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-organizegit 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-organize)<a href="https://agentmods.dev/skills/ybookoff/thebrain-mcp/thebrain-organize"><img src="https://agentmods.dev/badge/skills/ybookoff/thebrain-mcp/thebrain-organize/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-organize"><img src="https://agentmods.dev/badge/skills/ybookoff/thebrain-mcp/thebrain-organize.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 | $0.00085 | $0.01350 |
| Opus 5.5 | $0.00034 | $0.00540 |
| Sonnet 5.5 | $0.00017 | $0.00270 |
| Haiku 4.5 | $0.00009 | $0.00135 |
Grade A, and why
thebrain-organize 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 13d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tidying up a brain
A brain accumulates disorder quietly: duplicates born of different phrasings, orphan thoughts, stubs with no notes, two branches about the same thing under different names.
The governing rule: propose, do not act silently. The structure is authored, and what looks like a duplicate may be a deliberate distinction.
What to look for
Duplicates
Search for one concept through several phrasings and see whether different thoughts about the same thing come back:
brain_search { query: "<concept>", variants: ["synonym", "translation", "acronym"], limit: 20 }
A duplicate candidate is a pair of semantically close thoughts with different identifiers and overlapping notes. Before proposing a merge, read both in full: the difference may be substantive.
Orphans
Thoughts with no links get lost: traversal cannot reach them, only search can.
brain_recent_changes { limit: 200, identifiers: true }
identifiers: true adds a Thoughts section under the table: every thought the
rows name that is still there, once, as name — identifier. Without since the
rows cover the last seven days; give an earlier since to look further back.
Take the identifiers from that section and check each thought's neighbourhood:
brain_get_thought { thoughtId: "<identifier from the Thoughts section>" }
Empty in every link section means an orphan. Propose where to attach it, based on a search for something similar.
A thought the rows show as name (deleted) is gone, and is not in the section:
there is nothing to attach.
That holds for an ordinary thought only. A type or a tag is vocabulary, not a
thought that lost its place: nothing is meant to sit above it, and one that
nothing uses yet shows a heading and no sections at all, which is exactly what
an orphan looks like. Tell them apart by the mark that only a type or a tag
carries, [type] or [tag]: after the name in the rows of
brain_recent_changes, after the identifier in its Thoughts section and in
brain_get_thought. Leave a marked thought out of the hunt, and never propose a
parent for it. One that is in use lists its thoughts under Thoughts of this type or Thoughts with this tag; one that is not is unused vocabulary, worth at
most a line of its own in the report.
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.
- 13d ago Changed · +18 lines 7339044e59fd
- 15d ago Changed · +15 lines b404ef15a12c
- 1mo ago First seen · 110 lines · 85 tokens per session scan A 77b930811181
thebrain-organize is a skill published in the GitHub repository yBookoff/thebrain-mcp (8 stars, last pushed 14d ago), licensed MIT. It adds 85 tokens to every session and 1,350 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
setup
Set up memex with provisioned Postgres (RDS + pgvector), AGENTS.md injection, first import.
cold-start
Day-one data bootstrapping for a new brain. Sequences the highest-leverage data sources to go from empty brain to useful brain in one session. Uses the agent host's managed connectors for safe credential handling — the agent never holds raw API keys. Covers Gmail import, calendar sync, contacts seeding, X/Twitter…
maintain
Brain health checks: back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks. Use when asked to check brain health, run maintenance, or audit quality.
eiirp
Everything In Its Right Place. The universal post-work organizer. After any significant work session, EIIRP runs a 7-phase audit: (1) inventory every output, (2) walk the filing taxonomy to decide where each lands, (3) check ontology consistency against the brain's actual shape, (4) file enriched brain pages, (5)…
ingest
Route content to specialized ingestion skills. Detects input type and delegates.
schema-author
Evolve the brain's type taxonomy. Add page types, propose new ones from corpus scans, backfill frontmatter type on existing pages, audit taxonomy health. Triggers when an agent notices untyped pages, custom domains needing typed entities (researcher, contract, deposition), or wants to see what types the brain…