Opus 5 | $0.00003 | $0.00860 |
| Sonnet 5 | $0.00001 | $0.00344 |
| Haiku 4.5 | $0.00001 | $0.00172 |
Grade A, and why
local-review 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 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.
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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Provide a code review for uncommitted local changes (both staged and unstaged).
Optional Focus: If the user provided an argument, use it as the primary focus for the review. The argument might be:
- A specific area to focus on (e.g., "focus on the payment flow")
- Context about what changed (e.g., "I refactored the auth module")
- Specific concerns to check (e.g., "make sure the error handling is correct")
- A method or file to prioritize (e.g., "check the handleSubmit function")
When a focus is provided, all review agents should:
- Prioritize issues related to the focus area
- Provide more detailed analysis of the focused area
- Still check for critical issues elsewhere, but weight the focus area higher
To do this, follow these steps precisely:
-
Use a Haiku agent to check the current state of the working directory:
- Run
git statusto see what files have changes - Run
git difffor unstaged changes andgit diff --stagedfor staged changes - If there are no changes, do not proceed and inform the user
- Return a summary of what files changed and the nature of the changes
- If a focus argument was provided, note which files/changes are most relevant to that focus
- Run
-
Use another Haiku agent to find any relevant CLAUDE.md files: the root CLAUDE.md file (if one exists), as well as any CLAUDE.md files in the directories containing modified files
-
Then, launch 5 parallel Sonnet agents to independently code review the changes. Each agent should read the full file context when needed. If a focus argument was provided, include it in each agent's prompt so they prioritize that area. The agents should return a list of issues and the reason each issue was flagged: a. Agent #1: Audit the changes to make sure they comply with any CLAUDE.md guidelines found. Note that CLAUDE.md is guidance for Claude as it writes code, so not all instructions will be applicable during code review. b. Agent #2: Read the file changes, then scan for bugs, logic errors, and edge cases. Focus on significant bugs, avoid nitpicks. Check for: null/undefined issues, off-by-one errors, race conditions, resource leaks, error handling gaps. c. Agent #3: Scan for security vulnerabilities (OWASP top 10): injection flaws, XSS, auth bypass, sensitive data exposure, insecure dependencies, etc. d. Agent #4: Check for TypeScript type safety issues, performance problems, and code quality concerns that would fail code review. e. Agent #5 (Code Simplifier): You are an expert code simplification specialist focused on enhancing code clarity, consistency, and maintainability while preserving exact functionality. Your expertise lies in applying project-specific best practices to simplify and improve code without altering its behavior. You prioritize readable, explicit code over overly compact solutions.
Analyze the changed code and flag issues related to:
-
Preserve Functionality: Flag any simplification that would change what the code does - only how it does it matters. All original features, outputs, and behaviors must remain intact.
-
Apply Project Standards: Flag violations of coding standards from CLAUDE.md including:
- Use ES modules with proper import sorting and extensions
- Prefer
functionkeyword over arrow functions - Use explicit return type annotations for top-level functions
- Follow proper React component patterns with explicit Props types
- Use proper error handling patterns (avoid try/catch when possible)
- Maintain consistent naming conventions
-
Enhance Clarity: Flag code that could be simplified by:
- Reducing unnecessary complexity and nesting
- Eliminating redundant code and abstractions
- Improving readability through clear variable and function names
- Consolidating related logic
- Removing unnecessary comments that describe obvious code
- IMPORTANT: Flag nested ternary operators - prefer switch statements or if/else chains for multiple conditions
- Choose clarity over brevity - explicit code is often better than overly compact code
-
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 · 146 lines · 7 tokens per session scan A 878388df9e47
local-review is a command published in the GitHub repository agent37-platform/agent37-skills-collection (186 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 1,721 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.