brain
Skill2 starsChanged 4 months agoApache-2.0View on GitHub
Search and analyze governed notes, decisions, runbooks, and conventions, returning a qmd:// citation for every supported claim. Use when checking what the brain has captured about architecture, infrastructure, decisions, or operating practices. Trigger with "/brain", "ask the brain", or "check my knowledge base".
25 other projects use a version of this.
Adopted by
Most recently taken up by
- jzhao234/big-braintheir own version, first seen Nov 8, 2026
- jonmagic/skillstheir own version, first seen Nov 8, 2026
- keli-wen/agy-stafftheir own version, first seen Nov 8, 2026
- Aiqbee/aiqbee-aitheir own version, first seen Nov 8, 2026
- SeanningTatum/brain-axitheir own version, first seen Nov 1, 2026
- sophonfinance-wq/finance-automation-portfoliotheir own version, first seen Nov 1, 2026
Used with
Projects with it also use research.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
NVIDIASkillresearch
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 4 projects that use this
Other versions25 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 25
- keli-wen/agy-staff★ 873same name
- H-mmer/pentest-agents★ 815same name
- Anantys-oss/koan★ 49same name
- sophonfinance-wq/finance-automation-portfolio★ 16same name
- henriquecaner/brain-agent★ 13same name
- Aiqbee/aiqbee-ai★ 7same name
- jonmagic/skills★ 6same name
- tonydzi/second-brain-starter-kit★ 6same name
- aidemd-mcp/server★ 4same name
- gufranco/claude-engineering-rules★ 3same name
15 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brain-saveSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 6 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 20 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Ask your knowledge brain a question and get an answer grounded in your governed corpus, where every claim carries a qmd:// citation.
- Very specific: line 66
Call brain_search with those keywords and scope: "curated" (default promoted knowledge).
- Distinctive: line 77
Keyword retry (curated): only if the first call was still a long natural-language sentence (you skipped deriving 1–4 keywords).
- Very specific: line 80
Scope retry (
all): if curated is still empty, re-run the same keywords with scope: "all". - Distinctive: line 82
Only after curated+keywords and all+keywords are empty → Step 3 (honest refuse).
- Distinctive: line 95
If two hits conflict, surface both with their citations rather than silently picking one — the governance layer tracks contradictions.
- Very specific: line 102
If results is still empty after the empty-result ladder in Step 1, say so plainly: the brain has nothing governed on that topic.
- Very specific: line 146
Read-only. This skill never writes to the corpus — capture and governance live in /brain-save.
- Very specific: line 148
Never invent a qmd:// URI.
- Distinctive: line 149
Prefer fewer, well-cited claims over a broad answer that cannot be anchored.
- Distinctive: line 150
Do not conflate this product with IRSB / Moat / Scout (separate stack).
“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Brain — cited answers from your governed knowledge base
Ask your knowledge brain a question and get an answer grounded in your governed corpus, where every claim carries a qmd:// citation. The brain does not paraphrase from memory — it retrieves governed memories and cites them, so any answer is verifiable after the fact.
Overview
This is the read surface of Bob's Big Brain: your files are compiled into
governed memories, governed by deterministic code, and retrieved with citations
through qmd BM25, native FTS5 and configured dense retrieval. The brain_search MCP tool fronts that retrieval. Your product
surround is INTKB govern + ICO compile + this plugin — not a fork of qmd.
The job here is to turn a natural-language question into a cited answer — and to refuse to answer beyond what the citations support.
Prerequisites
- The bobs-big-brain / governed-brain plugin is installed (MCP
governed-brain). - Mode is automatic. In local mode (default) search runs in-process
against your local
~/.teamkbindex — no remote brain service or API key; a compatible qmd binary must be available (prefer monorepo pin@tobilu/qmdvia the Registrar / installer). Operators can usescripts/bbb-qmdfrom bobs-big-brain-registrar so XDG points at the team index, not personal~/.cache/qmd. In team mode (TEAMKB_API_URLset) search proxies to the team brain. Every hit is aqmd://citation. - See the runtime contract for exact inputs, result shapes, authentication, and mode-specific failures.
Instructions
Step 1: Search the governed corpus
The source entrypoints at the Registrar revision in gsb.lock.json configure
Tobi's qmd BM25, native FTS5 and a
sqlite-vec dense arm, joined with reciprocal-rank fusion and a freshness/category rerank.
Dense is enabled by default in those entrypoints, but requires a built index and
the configured loopback query embedder; disabling it or an unavailable arm leaves
the lexical results. Team mode uses the deployed server's configuration.
Retrieval makes no query-time generative LLM call.
Short keyword queries are useful for the lexical arms and empty-result retry; the configured dense arm also accepts natural-language phrasing. A zero-hit query is not proof that the brain lacks the fact.
- Derive 1–4 distinctive nouns/verbs from the user question (drop what/why/how, articles, auxiliaries, prepositions).
- Call
brain_searchwith those keywords andscope: "curated"(default promoted knowledge).
brain_search({ query: "SOPS age secrets", scope: "curated" })The tool returns { source, results: [{ citation, snippet, score, collection }] }.
Each citation is a qmd://COLLECTION/FILENAME URI — the receipt for that hit.
Empty-result ladder (do not stop after one miss):
- Keyword retry (curated): only if the first call was still a long natural-language sentence (you skipped deriving 1–4 keywords). Re-run with 1–4 keywords only. Skip this step when the first query was already keyword-style — do not re-call with the same tokens.
- Scope retry (
all): if curated is still empty, re-run the same keywords withscope: "all". Do not useinbox/archivedunless the user asks. - Only after curated+keywords and all+keywords are empty → Step 3 (honest refuse).
brain_search({ query: "shipped week", scope: "curated" })
// if empty (keywords already used):
brain_search({ query: "shipped week", scope: "all" })Step 2: Answer ONLY from the cited results
- Synthesize a direct answer from the returned snippets.
- Attach the qmd:// citation to every claim, inline — for example:
The proxy reverse-proxies the API (qmd://kb-curated/system-map.md). - If two hits conflict, surface both with their citations rather than silently picking one — the governance layer tracks contradictions; do not paper over them.
- Do not add knowledge the citations do not support. Any reasoning beyond the corpus must be labeled clearly as inference, not the brain's answer.
Step 3: Handle an empty result honestly
If results is still empty after the empty-result ladder in Step 1, say so plainly: the brain
has nothing governed on that topic. Do not fall back to general knowledge and present it as the
brain's answer. Optionally note that the topic may need to be captured (run /brain-save).
Output
- A short, direct answer.
- Each load-bearing claim followed by its qmd:// citation.
- A closing Sources list of the distinct qmd:// URIs used.
Examples
Cited answer:
/brain what does my system map say about the proxy?
→ The proxy is the single ingress; it reverse-proxies each domain to its service
and must be reloaded, not restarted, after edits (qmd://kb-curated/system-map.md).
Sources:
- qmd://kb-curated/system-map.mdEmpty result (honest refusal):
/brain what is my refund policy?
→ The brain has nothing governed on a refund policy. I won't guess from general
knowledge. If this should be in your brain, capture it with /brain-save.Error Handling
| Situation | Response |
brain_search returns empty results | Run the empty-result ladder (keywords → scope all); only then refuse. Do not fabricate. |
qmd missing / index empty | Retrieval degrades to empty. Tell operator: install @tobilu/qmd, run INTKB pnpm search-canary -- --heal or bbb-qmd status. |
| MCP tool unavailable | Plugin not enabled; install/enable governed-second-brain (governed-brain MCP server). |
| User asks to write/capture | Out of scope here — direct them to /brain-save. |
Guardrails
- Read-only. This skill never writes to the corpus — capture and governance live in
/brain-save. - Never invent a qmd:// URI. Cite only URIs returned by
brain_search. - Prefer fewer, well-cited claims over a broad answer that cannot be anchored.
- Do not conflate this product with IRSB / Moat / Scout (separate stack).
- Provenance ≠ truth. Promotion receipts record each memory's capture channel (or
unattested) and an origin-token hash — that proves WHERE a capture came from, not that its content is true. An authenticated insider can still have saved poisoned content with a valid origin; weigh cited answers accordingly and rely on govern policy, human review, and supersession as the content-quality gates.
Resources
- Bob's Big Brain umbrella — stack map.
- bobs-big-brain-plugin — this plugin.
- bobs-big-brain-registrar — govern layer (Bob's Big Brain Registrar) +
bbb-qmd. - tobi/qmd (npm
@tobilu/qmd) — retrieve engine (OSS; the stack pins it rather than forking it). - bobs-big-brain-compiler — compile layer (Bob's Big Brain Compiler).
- The write counterpart: the
/brain-saveskill (governed capture).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

