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 dhaupin/vant --skill vant-skill-review-codegit clone --depth 1 https://github.com/dhaupin/vantWrote 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/dhaupin/vant/vant-skill-review-code)<a href="https://agentmods.dev/skills/dhaupin/vant/vant-skill-review-code"><img src="https://agentmods.dev/badge/skills/dhaupin/vant/vant-skill-review-code/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/skills/dhaupin/vant/vant-skill-review-code"><img src="https://agentmods.dev/badge/skills/dhaupin/vant/vant-skill-review-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00015 | $0.00896 |
| Opus 5.5 | $0.00006 | $0.00358 |
| Sonnet 5.5 | $0.00003 | $0.00179 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
review-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 1mo 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Read code. Understand it. Find issues. Report clearly.
First: Read It Like It Works
Before finding bugs, understand what it does:
- Run it - Actually execute if possible
- Trace the data - Follow input to output
- Find the edges - Where does it start, where does it end?
- Check the happy path - Does the main thing work?
Assume it's right until you understand it. Then question.
Pass 1: Functionality
Does this actually do the thing?
| Check | Look For |
|---|---|
| Entry point | Where does execution start? |
| Main logic | Core algorithm correct? |
| Edge cases | null, empty, extremes |
| Error handling | What happens on failure? |
| Return values | What's actually returned? |
How to verify:
// Run with inputs
node file.js test-input
// Check output matches expectation
Pass 2: Security
Input enters. Something executes. Check:
// Credentials exposed?
process.env.API_KEY
// Hardcoded secrets?
const token = "sk-..."
// Injection points?
db.query(userInput)
exec(userInput)
eval(userInput)
// Filesystem?
fs.readFile(path)
Questions to ask:
- Can this be called by anyone?
- What happens with malicious input?
- Are credentials visible in stack traces?
- Rate limiting?
Pass 3: Performance
Expensive operations:
// Loops inside loops?
items.map(i => i.sub.map(s => ...))
// Async blocked?
await Promise.all(heavy)
// Missing cache?
// Same lookup repeated
// Memory unbounded?
arr.push(infinite)
Questions:
- Scales with users?
- Memory bounded?
- Async/await correct?
Pass 4: Code Quality
| Check | Issue | Fix |
|---|---|---|
| Name unclear | x |
userCount |
| Function too long | 500 lines | Split it |
| Comments what not why | // loop |
// sorted by date to match UI |
| No tests | - | Add tests |
Questions:
- Can I understand this in 30 seconds?
- Does function do one thing?
- Are side effects obvious?
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.
- 1mo ago First seen · 191 lines · 15 tokens per session scan A 3826b3db93ff
review-code is a skill published in the GitHub repository dhaupin/vant (11 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 896 once invoked, about $0.0001 per session on Opus 5.5. 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
pr-writing-review
Extract and analyze writing improvements from GitHub PR review comments. Use when asked to show review feedback, style changes, or editorial improvements from a GitHub pull request URL. Handles both explicit suggestions and plain text feedback. Produces structured output comparing original phrasing with reviewer…
check-vercel-rules
Explicit Codex workflow: Run the packaged Vercel Labs agent-skills rule audit on the current project.
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
hypotheses
Turns a research direction into testable hypotheses with predictions, competing explanations and the experiments that discriminate between them, including the design (controls, randomization, blocking), sample size or seed count, the pre-specified analysis, and the result that would falsify each hypothesis. Use when a…
check
Comprehensive rule-based check. Triggered by "/check [target]" to evaluate all source files against project rules and report every violation.
review
Review pull requests or code changes. Triggered by "/review [prlink]" or when user asks to review pending changes.