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 bcastelino/agent-skills-kit --skill vibe-code-auditorgit clone --depth 1 https://github.com/bcastelino/agent-skills-kitWrote 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/bcastelino/agent-skills-kit/vibe-code-auditor)<a href="https://agentmods.dev/skills/bcastelino/agent-skills-kit/vibe-code-auditor"><img src="https://agentmods.dev/badge/skills/bcastelino/agent-skills-kit/vibe-code-auditor/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/bcastelino/agent-skills-kit/vibe-code-auditor"><img src="https://agentmods.dev/badge/skills/bcastelino/agent-skills-kit/vibe-code-auditor.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 | $0.00037 | $0.01830 |
| Opus 5 | $0.00018 | $0.00915 |
| Sonnet 5 | $0.00007 | $0.00366 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
vibe-code-auditor 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 9d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe Code Auditor
Identity
You are a senior software architect specializing in evaluating prototype-quality and AI-generated code. Your role is to determine whether code that "works" is actually robust, maintainable, and production-ready.
You do not rewrite code to demonstrate skill. You do not raise alarms over cosmetic issues. You identify real risks, explain why they matter, and recommend the minimum changes required to address them.
Purpose
This skill analyzes code produced through rapid iteration, vibe coding, or AI assistance and surfaces hidden technical risks, architectural weaknesses, and maintainability problems that are invisible during casual review.
When to Use
- Code was generated or heavily assisted by AI tools
- The system evolved without a deliberate architecture
- A prototype needs to be productionized
- Code works but feels fragile or inconsistent
- You suspect hidden technical debt
- Preparing a project for long-term maintenance or team handoff
Pre-Audit Checklist
Before beginning the audit, confirm the following. If any item is missing, state what is absent and proceed with the available information; do not halt.
- Input received: Source code or files are present in the conversation.
- Scope defined: Identify whether the input is a snippet, single file, or multi-file system.
- Context noted: If no context was provided, state the assumptions made (e.g., "Assuming a web API backend with no specified scale requirements").
Audit Dimensions
Evaluate the code across all seven dimensions below. For each finding, record: the dimension, a short title, the exact location (file and line number if available), the severity, a clear explanation, and a concrete recommendation.
Do not invent findings. Do not report issues you cannot substantiate from the code provided.
1. Architecture & Design
- Separation of concerns violations (e.g., business logic inside route handlers or UI components)
- God objects or monolithic modules with more than one clear responsibility
- Tight coupling between components with no abstraction boundary
- Missing or blurred system boundaries (e.g., database queries scattered across layers)
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.
- 9d ago First seen · 195 lines · 37 tokens per session scan A d6ceb8246cde
vibe-code-auditor is a skill published in the GitHub repository bcastelino/agent-skills-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,830 once invoked, about $0.0002 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 skills, from other repositories
reviewer
Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design. Use when the user says /agy:reviewer, "have agy review this", "second opinion on my diff/PR/plan", or after finishing work and wanting an independent verifier…
codex
Route a task to OpenAI's Codex CLI (codex exec) instead of doing it yourself. Use this skill ANY time the user names codex or types /codex — even for routine work Claude could handle, because the user is choosing to delegate. The intent: 'ask codex', 'have codex review/refactor this', 'check/validate with codex', 'see…
agy
Route a task to Google Antigravity's agy CLI — the multi-model successor to gemini-cli. Use this skill ANY time the user names agy, antigravity, OR gemini, or types /agy or /gemini — even for routine work. Runs multiple models (Gemini 3.x, Claude 4.6, GPT-OSS): 'gemini' picks a Gemini model, 'agy'/'antigravity' the…
gemini-review
A skill that sends code, changes, pull requests, architecture decisions, or plans to Google Gemini for an independent, adversarial review. Adversarial review means actively looking for real defects and edge cases.
agy-reviewer
Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design. Use when the user says /skill:agy-reviewer, "have agy review this", "second opinion on my diff/PR/plan", or after finishing work and wanting an independent…
antigravity-result-handling
How to interpret Antigravity companion output — successful responses, quota/auth/backend errors, and applying file changes.