A command that checks whether a repository has the expected public documentation and reviews the quality of the documents it does have. A repository is the project’s tracked files and history.

Run /docs-audit to scan documentation, check it against the listed standards, and report findings with severity levels.

It reveals missing or weak files such as a README, license, contribution guide, security policy, or issue templates before others need them.

docs-audit — Command by littlebearapps

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/littlebearapps/pitchdocs/docs-audit

Clone the repo

git clone --depth 1 https://github.com/littlebearapps/pitchdocs

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,689 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.

Model	Per session	Once invoked
Fable 5	$0.00011	$0.02689
Opus 5	$0.00005	$0.01345
Sonnet 5	$0.00002	$0.00538
Haiku 4.5	$0.00001	$0.00269

Measured 2d ago against content hash 3eac5fef042d, 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.

commands/docs-audit.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/docs-audit

Check what public-facing documentation is missing or needs improvement.

Behaviour

Load the pitchdocs-suite skill for the complete inventory
If GitHub MCP tools are unavailable (GitLab/Bitbucket), gather equivalent data via glab CLI, REST API, or git history. Load platform-profiles for platform-specific template paths.
Scan the repository for all expected documentation files
Quality-check existing documents against the 4-question framework (auto-loaded via doc-standards rule)
Report findings with severity levels

Audit Checklist

Presence Check (Does the file exist?)

Priority	File	Status
Critical	README.md	?
Critical	LICENSE	?
High	CONTRIBUTING.md	?
High	.github/ISSUE_TEMPLATE/bug_report.yml	?
High	.github/ISSUE_TEMPLATE/feature_request.yml	?
High	.github/PULL_REQUEST_TEMPLATE.md	?
Medium	CHANGELOG.md	?
Medium	CODE_OF_CONDUCT.md	?
Medium	SECURITY.md	?
Medium	.github/ISSUE_TEMPLATE/config.yml	?
Medium	SUPPORT.md	?
Medium	.github/release.yml	?
Medium	llms.txt	?
Low	ROADMAP.md	?
Low	.github/FUNDING.yml	?
Low	docs/README.md	?
Low	docs/guides/	?
Low	CITATION.cff	?
Medium	AGENTS.md	?
Medium	.github/copilot-instructions.md	?
Low	CLAUDE.md	?
Low	.cursorrules	?

AI Context Files Check

If the project has AI context files, verify they reflect the current codebase:

AGENTS.md references correct language/framework version
AGENTS.md key commands are runnable (test, build, lint)
CLAUDE.md file paths exist on disk
.cursorrules conventions match current linter config
.github/copilot-instructions.md patterns are consistent with codebase

Report format:

AI Context Files:
  ✓ AGENTS.md — present, references TypeScript + Vitest (matches codebase)
  ⚠ CLAUDE.md — references src/index.ts but file is now src/main.ts
  · .cursorrules — not present (recommend: install ContextDocs and run /contextdocs:ai-context cursor)
  · .github/copilot-instructions.md — not present (recommend: install ContextDocs and run /contextdocs:ai-context copilot)

Read the full file on GitHub · 298 lines

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.

2d ago First seen · 298 lines · 11 tokens per session scan A 3eac5fef042d

Subscribe to this mod's changes

docs-audit is a command published in the GitHub repository littlebearapps/pitchdocs (7 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 2,689 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.

Git and workflow Writing and docs changelog-generator claude-code claude-code-plugin developer-tools documentation documentation-generator

docs-audit

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/docs-audit

Behaviour

Audit Checklist

Presence Check (Does the file exist?)

AI Context Files Check

What this file has done since we first saw it

Other commands, from other repositories

create-skill

install-skill

sync-config

review-renovate

monitor-ci

/add-claude-rule