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/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/frankchu91/mindbase-llm-wiki/researcher"><img src="https://agentmods.dev/badge/agents/frankchu91/mindbase-llm-wiki/researcher.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 | $0.00054 | $0.00496 |
| Opus 5.5 | $0.00022 | $0.00198 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (135 stars, last pushed 7d ago), licensed MIT. It adds 54 tokens to every session and 496 once invoked, about $0.0002 per session on Opus 5.5. 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
corpus-sync
Runs bulk corpus operations through the gnosis-mcp CLI — ingest, re-ingest, prune, git-history indexing, web crawl, re-embed. Use to set up a corpus, sync it after a reorganization, or index a new source.
kmd-operator
The knowledge-base interface agent. Delegate to it for any KB work — answering questions from a markdown knowledge base (queries with citations), writing knowledge into it (ingesting sources, promoting artifacts/reports, filing learnings, correcting pages), or deciding where something belongs in the KB. Works with…
wiki-cartographer
High-altitude field synthesizer. Reads the compiled wiki/papers, wiki/concepts, and wiki/gaps trees and writes incremental updates to the field/ artifacts — shared assumptions, cross-paper tensions, topic saturation, and the problems.md candidate list — never touching ideas or novelty.
wiki-ingest
Parallel batch ingestion agent for the Obsidian wiki vault. Dispatched when multiple sources need to be ingested simultaneously. Processes one source fully (read, extract, file entities and concepts, update index) then reports what was created and updated. Use when the user says "ingest all", "batch ingest", or…
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.