What is create-audit?

A skill for adding a new audit module to check-ai, a scanner that checks whether a repository contains files, folders, or patterns that support AI-assisted development. Each audit is a separate JavaScript module.

Use it when you need check-ai to inspect a new file, directory, or pattern. It creates an audit with checks, labels, weights, paths, and optional custom analysis.

It lets you add a new kind of repository check without changing the scanner, scoring system, or report generator. The module is discovered automatically when the scanner runs.

How f/check-ai configures Windsurf

Reuse

Borrowing it

Nothing to install: this file belongs to f/check-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/f/check-ai/main/.windsurf/skills/create-audit/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/f/check-ai

Made for: Windsurf.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/f/check-ai/create-audit/github.svg)](https://agentmods.dev/skills/f/check-ai/create-audit)

Your own site

<a href="https://agentmods.dev/skills/f/check-ai/create-audit"><img src="https://agentmods.dev/badge/skills/f/check-ai/create-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/f/check-ai/create-audit"><img src="https://agentmods.dev/badge/skills/f/check-ai/create-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,182 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00066	$0.01182
Opus 5.5	$0.00026	$0.00473
Sonnet 5.5	$0.00013	$0.00236
Haiku 4.5	$0.00007	$0.00118

Measured 2mo ago against content hash c1854d368a90, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/mcp-audit-example.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.windsurf/skills/create-audit/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Audit

Create new audit modules for the check-ai AI-readiness scanner. Each audit is a single .mjs file in src/audits/ that is dynamically loaded at scan time — no changes to scanner, scorer, or reporter needed.

Audit File Contract

Every audit file must export:

export const section = 'Section Name';  // shown in report
export const checks = [ ... ];          // array of check objects
// optional:
export function analyze(rootDir, ctx) { return { 'custom-key': { found, detail } }; }

The scanner auto-discovers all .mjs files in src/audits/, sorted alphabetically.

Check Object Schema

{
  id: 'unique-kebab-id',        // unique across all audits
  label: 'Display label',       // shown in terminal output
  section,                       // use the exported section constant
  weight: 5,                    // 1-20, impact on score
  paths: ['file.md', '.dir/'],  // candidate paths to probe
  type: 'file',                 // see Check Types below
  description: 'Why this matters for AI-readiness',
}

Check Types

Type	Behavior
`file`	Exists as a file at any of `paths`
`dir`	Exists as a directory at any of `paths`
`any`	Exists as either file or directory
`deep-scan`	Walks the file tree for `deepPattern` matches (requires `deepPattern` field)
`custom`	Handled by the audit's `analyze()` function (requires `custom` field matching a key in analyze's return)

Weight Guidelines

Weight	Meaning
1-2	Nice to have
3-4	Useful signal
5-7	Important
8-10	High impact
15-20	Critical (use sparingly)

Read the full file on GitHub · 144 lines

Files

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.

references/mcp-audit-example.mjs 2.5 KB runs code

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.

2mo ago First seen · 144 lines · 66 tokens per session scan A c1854d368a90

Subscribe to this mod's changes

create-audit is a skill published in the GitHub repository f/check-ai (66 stars, last pushed 7mo ago), licensed MIT. It adds 66 tokens to every session and 1,182 once invoked, about $0.0003 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 2026-08-30.

Debugging agents ai-readiness

create-audit next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
create-auditf/check-ai	Skill	66	7mo ago	MIT	A	66	Windsurf
adk-debuggoogle/adk-python	Skill	22k	yesterday	Apache-2.0	A	191	Claude Code, Codex
resolve-handoffomnigent-ai/omnigent	Skill	11k	today	Apache-2.0	A	23	Claude Code, Codex
iterate-implementationhumanlayer/humanlayer	Skill	13k	yesterday	Apache-2.0	A	16	Claude Code, Codex
verify-omnigentomnigent-ai/omnigent	Skill	11k	today	Apache-2.0	A	100	Claude Code, Codex
typescript-testingComposioHQ/composio	Skill	31k	yesterday	MIT	A	92	Claude Code, Codex
cli-e2eComposioHQ/composio	Skill	31k	yesterday	MIT	A	62	Claude Code, Codex

check-ai: Skill for Windsurf