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 agents/oshayr/llm-wiki/wiki-auditorgit clone --depth 1 https://github.com/Oshayr/LLM-WikiWrote 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/agents/oshayr/llm-wiki/wiki-auditor)<a href="https://agentmods.dev/agents/oshayr/llm-wiki/wiki-auditor"><img src="https://agentmods.dev/badge/agents/oshayr/llm-wiki/wiki-auditor.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 5.1 | $0.00034 | $0.00479 |
| Opus 5 | $0.00017 | $0.00239 |
| Sonnet 5 | $0.00007 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
wiki-auditor 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 6d 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
Audit and fix wiki structural issues. Resolve .wiki/ from plugin install scope.
Process
1. Scan All Pages
Read all .md files in .wiki/pages/. For each page, parse YAML frontmatter and body content.
2. Check Broken Links
Delegate backlink integrity to the backlink-manager agent (full rebuild mode). Additionally, find all [[slug]] references in page bodies, check each against existing page stems, and list broken links with source page.
3. Fix Missing Frontmatter
Every page must have: title, type, confidence, created, updated. Add defaults for any missing fields:
- title: derive from filename (slug → Title Case)
- type:
concept(default) - confidence:
low - created/updated: file modification date
4. Find Orphans
Pages with zero incoming links from other pages. Report them — they may need connections or may be stale.
5. Detect Near-Duplicates
Compare all page slugs using Jaccard similarity on word tokens (split by -). Flag pairs with >60% overlap for potential merge.
6. Concept Auto-Generation
Find groups of 3+ pages that share common [[wiki-links]] targets. Suggest synthesis articles that connect these clusters.
7. Delegate Backlink Checks
Delegate backlink auditing to the backlink-manager agent for thorough reverse index maintenance and unlinked mention detection.
8. Remove Dead Index Entries
Read .wiki/index.md. Remove entries pointing to pages that no longer exist.
9. Fix Inline
Apply all fixes directly to the files. No separate report file. Print a summary of what was fixed.
Rules
- Fix structural issues silently (frontmatter, dead index entries)
- Flag but don't auto-merge duplicates (requires user review)
- Flag but don't auto-delete orphans (they may be valuable)
- Delegate backlink maintenance to backlink-manager agent
- Report: broken links fixed, frontmatter added, orphans found, duplicates flagged, concepts suggested
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.
- 6d ago First seen · 48 lines · 34 tokens per session scan A 29b36f2a1d99
wiki-auditor is an agent published in the GitHub repository Oshayr/LLM-Wiki (49 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 479 once invoked, about $0.0002 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.
Other agents, from other repositories
ia-learnings-researcher
Searches docs/solutions/ for relevant past solutions by frontmatter metadata. Use before implementing features or fixing problems to surface institutional knowledge and prevent repeated mistakes.
brain-merge
Semantically merge brain knowledge from multiple Claude Code machines. Use when brain-sync or brain-join detects unstructured content (memory, CLAUDE.md) that needs intelligent merging. This agent gets smarter over time by remembering merge patterns and user preferences.
ingest-confluence
Ingest one Confluence page into an AKB vault as a five-section LLM-wiki summary document, fetched live via the Atlassian MCP server.
ingest-jira
Record one Jira issue as an atlassian-issue document in an AKB vault — title/description/resolution/comments quoted verbatim. Fetched live via the Atlassian MCP server; always upsert.
ingest-pr
Record a single GitHub PR merge event as a git-pr document in an AKB vault — PR title/body quoted verbatim, commit summaries pulled from pre-ingested git-commit docs. Fetched live via gh pr view.
ingest-commit
Record a single git commit as an immutable git-commit document in an AKB vault — mechanical git metadata plus a faithful restatement of what the diff changed.