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 mindmuxai/brain.md --skill brain-pagegit clone --depth 1 https://github.com/mindmuxai/brain.mdWrote 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/mindmuxai/brain.md/brain-page)<a href="https://agentmods.dev/skills/mindmuxai/brain.md/brain-page"><img src="https://agentmods.dev/badge/skills/mindmuxai/brain.md/brain-page/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/mindmuxai/brain.md/brain-page"><img src="https://agentmods.dev/badge/skills/mindmuxai/brain.md/brain-page.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00047 | $0.02391 |
| Opus 5.5 | $0.00019 | $0.00956 |
| Sonnet 5.5 | $0.00009 | $0.00478 |
| Haiku 4.5 | $0.00005 | $0.00239 |
Grade A, and why
brain-page 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 today.
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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brain-page
This skill is the operating manual for working with a project's brain under the Open Project Brain Standard. The protocol overview lives in the project's root BRAIN.md; here we expand the category taxonomy and the exact command for every operation.
The model is simple: everything goes through the brain CLI.
- Read =
brainread subcommands (brain-dir/list-pages/read-page <id>/read-root <slug>) — location-independent, no need to know where the brain lives. - Write =
brainwrite subcommands. Every mutation (create / update / append / archive / tag / root-page rewrite / reindex) is correct-by-construction, so frontmatter can never be mis-shaped and a compiled_truth rewrite can never silently skip its timeline entry.
NEVER hand-edit any file under the brain directory. All reads and writes MUST go through the
brainCLI. Manual edits are unsupported and illegitimate. Correctness is guaranteed by construction inside the CLI — there is no validator, and nothing at the file layer can catch or undo a bad manual edit, so a hand edit silently breaks the brain's invariants. Always reach for abrainsubcommand instead of an editor.
Invoking the CLI
The CLI ships inside this skill bundle at bin/brain.mjs. It is zero-dependency Node (ESM) — run it directly:
node <this-skill-bundle>/bin/brain.mjs <subcommand> [flags]
Resolve <this-skill-bundle> to the directory this SKILL.md lives in. In the brain.md source repository itself that path is skills/brain-page/bin/brain.mjs; when the skill is installed globally it is wherever setup linked it (e.g. ~/.claude/skills/brain-page/bin/brain.mjs). Run all commands from the project root.
The CLI resolves the brain directory itself: it reads brainRoot from ./.mindmux/preferences.json when present (absolute or relative to the project root), otherwise falls back to ./brain. A missing file, broken JSON, or absent field all fall back silently. Run brain brain-dir to see the resolved directory and its source.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed 5cd0b0420d5e
- 1mo ago Changed · +19 lines cc9312c128bb
- 1mo ago First seen · 146 lines · 47 tokens per session scan A c4c78cd61750
brain-page is a skill published in the GitHub repository mindmuxai/brain.md (578 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 2,391 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
chain
Inject the 3 most recent session IDs for the current workspace into the prompt before Claude responds. Use when starting work and wanting recent session context.
using-memory
Persistent dual-layer memory engine with Notebook facts, curated RAG knowledge base, agent-driven knowledge graph, and general MCP helpers. Trigger proactively whenever user preferences, project conventions, technology stack choices, or architecture decisions are introduced, or when querying ingested documentation…
recall
Retrieve what LemonCrow already learned from your past sessions — semantic recall over indexed sessions, durable facts, and extracted lessons. Use for 'have we seen this before', 'what did we learn about X', 'what does LemonCrow remember', or /recall. Read-only; importing, indexing, and extraction run in the LemonCrow…
agent-context-crystallizer
Preserve high-signal work context with local checkpoints and session crystals using the agent-crystallize CLI. Use before compaction, handoff, session end, cross-agent transfer, after major decisions/findings/failures, or when the user asks to checkpoint, crystallize, preserve context, save open loops, or create a…
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
mnemon
Persistent graph-based memory. Recall context before responding, remember insights after. Each group has private memory; global memory is read-only.