audit-design-docs

audit-design-docs is a skill for Claude Code, Codex from sunholo-data/ailang-parse. It costs 79 tokens per session (468 once invoked), scanned A, original, Apache-2.0.

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.

In plain words
What is it for?
Use it to audit design-doc folders, find loose or stale files, detect impossible version assignments, and propose moves before making them.
Why use it?
It reveals version and status mismatches so design documentation reflects the actual project state.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sunholo-data/ailang-parse/audit-design-docs
Any agent
npx skills add sunholo-data/ailang-parse --skill audit-design-docs
Clone the repo
git clone --depth 1 https://github.com/sunholo-data/ailang-parse

Made for: Claude Code, Codex.

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.

agentmods badge for audit-design-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/sunholo-data/ailang-parse/audit-design-docs.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.svg" alt="Measured on agentmods" 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. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00079 $0.00468
Opus 5 $0.00039 $0.00234
Sonnet 5 $0.00016 $0.00094
Haiku 4.5 $0.00008 $0.00047

Measured 3d ago against content hash 8902ad1c3604, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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

  1. Never delete design docs — move to archive/ if superseded
  2. implemented/ folders must use the actual release version, not the design milestone version
  3. The Go binary doc is intentionally unversioned (blocked on external compiler bugs) — don't flag it
  4. When moving to implemented/, strip old version prefixes from filenames
  5. 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.

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.

  1. 3d 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 today), licensed Apache-2.0. It adds 79 tokens to every session and 468 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories