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 skills add yBookoff/thebrain-mcp --skill thebrain-researchgit clone --depth 1 https://github.com/yBookoff/thebrain-mcpWrote 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/skills/ybookoff/thebrain-mcp/thebrain-research)<a href="https://agentmods.dev/skills/ybookoff/thebrain-mcp/thebrain-research"><img src="https://agentmods.dev/badge/skills/ybookoff/thebrain-mcp/thebrain-research/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/skills/ybookoff/thebrain-mcp/thebrain-research"><img src="https://agentmods.dev/badge/skills/ybookoff/thebrain-mcp/thebrain-research.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 | $0.00110 | $0.00693 |
| Opus 5 | $0.00055 | $0.00347 |
| Sonnet 5 | $0.00022 | $0.00139 |
| Haiku 4.5 | $0.00011 | $0.00069 |
Grade A, and why
thebrain-research 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The brain as a source of knowledge
A brain holds what its owner has already worked out. Answering from general principles while their own conclusion sits right there throws away the main value.
When to look
Always, if the question touches a topic where the person may have accumulated something: their projects, decisions, research, observations. A redundant search is cheaper than a generic answer laid over a ready-made specific one.
Not needed for common-knowledge questions unrelated to their work.
How to search so that you find things
A single query is almost never enough. The ceiling for semantic search here is around 75–80% top-1 hits, and the misses are substantive ones.
Break the question into concepts and search for each, with variants:
brain_search { query: "<concept>", variants: ["synonym", "translation", "broader", "narrower"] }
Found a foothold? Look around it — the answer is often in the neighbours:
brain_get_thought { thoughtId: "<what you found>" } → note plus one hop of links
brain_traverse { thoughtId: "<what you found>", depth: 2 } → the whole area
If a search returns little, try other phrasings before concluding the brain has nothing. Absence of results is weak evidence.
How to answer
Separate what came from the brain from what is yours. The person needs to know which part is their own conclusion and which is general knowledge:
Your brain records that q8 quantization does not hurt ranking — with measurements over 48 thoughts. My own addition: on larger models the picture is usually the same.
Refer to thoughts by name so the person can find them.
Contradictions
If what you find in the brain disagrees with what you know, do not paper over it and do not silently substitute your version. Say it plainly: the brain records this, but there are grounds to think otherwise, and here is why.
The brain can also contradict itself — an old entry against a new one. Show both
and say which is more recent (brain_recent_changes, or dates in the notes).
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 · 77 lines · 110 tokens per session scan A 8432578e7edd
thebrain-research is a skill published in the GitHub repository yBookoff/thebrain-mcp (6 stars, last pushed 29d ago), licensed MIT. It adds 110 tokens to every session and 693 once invoked, about $0.0006 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 skills, from other repositories
refresh-context
A context snapshot updater for Core Context.md, a summary file built from nine main system files and selected essays. It refreshes that summary when the underlying material changes or the snapshot is more than 30 days old.
llm-wiki
Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management"…
llm-wiki
Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management"…
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
yopedia
Save research and reflections into (and recall from) your personal knowledge vault (yopedia) — your second brain.
lc-curate-context
Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…