docs-qa

docs-qa is a skill for Claude Code, Codex from Edmonds-Commerce-Limited/claude-code-hooks-daemon. It costs 57 tokens per session (659 once invoked), scanned A, original, MIT.

A documentation-checking skill that looks for conflicting facts, repeated information, outdated references, and long comments being used as documentation.

In plain words
What is it for?
Use it to audit one topic, a plan folder, or the full documentation collection for duplicated or inconsistent guidance.
Why use it?
It reveals documentation drift, where different files give different instructions or old information remains after the project changes.

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/edmonds-commerce-limited/claude-code-hooks-daemon/docs-qa
Any agent
npx skills add Edmonds-Commerce-Limited/claude-code-hooks-daemon --skill docs-qa
Clone the repo
git clone --depth 1 https://github.com/Edmonds-Commerce-Limited/claude-code-hooks-daemon

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 docs-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/edmonds-commerce-limited/claude-code-hooks-daemon/docs-qa.svg)](https://agentmods.dev/skills/edmonds-commerce-limited/claude-code-hooks-daemon/docs-qa)
Your own site
<a href="https://agentmods.dev/skills/edmonds-commerce-limited/claude-code-hooks-daemon/docs-qa"><img src="https://agentmods.dev/badge/skills/edmonds-commerce-limited/claude-code-hooks-daemon/docs-qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 659 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 $0.00057 $0.00659
Opus 5 $0.00028 $0.00329
Sonnet 5 $0.00011 $0.00132
Haiku 4.5 $0.00006 $0.00066

Measured 4d ago against content hash e8f190360c37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-qa 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 4d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/_locate-cli.sh, scripts/find-comment-blocks.sh, scripts/sweep.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/docs-qa/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation QA

This skill is a shim. It carries no documentation body of its own — it exists to dispatch the hooks-daemon-docs-qa agent, which does the real work. See CLAUDE/DocumentationStrategy.md for the ruleset it enforces.

What to do

Dispatch the hooks-daemon-docs-qa agent (Task tool, subagent_type: "hooks-daemon-docs-qa") with:

  • the scope the user asked for (a topic, a plan folder, or "the whole corpus" if unstated)
  • a pointer to run the deterministic checks first: hooks-daemon docs-qa --sweep --json
  • a pointer to the comment-block finder for its Decision-7 hunt: hooks-daemon find-comment-blocks <source-root> --json
/docs-qa                    # full-corpus audit
/docs-qa CLAUDE/Plan/00284   # scoped to one plan folder's topic

The agent is read-only — it delivers findings inline, as its final report, and never edits anything or writes a report file on its own initiative. If you want the findings persisted (e.g. to untracked/reports/), name that target explicitly when dispatching it. Review its report and act on the findings yourself (or ask it to be dispatched again after you have made changes, to re-verify).

If the agent is not deployed

hooks-daemon-docs-qa ships opt-in (agents.docs_qa.enabled: false by default). If the Task dispatch fails because the agent is not found, tell the user to enable it in .claude/hooks-daemon.yaml:

agents:
  docs_qa:
    enabled: true

then run hooks-daemon restart (or the next daemon upgrade/install run) to deploy it into .claude/agents/hooks-daemon-docs-qa.md.

Bundled finder scripts

scripts/ bundles thin wrappers over the deterministic CLI, for a human or the agent to run directly without recalling the exact daemon subcommand:

  • scripts/sweep.shhooks-daemon docs-qa --sweep --json
  • scripts/find-comment-blocks.sh <path>...hooks-daemon find-comment-blocks <path>... --json

Both are finders: they LIST candidates, they never judge content and never gate a tool call. Judgement is the agent's job (or the reviewing human's).

Read the full file on GitHub · 65 lines

Files

What ships with it

3 files 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. 4d ago First seen · 65 lines · 57 tokens per session scan A e8f190360c37

Subscribe to this mod's changes

docs-qa is a skill published in the GitHub repository Edmonds-Commerce-Limited/claude-code-hooks-daemon (3 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 659 once invoked, about $0.0003 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