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 agentmods add commands/latestaiagents/agent-skills/review-ai-codegit clone --depth 1 https://github.com/latestaiagents/agent-skillsWrote 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/latestaiagents/agent-skills/review-ai-code)<a href="https://agentmods.dev/commands/latestaiagents/agent-skills/review-ai-code"><img src="https://agentmods.dev/badge/commands/latestaiagents/agent-skills/review-ai-code.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 | $0.00013 | $0.00849 |
| Opus 5 | $0.00006 | $0.00425 |
| Sonnet 5 | $0.00003 | $0.00170 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
review-ai-code 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 6d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review-ai-code
Systematic review of AI-generated code for bugs, security issues, and best practices.
What to Review
Paste the AI-generated code, or point me to the file(s) to review.
Review Checklist
I'll check for these common AI code issues:
1. Correctness Issues
| Issue | What I Look For |
|---|---|
| Hallucinated APIs | Methods/functions that don't exist |
| Wrong signatures | Incorrect parameter types or order |
| Logic errors | Off-by-one, wrong comparisons, missing cases |
| Incomplete handling | Missing error cases, edge cases |
| Outdated patterns | Deprecated APIs, old syntax |
2. Security Issues
| Issue | What I Look For |
|---|---|
| Injection vulnerabilities | SQL injection, XSS, command injection |
| Hardcoded secrets | API keys, passwords in code |
| Insecure defaults | Missing auth, permissive CORS |
| Data exposure | Logging sensitive data, verbose errors |
3. Quality Issues
| Issue | What I Look For |
|---|---|
| Over-engineering | Unnecessary abstractions |
| Under-engineering | Missing validation, error handling |
| Inconsistent style | Doesn't match codebase conventions |
| Poor naming | Unclear variable/function names |
| Missing types | TypeScript any, missing interfaces |
Review Process
Step 1: Quick Scan
## First Impressions
- [ ] Code compiles/runs
- [ ] Imports exist
- [ ] Functions are called correctly
- [ ] Types are correct
Step 2: Line-by-Line Review
I'll annotate issues:
// ❌ Issue: SQL injection vulnerability
const query = `SELECT * FROM users WHERE id = ${userId}`;
// ✅ Fixed: Use parameterized query
const query = 'SELECT * FROM users WHERE id = $1';
const result = await db.query(query, [userId]);
Step 3: Verification Steps
## Verify Before Using
1. **Test the happy path**
- Does it work with valid inputs?
2. **Test edge cases**
- Empty inputs, null values, boundaries
3. **Test error cases**
- Invalid inputs, network failures, timeouts
4. **Check against real APIs**
- Do the function calls actually exist?
- Are the parameters correct?
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.
- 6d ago First seen · 152 lines · 13 tokens per session scan A 984467cd5278
review-ai-code is a command published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 849 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 2026-08-31.
Other commands, from other repositories
fdk-react-create
Create a new Platform 3.0 React Meta app (default UI stack). Uses fdk create react-starter-template or react-meta skeletons with DEW components, metaConfig in manifest.json, and React Router.
fdk-refactor
Reduce function complexity in a Freshworks app to meet cyclomatic complexity ≤ 7 per function. Extracts helper functions, simplifies conditionals, and preserves behavior while improving code quality.
fw-setup-uninstall
Uninstall FDK completely — keeps Node.js and nvm (/fw-setup uninstall).
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.