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-ingestgit 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-ingest)<a href="https://agentmods.dev/skills/ybookoff/thebrain-mcp/thebrain-ingest"><img src="https://agentmods.dev/badge/skills/ybookoff/thebrain-mcp/thebrain-ingest/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-ingest"><img src="https://agentmods.dev/badge/skills/ybookoff/thebrain-mcp/thebrain-ingest.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 | $0.00112 | $0.03719 |
| Opus 5.5 | $0.00045 | $0.01488 |
| Sonnet 5.5 | $0.00022 | $0.00744 |
| Haiku 4.5 | $0.00011 | $0.00372 |
Grade A, and why
thebrain-ingest 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breaking material down into TheBrain
The job is not "store the text" but graft meaning into the existing graph so that six months from now it can be found, and is already connected to whatever arrives later.
Fifteen thoughts dangling under a single article is a bad outcome, even if every one of them is accurate.
Order of work
1. Find out where you are landing
brain_list → which brain, is the index ready
brain_list_types_and_tags → the conventions this brain already uses
If the index is not ready, brain_search will say so. Tell the person — without
an index, finding existing material works worse and the risk of duplicates goes up.
2. Extract the concepts, then search for each one
Read the material and write out the concepts — what it is actually about. Then search for each of them:
brain_search { query: "<concept>", variants: ["synonym", "translation", "broader term"] }
Variants are mandatory. Without an index, search runs on them alone; with an index, they still raise recall.
If something close turns up, do not create a new thought. Extend the existing one and link to it. This is the whole difference between a second brain and a folder of files.
3. Look at the neighbourhood of your attachment points
brain_traverse { thoughtId: "<what you found>", depth: 2 }
This shows which area has already taken shape and what naming conventions hold there. Graft into the existing structure, not alongside it.
4. Assemble a plan and write it in one call
brain_ingest { thoughts: [...], links: [...] }
Do not create thoughts one at a time. Fifteen thoughts means fifteen calls plus links plus notes — minutes of work, and a failure halfway through.
Give the top thought of the plan a parent. Sent a second time, a plan finds
each thought next to its parent and creates nothing twice; a thought with no
parent it cannot find, and creates again with everything under it.
Send one plan at a time, and wait for its result before the next. Two
brain_ingest calls sent at once do not see each other's thoughts, and a
thought both of them name is created twice.
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 · +23 lines 60f006c1119e
- 15d ago Changed · +123 lines 5f13714d1427
- 1mo ago First seen · 170 lines · 112 tokens per session scan A 407f1acd5dda
thebrain-ingest is a skill published in the GitHub repository yBookoff/thebrain-mcp (8 stars, last pushed 14d ago), licensed MIT. It adds 112 tokens to every session and 3,719 once invoked, about $0.0004 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…