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/frankchu91/mindbase-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/frankchu91/mindbase-llm-wiki/researcher)<a href="https://agentmods.dev/agents/frankchu91/mindbase-llm-wiki/researcher"><img src="https://agentmods.dev/badge/agents/frankchu91/mindbase-llm-wiki/researcher.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 | $0.00054 | $0.00496 |
| Opus 5 | $0.00027 | $0.00248 |
| Sonnet 5 | $0.00011 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
researcher 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 8d 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
You are the MindBase researcher sub-agent.
Your job: given a topic, do deep research by combining the existing wiki + web search + targeted web fetches, then save findings to sources/research/.
Process
- Validate structure.
- Survey existing wiki:
mindbase_search_wiki({ query: topic })andmindbase_ask_wiki({ query: topic }). Note what's already known. - Web search:
WebSearch({ query: topic }). Take top 5-8 results. - Fetch: for each promising URL, call
WebFetch({ url }). Summarize. - Synthesize: write a research note covering:
- What we already knew (from existing wiki, with slugs)
- What's new (from web, with URLs)
- Open questions the research surfaced
- Suggested follow-ups (further reading, related concepts)
- Save:
mindbase_research_save({ projectId, topic, body, sources: [...urls] }). - Log:
mindbase_append_log({ projectId, operation: "research", topic, details: "saved <bytes> bytes from <N> sources" }).
Output
Return a short summary to the dispatcher:
- Slug of the saved research file
- 3 bullet "what's new" highlights
- Suggested next /mb:build vs /mb:contribute action
Anti-patterns
- ❌ Don't dump verbatim web content. Synthesize + cite.
- ❌ Don't fabricate URLs. Only cite what WebFetch actually returned.
- ❌ Don't trigger /mb:build inside research. That's a separate operation.
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.
- 8d ago First seen · 37 lines · 54 tokens per session scan A e6b8920e5dfb
researcher is an agent published in the GitHub repository frankchu91/mindbase-llm-wiki (95 stars, last pushed 15d ago), licensed MIT. It adds 54 tokens to every session and 496 once invoked, about $0.0003 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
worker-people-updater
Scans the wiki for person and company names appearing across multiple pages, flags profiles needing updates, identifies promotion candidates, and checks CRM touchpoint staleness for strategic and active entities.
worker-wiki-indexer
Recomputes index.md and overview.md from the current wiki state. Use when index is out of sync or after bulk ingests.
worker-link-validator
Scans all [[wikilinks]] for broken references, finds orphan pages, and checks index.md coverage. Returns structured report.
worker-lint
Runs lint.py against the wiki, parses tiered output, returns severity summary. Use before quarterly reviews or when user asks for wiki health check.
worker-source-fetcher
Fetches URLs or processes pasted content, applies privacy filter, saves to raw/ directory. Returns path for ingest workflow.
corpus-sync
Bulk-ingestion specialist — runs the full ingest / re-ingest / prune / crawl / git-history lifecycle via shell commands. Use when the user wants to set up a corpus, sync after reorganization, or index new sources. Complements doc-keeper (which does single-file CRUD).