audit

A command for checking all documentation sources in a registry for short or index-only entries that may have fuller documentation elsewhere. It also looks for broken links and reports sources by priority.

In plain words
What is it for?
Use it to audit a documentation registry, discover linked full sources, find broken links, and prioritize follow-up work.
Why use it?
It helps identify incomplete registry coverage without checking every source manually. This makes it easier to find missing documentation and decide what to add next.

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/outfitter-dev/blz/audit
Clone the repo
git clone --depth 1 https://github.com/outfitter-dev/blz

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 564 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 $0.00000 $0.00564
Opus 5 $0.00000 $0.00282
Sonnet 5 $0.00000 $0.00113
Haiku 4.5 $0.00000 $0.00056

Measured 2d ago against content hash 709093b82995, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/commands/registry/audit.md · 55 lines

What it actually says

Registry: Audit All Sources for Quality

Instructions: $ARGUMENTS

  • Invoke the @agent-registry-handler subagent to audit all registry sources and identify index files that may have full documentation alternatives
  • Provide the subagent with any specific focus areas from $ARGUMENTS (e.g., "focus on sources with <100 lines" or "check AI/LLM sources")

Instructions to provide subagent:

  • Analyze all sources in the registry to identify potential index files:

    • Sources with "index" tag
    • Sources with "(Index)" in the name
    • Sources with contentType "index" or very low line counts (< 100 lines)
  • For each identified index source:

    • Run ./registry/scripts/discover-links.sh <source-id> to check for linked documentation
    • Note sources that have no .txt links (like Vercel, Redis)
    • Note sources that have discoverable full documentation alternatives
    • Document any 404s or broken links
  • Provide a comprehensive audit report organized by priority:

    1. High Priority: Index sources with discoverable full documentation (ready to add)
    2. Medium Priority: Mixed content sources (500-1000 lines) that might benefit from alternatives
    3. Low Priority: Index sources with no .txt links (need manual investigation)
    4. No Action: Full sources (>1000 lines) that are already comprehensive

Follow-up steps after audit:

  1. Present the audit report with statistics:

    • Total sources in registry: X
    • Index sources found: X
    • Discoverable alternatives: X
    • Sources needing manual review: X
    • Sources that are fine as-is: X
  2. For each high-priority finding:

    • Show the discovered sources
    • Provide recommended blz registry create-source commands
    • Note estimated time to add all sources
  3. For medium-priority findings:

    • List sources with justification for review
    • Suggest investigation approach
  4. For low-priority findings:

    • List index sources with no alternatives found
    • Suggest next steps (manual inspection, GitHub issue, etc.)
  5. Ask the user:

    • "Would you like me to proceed with adding the high-priority sources?"
    • "Should I investigate any of the medium-priority sources?"
    • "Would you like me to update index entries with proper tags and suffixes?"

Example usage:

  • /registry audit - Audit all sources
  • /registry audit focus on AI sources - Audit only AI/LLM category
  • /registry audit check for new .txt files - Re-check known indexes
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 · 55 lines · 0 tokens per session scan A 709093b82995

Subscribe to this mod's changes

audit is a command published in the GitHub repository outfitter-dev/blz (27 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 564 tokens. 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.