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 jzhao234/big-brain --skill braingit clone --depth 1 https://github.com/jzhao234/big-brainWrote 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/jzhao234/big-brain/brain)<a href="https://agentmods.dev/skills/jzhao234/big-brain/brain"><img src="https://agentmods.dev/badge/skills/jzhao234/big-brain/brain/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/jzhao234/big-brain/brain"><img src="https://agentmods.dev/badge/skills/jzhao234/big-brain/brain.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 | $0.00087 | $0.00536 |
| Opus 5.5 | $0.00035 | $0.00214 |
| Sonnet 5.5 | $0.00017 | $0.00107 |
| Haiku 4.5 | $0.00009 | $0.00054 |
Grade A, and why
brain 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 7d 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.
What it actually says
brain
The big-brain vault is the user's external memory, shared by all their AI tools. This skill loads it and switches you into brain-aware mode. The vault is whichever one big-brain resolves using the BIG_BRAIN_VAULT env var, a --vault path, or the nearest brain.config.json. Use the big-brain CLI or the big-brain MCP tools; don't hardcode a vault path.
With no argument
- Run
big-brain status(or call thebrain_overviewMCP tool). - Report in one screen, BLUF: active projects with their next task, anything overdue or due this week, inbox count if it's piling up. No filler; skip empty sections.
- If the vault hasn't been linted recently, run
big-brain doctorand surface only warnings.
With an argument
Treat it as a project or topic: big-brain show <arg> (falling back to big-brain search <arg>), then summarize where it stands (goal, status, open tasks, last Log entries) and ask what to work on.
Brain-aware mode (rest of the session)
From here on, keep the vault current as a side effect of the work:
- Decisions, progress, and problems →
big-brain daily --log "..."and a Log line on the affected project. - New commitments → project notes; new action items →
big-brain task add. - Completed work →
big-brain task done <id>. - Facts worth keeping with no obvious home →
big-brain capture "...".
Do routine captures/logs without asking (mention them in one line); ask before rewriting or archiving existing notes. If the vault has git auto-commit enabled, these saves also commit and push on their own. At the end of a work session, make sure what happened is reflected in the vault. The next session (or another LLM) starts from there.
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.
- 7d ago Changed 08eceb387501
- 1mo ago First seen · 36 lines · 87 tokens per session scan A ae34bb3ff01f
brain is a skill published in the GitHub repository jzhao234/big-brain (1 stars, last pushed 6d ago), licensed MIT. It adds 87 tokens to every session and 536 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
wrap-session-up
End-of-session review for a Claude Code conversation. Replays what was discussed, checks for open action items, documents relevant outcomes in the brain vault, and creates Todoist tasks for anything untracked. Use at the end of a work session to ensure nothing falls through the cracks.
vault-onboarding-guide
An interactive guide for learning a file-based knowledge store with an agent. It teaches how to organize incoming material, projects, plans, tasks, logs, parked work, and resumed work.
obsidian-ai-setup
Bootstrap an Obsidian vault with the AI Pro Obsidian Plugin. Creates the complete vault structure, system files, Obsidian configuration, memory system, hooks, and output styles, then runs personalized onboarding to tailor the workspace to the user. Uses a single universal structure with no mode selection. Trigger when…
molio-kb
Query the user's local Molio knowledge base — browse files, full-text search, read documents, and run AI Q&A grounded in the user's own notes (read-only).
priority-dashboard
Use this to rebuild, inspect, or temporarily steer {{username}}'s current PersonalOS priority dashboard from canonical Actions, Attention Triggers, and owner context. Do NOT use it to create, complete, or independently manage tasks; use task-manager for Action and Trigger lifecycle changes.
screenpipe-api
Query the user's local and synced-device data via the screenpipe REST API at localhost:3030 — recordings, audio, UI, meetings, connected services, and memory. Use for screen activity, other-device or cross-device history, productivity, media export, connections, durable memory, or discovering and automating saved…