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 skills/flonat/flonat-research/pre-commit-auditnpx 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.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 | $0.00100 | $0.02868 |
| Opus 5 | $0.00050 | $0.01434 |
| Sonnet 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 2d 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.
- 2d 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 (131 stars, last pushed 10d ago), licensed MIT. It adds 100 tokens to every session and 2,868 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
wrap
Session end - document updates, commit.
chezmoi-workflows
Dotfile backup and sync with chezmoi. TRIGGERS - chezmoi, dotfiles, sync dotfiles, backup configs, cross-machine sync.
wolfram-headless
Run heavy Wolfram Language (wolframscript) computations from Claude Code reliably, and diagnose the misleading "The product exited because of a license error". Use whenever invoking wolframscript on a non-trivial computation, when a wolframscript job dies with a "license error" despite a valid license, or when Wolfram…
claim-audit
Audit what a passing script actually established, before writing any prose about it — build the computed-object ledger, rewrite every check's label as the weakest statement that makes its body pass, and separate the verdict on someone else's work from your own new claim. Run after the script passes and BEFORE the…
cross-validate
Format a result, derivation, or numerical value for independent verification by a second model. Use when you want a cross-check on an important or contested result.
sync-brief
Propagate load-bearing changes from workbook.tex to brief.tex.