agentsclimarketplace

Workflow code review

Skill subhansh-dev/agent-maxxing/examples/workflow-code-review

Run an 8-angle code review with security audit before merging.From its SKILL.md

Install
npx -y skills add subhansh-dev/agent-maxxing --skill workflow-code-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.4 KB, 591 tokens by cl100k_base, as published. Nobody here has run it

Multi-Agent Workflow: Deep Code Review

Run an 8-angle code review with security audit before merging.

Skills Used

SkillRole
Deep Code Review8-angle correctness review
Security ReviewSecurity vulnerability audit
Code SimplifyCleanup and optimization
Runtime VerifyRun the app and observe behavior
Code Review ChecklistFinal checklist pass

Workflow

Phase 1: Gather Context

git diff @{upstream}...HEAD  # Get the diff
git log --oneline -10        # Recent commits

Phase 2: Deep Review (Parallel)

Launch 3 parallel reviews:

Review 1 — Correctness (8 angles):

Load Deep Code Review skill.
Run all 8 angles: line-by-line, removed-behavior, cross-file, reuse, simplification, efficiency, altitude, conventions.
Return: up to 10 findings ranked by severity.

Review 2 — Security:

Load Security Review skill.
Examine: input validation, auth, crypto, injection, data exposure.
Return: HIGH/MEDIUM findings only with confidence scores.

Review 3 — Cleanup:

Load Code Simplify skill.
Run 4 cleanup angles: reuse, simplification, efficiency, altitude.
Return: actionable fixes.

Phase 3: Runtime Verification

Load Runtime Verify skill.
Build the app, run it, drive the changed code paths.
Capture: stdout, screenshots, error messages.
Push on it: try edge cases, wrong inputs, rapid actions.
Verdict: PASS / FAIL / BLOCKED / SKIP

Phase 4: Final Checklist

Load Code Review Checklist.
Check: works? readable? safe? performant? maintainable?
Frontend: accessible? responsive? loading states? no CLS?
Backend: migrations reversible? rate limiting? logging?

Phase 5: Report

## Review Summary

**Correctness:** 3 findings (1 HIGH, 2 MEDIUM)
**Security:** 1 finding (1 MEDIUM)
**Cleanup:** 2 suggestions
**Runtime:** PASS — all paths verified

### Critical Findings
1. [HIGH] SQL injection in user search — line 42
2. [MEDIUM] Missing error handler in API route — line 87

### Recommendations
- Add input validation before line 42
- Wrap API handler in try/catch
- Consider adding rate limiting

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.