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 skills/closetheloops/moradin/auditnpx skills add CloseTheLoops/moradin --skill auditgit clone --depth 1 https://github.com/CloseTheLoops/moradinWrote 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.
[](https://agentmods.dev/skills/closetheloops/moradin/audit)<a href="https://agentmods.dev/skills/closetheloops/moradin/audit"><img src="https://agentmods.dev/badge/skills/closetheloops/moradin/audit.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00027 | $0.00423 |
| Opus 5 | $0.00014 | $0.00211 |
| Sonnet 5 | $0.00005 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
moradin-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 4d 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
moradin:audit
Run a health check on Moradin's memory and report issues.
When invoked
/moradin:audit
Typically run weekly, or before a publish, or when something feels off.
What you do
-
Run the audit script:
python scripts/audit.py --format json -
Categorize issues by severity (error/warn/info):
- ERROR: missing required frontmatter fields
- WARN: unknown topic tags, orphan files (not in _INDEX)
- INFO: stale files (unchanged > 180 days)
-
Group issues by file and by type.
-
For each issue, propose a concrete fix. Don't just report — recommend action:
- Missing
applies_tofield → "Addapplies_to: [universal]to frontmatter" - Unknown topic
cargo→ "Either rename to one of [harness, memory, ...] or justify adding cargo to taxonomy" - Orphan file → "Run
python scripts/refresh_indexes.pyto relink" - Stale file → "Decide: still applies? Add
last_verified: <today>to keep, or marksuperseded_by: <new>to retire"
- Missing
-
Don't auto-fix. Audit reports + proposes. Operator approves each fix.
-
Summary report: count by severity, top 3 files needing attention.
Output
- A human-readable report with concrete fix proposals
- Operator-approved fixes get applied one by one (Edit, refresh_indexes.py)
Don't
- Don't auto-delete stale files. Stale ≠ wrong — operator decides.
- Don't add
superseded_bymarkers without operator approval. - Don't reformat all frontmatter at once — touch only files with reported issues.
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.
- 4d ago First seen · 50 lines · 27 tokens per session scan A ae28c96a656f
moradin-audit is a skill published in the GitHub repository CloseTheLoops/moradin (2 stars, last pushed 25d ago), licensed MIT. It adds 27 tokens to every session and 423 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.
Other skills, from other repositories
llm-wiki-company-flow-audit
Map company/team information flows into an LLM-Wiki adoption plan. Use when the user asks where team knowledge lives, which streams can be automated, how Confluence/Jira/Slack/Drive changes stay synced, how fragile review is, how confidential data is handled, or whether maintenance cost is worth the benefit.
llm-wiki-capture-pipeline
Design cross-channel capture architecture and named connector runbooks for LLM-Wiki. Use when the user wants an inbox/raw topology, metadata contract, dedupe boundary, triage handoff, privacy defaults, capture-to-ingestion flow, or Telegram/email/Slack/PDF/GitHub/voice connector rules.
llm-wiki-orient
Explain the LLM-Wiki pattern, its raw/wiki/schema architecture, how it differs from RAG, GraphRAG and agent memory, and what ready-made solution families exist. Use when the user asks what LLM-Wiki is, whether it is worth adopting, what OpenWiki/wiki memory means, or how the ecosystem fits together.
llm-wiki-zero-to-working-wiki
Create a first useful LLM-Wiki from zero. Use when the user wants a zero-to-working-wiki walkthrough, first vault, first source ingest, first reusable query, first lint report, or a visible demo loop before a larger rollout; route full workflow installs to llm-wiki-setup.
wiki-lint
Run structural and trust health checks for an LLM-Wiki vault. Use for broken links, orphan pages, missing provenance, stale claims, contradiction reports, taxonomy drift, protected-section edits, and review queue generation.
llm-wiki-agent-memory-bridge
Decide what belongs in LLM-Wiki versus agent memory, AGENTS.md, CLAUDE.md, Auto Memory, Codex project memory, or other runtime memories. Use when instruction files are bloated, domain facts live in agent memory, or the user wants clean memory boundaries.