What is audit-design-docs?

A checker for organizing design documents according to the project's current version. It distinguishes planned work from features that have already shipped and reports misplaced or contradictory documents.

Use it to audit design-doc folders, find loose or stale files, detect impossible version assignments, and propose moves before making them.

It reveals version and status mismatches so design documentation reflects the actual project state.

How sunholo-data/ailang-parse configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sunholo-data/ailang-parse. 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/sunholo-data/ailang-parse/main/.claude/skills/audit-design-docs/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/sunholo-data/ailang-parse

Made for: Claude Code.

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/sunholo-data/ailang-parse/audit-design-docs/github.svg)](https://agentmods.dev/skills/sunholo-data/ailang-parse/audit-design-docs)

Your own site

<a href="https://agentmods.dev/skills/sunholo-data/ailang-parse/audit-design-docs"><img src="https://agentmods.dev/badge/skills/sunholo-data/ailang-parse/audit-design-docs/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/sunholo-data/ailang-parse/audit-design-docs"><img src="https://agentmods.dev/badge/skills/sunholo-data/ailang-parse/audit-design-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 468 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	$0.00079	$0.00468
Opus 5.5	$0.00032	$0.00187
Sonnet 5.5	$0.00016	$0.00094
Haiku 4.5	$0.00008	$0.00047

Measured 2mo ago against content hash 8902ad1c3604, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

audit-design-docs 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 (scripts/audit.sh), 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.

.claude/skills/audit-design-docs/SKILL.md · 46 lines

What it actually says

Audit Design Docs

How It Works

The audit compares the project's current version (from ailang.toml) against every design doc in design_docs/ and flags inconsistencies. The implemented/ folder is a changelog — version folders reflect the actual release each feature shipped in. The planned/ folder has target versions for future work.

Workflow

Step 1: Get Current Version

grep '^version' ailang.toml

Step 2: Run the Audit Script

bash .claude/skills/audit-design-docs/scripts/audit.sh

Step 3: Review Findings

Category	Severity	Meaning
`VERSION_MISMATCH`	High	Implemented doc with version > current (impossible — hasn't shipped)
`STATUS_CONTRADICTION`	High	Doc's Status: header contradicts its folder
`LOOSE_FILE`	Medium	File not in a version subfolder
`STALE_PLANNED`	Medium	Planned doc with version <= current (should be implemented or re-versioned)

Step 4: Propose and Execute Fixes

For each finding, propose a move. Use git mv for tracked files. Always ask user to confirm before executing. After moves, update design_docs/README.md.

Rules

Never delete design docs — move to archive/ if superseded
implemented/ folders must use the actual release version, not the design milestone version
The Go binary doc is intentionally unversioned (blocked on external compiler bugs) — don't flag it
When moving to implemented/, strip old version prefixes from filenames
Update Status: headers when moving docs between folders

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.

scripts/audit.sh 4.4 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 · 46 lines · 79 tokens per session scan A 8902ad1c3604

Subscribe to this mod's changes

audit-design-docs is a skill published in the GitHub repository sunholo-data/ailang-parse (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 79 tokens to every session and 468 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 2026-08-31.

Planning document docx markdown parser parsing-library pptx

document-converter

Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown. Provides the agent with conversion strategies for academic and research workflows.

wentorai/Research-Claw · 50 tokens

document-processing

Use this skill when processing documents programmatically — PDF manipulation (extract, merge, split, rotate, watermark, form-fill, OCR), DOCX creation and editing (templates, mail-merge, style management), XLSX spreadsheet handling (formulas, charts, pivot tables, data analysis), PPTX presentation generation (layouts…

JPeetz/agent-skills · 120 tokens

doc-converter

Universal document format converter - DOCX, PDF, Markdown, HTML, TXT.

chainlesschain/chainlesschain · 19 tokens

anywrite

Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.

ranbot-ai/awesome-skills · 37 tokens

office-router

Route Office requests into the correct xlsx, docx, or pptx workflow, while preferring Slidev for new presentation drafts unless .pptx is explicitly required.

matingai/crab · 38 tokens

document-generation

Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. This is the generic document-writing engine (tool surface, tagged-value shapes, fabrication rules). For the four standard NetClaw report…

automateyournetwork/netclaw · 118 tokens

ailang-parse: Skill for Claude Code