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-digestgit 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-digest)<a href="https://agentmods.dev/skills/ybookoff/thebrain-mcp/thebrain-digest"><img src="https://agentmods.dev/badge/skills/ybookoff/thebrain-mcp/thebrain-digest/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-digest"><img src="https://agentmods.dev/badge/skills/ybookoff/thebrain-mcp/thebrain-digest.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 | $0.00094 | $0.00680 |
| Opus 5 | $0.00047 | $0.00340 |
| Sonnet 5 | $0.00019 | $0.00136 |
| Haiku 4.5 | $0.00009 | $0.00068 |
Grade A, and why
thebrain-digest 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A digest of the brain
The modification log is unreadable on its own: a hundred lines of "note changed". The job is to turn it into an account of what the person was doing.
How to gather it
brain_recent_changes { since: "2026-08-04T00:00:00Z", limit: 200 }
Without since it takes a week. The tool already decodes the numeric codes into
readable phrasings and resolves thought names.
Limit: names are resolved for at most sixty thoughts. Over a long period some lines will have no names — that is not lost data, it is saved requests. If you need a full breakdown, take a shorter period.
How to narrate it
Do not retell the log line by line. Group by theme and say what was going on.
Bad:
11 August 13:24 created — API layer
11 August 13:24 note created
11 August 13:24 created — Semantic layer
11 August 13:24 note created
Good:
The week was mostly the "Implementation" branch: four layers appeared
(API, semantics, operations, server), each with a note carrying measurements.
Separately, the tools area was extended: entries about brain_ingest and the
race condition found in it.
Old entries were revised: "Search indexing takes up to 15 seconds" was renamed
to "Writes are not immediately visible" — the earlier phrasing turned out to be
wrong.
To narrate like that, look at which thoughts changed:
brain_get_thought { thoughtId: "<from the log>" }
A few key ones are enough, not every single one.
What to pay attention to
- Edits to old entries. The person rethought something — more interesting than what is new.
- Bursts around one area. That is where real work was happening.
- Things created with no notes and no links — probably abandoned halfway. Worth mentioning.
- Deletions. If a noticeable amount was deleted, say what is gone.
What to propose at the end
One or two concrete suggestions, not a general "keep it up":
- something unfinished worth returning to;
- an area with a lot of new material that could use tidying (
thebrain-organize); - a question that the accumulated material begs.
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 · 87 lines · 94 tokens per session scan A b11016867b29
thebrain-digest is a skill published in the GitHub repository yBookoff/thebrain-mcp (6 stars, last pushed 29d ago), licensed MIT. It adds 94 tokens to every session and 680 once invoked, about $0.0005 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…