docs

A command for checking whether a project's documentation still matches its code and files. It reviews written content, README file listings, and links between documents.

In plain words
What is it for?
Auditing documentation for accuracy, checking README structure, validating internal links, and applying safe fixes within a selected file or directory.
Why use it?
It finds outdated instructions, incorrect file trees, broken references, and other documentation that no longer reflects the repository.

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/rjwalters/kicad-tools/docs
Clone the repo
git clone --depth 1 https://github.com/rjwalters/kicad-tools

Made for: Claude Code.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,679 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 $0.00017 $0.01679
Opus 5 $0.00009 $0.00839
Sonnet 5 $0.00003 $0.00336
Haiku 4.5 $0.00002 $0.00168

Measured 3d ago against content hash 8e6da887ecfc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

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/commands/repo/docs.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/repo:docs — Documentation Check

The canonical documentation-health command. Verify that the repo's docs still describe the repo that exists — not the one that existed three refactors ago.

This is the single entry point for docs work. It covers three layers:

  1. Content accuracy — does the prose still match how things actually work? (unique to this command)
  2. README structure — do file trees and directory listings match disk? (delegates to [[readme]])
  3. Cross-references — do internal links and paths still resolve? (delegates to [[links]])

/repo:readme and /repo:links remain callable on their own when you only want that one layer. Reach for /repo:docs when you want the whole picture.

Usage

/repo:docs                     # Full repo — apply safe fixes, report as you go
/repo:docs docs/               # Scope to one subtree
/repo:docs README.md           # Check a single doc
/repo:docs --ask               # Review findings and confirm before applying

The optional path argument scopes every layer the same way, exactly as [[readme]] and [[links]] scope on their own.

What It Checks

1. Content Accuracy

This is the semantic layer that structural checks miss — prose that parses fine and links that resolve fine, but describes behavior that has since changed. Read the docs against the actual repo state and flag drift:

  • Feature / command tables that list capabilities the repo no longer has, or omit ones it gained. For a repo with .claude/commands/, cross-check every documented command against the files that actually exist, in both directions.
  • CHANGELOG currency — recent commits (features, breaking changes, renames) that landed with no corresponding CHANGELOG entry. Compare the top entry's date/version against git log since then.
  • Code examples & snippets in docs that reference symbols, flags, file paths, or commands that no longer exist. Verify each referenced identifier resolves in the current tree.
  • Described workflows — step-by-step instructions (install, build, usage) that name scripts, targets, or flags. Confirm they still exist and still take the arguments shown.
  • Version / count claims — "supports 12 commands", "requires Node 18", hardcoded numbers that drift as the repo changes.

Read the full file on GitHub · 167 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.

  1. 3d ago First seen · 167 lines · 17 tokens per session scan A 8e6da887ecfc

Subscribe to this mod's changes

docs is a command published in the GitHub repository rjwalters/kicad-tools (52 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 1,679 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 2026-08-30.