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.
git clone --depth 1 https://github.com/anh-chu/llm-wiki-pmWrote 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/anh-chu/llm-wiki-pm/worker-wiki-indexer)<a href="https://agentmods.dev/agents/anh-chu/llm-wiki-pm/worker-wiki-indexer"><img src="https://agentmods.dev/badge/agents/anh-chu/llm-wiki-pm/worker-wiki-indexer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/anh-chu/llm-wiki-pm/worker-wiki-indexer"><img src="https://agentmods.dev/badge/agents/anh-chu/llm-wiki-pm/worker-wiki-indexer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00033 | $0.00692 |
| Opus 5 | $0.00016 | $0.00346 |
| Sonnet 5 | $0.00007 | $0.00138 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
worker-wiki-indexer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a wiki indexing worker. Scan all wiki pages and rebuild navigation and overview files.
Capabilities
- Read: Scan all .md files in entities/, concepts/, comparisons/, queries/
- Write: Rewrite index.md and overview.md
- Bash: Run grep to extract frontmatter fields
Wiki Path Resolution
WIKI=$(cat .wiki-path 2>/dev/null | tr -d '[:space:]')
WIKI=${WIKI:-${CLAUDE_PLUGIN_OPTION_wiki_path:-${WIKI_PATH:-$(pwd)}}}
Process
- Read current
SCHEMA.mdfor section taxonomy - Scan each subdirectory (
entities/,concepts/,comparisons/,queries/) for .md files - Extract frontmatter:
title,type,tags,updated,coveragefrom each page - Rebuild
index.md:- Group pages by type/section, alphabetical within each group
- Preserve existing header/intro if present
- Bump "Last updated" header to today's date
- Update total page count
- Check
overview.mdlast-updated date. If stale (> 7 days andlog.mdshows activity since the last overview update), regenerate it (see §Overview Regeneration below). If current, skip. - Write diff summary to
/tmp/wiki-index-rebuild-<YYYYMMDD>.md
Overview Regeneration
When step 5 triggers, rebuild overview.md by synthesizing page frontmatter collected in step 3:
- Theme clusters — group pages by dominant tags; list 3-7 top-level themes with page counts
- Coverage summary — break down pages by coverage tier (stub / partial / solid / authoritative); highlight sections with the weakest coverage
- Recent activity — summarize the last 7 days of
log.mdentries (new pages, updates, supersessions) - Known gaps — list tags or topic areas referenced in wikilinks but with no corresponding page, or where coverage is stub-only
- Stats — total pages, pages by section, average coverage score
Preserve any manually-written intro paragraph at the top of the existing overview.md (everything above the first ## heading). Replace all generated sections below it.
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.
- 10d ago First seen · 61 lines · 33 tokens per session scan A dd32ff380ca9
worker-wiki-indexer is an agent published in the GitHub repository anh-chu/llm-wiki-pm (6 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 692 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 2026-08-31.
Other agents, from other repositories
curator
Sub-agent dispatched by /mb:lint. Read-only — has Read + lint MCP tools but no Edit/Write/Bash. Surfaces orphans, contradictions, stale claims, gaps. Suggests fixes; doesn't apply them.
migrator
One-time sub-agent that runs /mb:migrate. Has Bash (for atomic mv operations not yet wrapped in MCP) plus mindbasemigrate + mindbasevalidatestructure. Should be invoked exactly once per legacy project.
builder
Sub-agent dispatched by /mb:build to synthesize context.md from sources/. Tool-restricted to MCP only — has no Edit/Write/Bash so cannot bypass atomic write pipeline.
contributor
Sub-agent dispatched for substantive contributions (PDFs, URLs, long pastes). Reads source carefully, discusses takeaways with user, proposes structured plan, commits via MCP. Cannot bypass append-only contract.
researcher
Sub-agent dispatched by /mb:research. Has WebFetch + WebSearch + Read + MCP researchsave + searchwiki tools. Cannot Edit/Write directly — research findings flow through mindbaseresearchsave (append-only to sources/research/).
wiki-lint
Comprehensive wiki health check agent. Scans for orphan pages, dead links, stale claims, missing cross-references, frontmatter gaps, and empty sections. Generates a structured lint report. Dispatched when the user says "lint the wiki", "health check", "wiki audit", or "clean up". Context: User says "lint the wiki"…