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 flonat/flonat-research --skill pre-commit-auditgit clone --depth 1 https://github.com/flonat/flonat-researchWrote 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/flonat/flonat-research/pre-commit-audit)<a href="https://agentmods.dev/skills/flonat/flonat-research/pre-commit-audit"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/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/flonat/flonat-research/pre-commit-audit"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/pre-commit-audit.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 | $0.00100 | $0.02868 |
| Opus 5.5 | $0.00040 | $0.01147 |
| Sonnet 5.5 | $0.00020 | $0.00574 |
| Haiku 4.5 | $0.00010 | $0.00287 |
Grade A, and why
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 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Commit Audit — File Size, Anonymity, Secrets
Three-pass safety scan before commit. Blocks pain-points: oversized commits (1.3GB parquet incident), CCS-style anonymity breaches, leaked credentials. Each pass is a hard gate; user OKs proceed.
Hard Rules
Existential — block proceed
- Size pass blocks anything >10MB unless gitignored OR user explicitly approves. Threshold matches
block-large-files.shhook for consistency. - Anonymity pass runs only on paper-relevant paths:
paper-*/,*.tex,*.bib,*.mdinside paper directories. Scope is data-driven — we don't false-flag README authorship. - Secrets pass uses an entropy heuristic + known-prefix list. No regex-only matching that misses high-entropy keys. Block on confirmed secret; warn on suspicious-but-uncertain.
- All four passes run on the same file set (default: staged for commit). Don't mix staged-only size check with all-files anonymity check.
- The Unicode pass is the one pass that is always in scope, including infra-only commits. It is identity-blind — it reads codepoints, never names — so it cannot false-flag authorship the way the anonymity pass can.
Format — catch in review
- Output a single consolidated table (file × pass × verdict) — not four separate reports.
- Severity tiers: BLOCK (must fix), WARN (proceed with confirm), OK.
- Always show the file path and line number when flagging — make it copy-paste-fixable.
When to Use
- Before any
git commiton a paper / project repo - Pre-submission checklist (research projects)
- Before pushing to anonymous-artifact repo (the highest-risk anonymity surface)
- After a sub-agent has written files (verify before committing their work)
- Wired as a
session-closePhase 4 sub-step (alternate path to running the hook)
When NOT to Use
- Before commits on infrastructure-only changes (skills, hooks, rules) — anonymity scan would false-flag README author lines. Exception: Phase 4 (Unicode) stays valid there and can be run alone:
pre-commit-audit --unicode-only - Auto-generated commits (CI, dependabot) — they don't need the scan
- When the change is purely metadata (
.gitignore,LICENSE, etc.)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 188 lines · 100 tokens per session scan A afaa6c7ec827
pre-commit-audit is a skill published in the GitHub repository flonat/flonat-research (147 stars, last pushed 25d ago), licensed MIT. It adds 100 tokens to every session and 2,868 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
commit
Analyze git diffs or staged changes and generate conventional commit messages that explain WHY a change was made. Supports auto-detecting type and scope, intelligent file staging, and interactive overrides. Use when asked to "write a commit message", "generate a commit", "describe my changes", "commit this"…
push-preflight
Secret-scans the commits a git push would send (gitleaks + regex layer; never history), then checks clean tree, forbidden files and fast-forward, with size and open-issue advisories. Refuses on any secret hit, no bypass. Triggers on: push to origin, push to github, push to remote, git push, can we push, safe to push…
tools
Utility commands — commit, compile, validate-bib, journal, context-status, deploy, learn. Replaces individual utility skills.
commit-push-pr
Commit changes, push to remote, and create a pull request. Use for completing features or fixes ready for review.
commit
Stage, commit, create PR, and merge to main. Use for the standard commit-PR-merge cycle.
pr-fallback
WHAT — When the repo has no GitHub PR template, structure the pull-request body using the default in references/pr-body-default.md. Pair with output-handshake and github-cli-workflow. Does not open the PR; HOW stays in the forge skill.