docs-audit

A command for auditing a project's documentation structure and Claude Code rules for size, missing files, stale patterns, dead paths, and orphaned records.

In plain words
What is it for?
Use it to inspect CLAUDE.md, .claude/rules/, docs/, registries, and documentation commands, then produce a report and propose fixes.
Why use it?
It finds documentation problems that waste AI context or leave project guidance incomplete or outdated.

Command for Claude Code

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 commands/jondarza/loadout/docs-audit
Clone the repo
git clone --depth 1 https://github.com/JOndarza/loadout

Made for: Claude Code.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 297 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 $0.00015 $0.00297
Opus 5 $0.00008 $0.00148
Sonnet 5 $0.00003 $0.00059
Haiku 4.5 $0.00002 $0.00030

Measured 2d ago against content hash 9a55e8c159bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-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.

.claude/skills/docs-architect/assets/commands/docs-audit.md · 21 lines

What it actually says

Run the docs-architect skill in audit mode. Check:

  • CLAUDE.md over 100 lines (v2 tight limit)
  • .claude/rules/*.md files over 40 lines or missing frontmatter where expected
  • .claude/rules/*.md with paths: patterns that match zero files in the repo (dead scopes)
  • Presence of legacy docs/_lite/*.summary.md → suggest /docs-migrate
  • Missing always-loaded rules (business-context.md, coding-rules.md, tech-stack.md, architecture.md)
  • Missing .claude/agents/doc-explorer.md when docs/ has more than 10 files
  • Missing /docs-audit, /docs-sync, /docs-migrate slash commands in .claude/commands/
  • CLAUDE.md containing @docs/_lite/* imports (stale v1 pattern)
  • Full-doc files (docs/*.md) over 150 lines without segmentation
  • Orphaned story/bug files not referenced in backlog.md / bugs.md
  • Registry entries pointing to missing files
  • docs/README.md missing or over 200 lines

After the report, offer to auto-fix each issue. Group fixes by type and ask confirmation before applying.

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. 2d ago First seen · 21 lines · 15 tokens per session scan A 9a55e8c159bd

Subscribe to this mod's changes

docs-audit is a command published in the GitHub repository JOndarza/loadout (2 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 297 once invoked, about $0.0001 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.