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 ash1794/vibe-engineering --skill vibe-pre-commit-auditgit clone --depth 1 https://github.com/ash1794/vibe-engineeringWrote 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/ash1794/vibe-engineering/vibe-pre-commit-audit)<a href="https://agentmods.dev/skills/ash1794/vibe-engineering/vibe-pre-commit-audit"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/vibe-pre-commit-audit/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/ash1794/vibe-engineering/vibe-pre-commit-audit"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/vibe-pre-commit-audit.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 | $0.00035 | $0.00820 |
| Opus 5.5 | $0.00014 | $0.00328 |
| Sonnet 5.5 | $0.00007 | $0.00164 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
vibe-pre-commit-audit 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 17d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-pre-commit-audit
Catch the easy mistakes before they enter history.
When to Use This Skill
- Before creating a git commit
- When reviewing your own staged changes
- Before pushing to a shared branch
When NOT to Use This Skill
- Commits to personal scratch branches
- When the user explicitly says to skip checks
- Auto-generated code commits (lock files, etc.)
- Private or draft content leaking through built output (use
vibe-publication-leak-guard)
Tools First, Eyeballing Second
Pattern-matching a diff by eye misses things that a deterministic scanner catches. Before the manual checks:
- Run what the repo already has —
pre-commit run,lefthook,husky, or a lint/checkscript. Check.pre-commit-config.yaml,package.json, and theMakefile. - Run a secret scanner if one is installed (
gitleaks protect --staged,trufflehog git file://. --since-commit HEAD) orvibe-cli pre-commitfrom this repo. - If nothing is set up, suggest adding one (for example
vibe-cli hook install, or a gitleaks pre-commit hook), then fall back to the manual checks below.
Tool findings are blocking. The manual checks cover what the tools don't.
Checks
1. Secrets & Credentials
Scan for patterns:
API_KEY=,SECRET=,PASSWORD=,TOKEN=- AWS keys:
AKIA[0-9A-Z]{16} - Private keys:
-----BEGIN.*PRIVATE KEY----- - Connection strings with credentials
.envfiles being staged
2. Debug Statements
console.log(,fmt.Println(,print(,debugger;// DEBUG,# DEBUG,/* DEBUGlog.Debugin non-debug code paths
3. TODOs Without References
TODOwithout issue number:TODO: fix this(bad)TODO(#123): fix this(good)FIXME,HACK,XXX— flag all
4. Disabled Tests
t.Skip(,xit(,xdescribe(,@pytest.mark.skip- Commented-out test functions
//nolintwithout justification
5. Large Files
- Files > 1MB
- Binary files (images, compiled assets)
- Lock files with excessive changes
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.
- 17d ago Changed · +1 lines 408215f7a926
- 20d ago First seen · 89 lines · 35 tokens per session scan A aee319952a1f
vibe-pre-commit-audit is a skill published in the GitHub repository ash1794/vibe-engineering (164 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 820 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 2026-09-26.
Other skills, from other repositories
precommit
Pre-commit checks — lint:fix -> build -> test.
precommit-fast
Quick pre-commit checks — lint:fix -> test.
next-step
Change-aware next step advisor. Use when: user asks what to do next, workflow progression is unclear, session just started with dirty worktree. Not for: executing the suggested command (user decides), auto-loop decisions (hooks handle that). Output: findings-based suggestions or session summary with commit seed.
quick-finalize
Close out a change without the deep review loop: stage, simplify code and docs, run the project's checks, smoke test, update the changelog, self-improve, and ship. Use when the user asks to "quick finalize", "quickly finalize", "finalize quickly", "light finalize", "wrap this up quickly", "close this out without the…
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.
incremental-implementation
Use when implementing a multi-file change, building a feature from a breakdown, or writing a large amount of code. Not for a single settled ticket: use work.