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.
npx agentmods add commands/outfitter-dev/blz/auditgit clone --depth 1 https://github.com/outfitter-dev/blzWhat 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 | $0.00000 | $0.00564 |
| Opus 5 | $0.00000 | $0.00282 |
| Sonnet 5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00056 |
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.
What it actually says
Registry: Audit All Sources for Quality
Instructions: $ARGUMENTS
- Invoke the
@agent-registry-handlersubagent 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
- Run
-
Provide a comprehensive audit report organized by priority:
- High Priority: Index sources with discoverable full documentation (ready to add)
- Medium Priority: Mixed content sources (500-1000 lines) that might benefit from alternatives
- Low Priority: Index sources with no .txt links (need manual investigation)
- No Action: Full sources (>1000 lines) that are already comprehensive
Follow-up steps after audit:
-
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
-
For each high-priority finding:
- Show the discovered sources
- Provide recommended
blz registry create-sourcecommands - Note estimated time to add all sources
-
For medium-priority findings:
- List sources with justification for review
- Suggest investigation approach
-
For low-priority findings:
- List index sources with no alternatives found
- Suggest next steps (manual inspection, GitHub issue, etc.)
-
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
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 · 55 lines · 0 tokens per session scan A 709093b82995
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.
Other commands, from other repositories
CAA-add
Add a valuable fix/insight from this session to the Claude Archive (CAA) — give, score honestly, sync.
CAA-search
Search the Claude Archive (CAA) for scored solutions BEFORE solving — take the best hit, verify, apply.
CAA-add-latest
Instantly archive the LATEST hard-won fix from this session to the Claude Archive (CAA) — zero questions.
template
Manage issue templates for streamlined issue creation.
fieldtheory
Explain and drive the Field Theory CLI — bookmark-sourced seeds, repo-aware possibility runs that score ideas onto a 2x2 grid, and the interconnected .md files they leave behind. Trigger when the user asks about ft, bookmarks, seeds, ft possible (or the older name ft ideas), grids, dots/nodes, or how to turn saved…
security-review
CWE 기반 보안 검토 + STRIDE 위협 모델링 (v6 - effort:max 강제).