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.
git clone --depth 1 https://github.com/brainOS-HQ/brain-osWrote 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/commands/brainos-hq/brain-os/brain)<a href="https://agentmods.dev/commands/brainos-hq/brain-os/brain"><img src="https://agentmods.dev/badge/commands/brainos-hq/brain-os/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/commands/brainos-hq/brain-os/brain"><img src="https://agentmods.dev/badge/commands/brainos-hq/brain-os/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 | $0.00000 | $0.01185 |
| Opus 5.5 | $0.00000 | $0.00474 |
| Sonnet 5.5 | $0.00000 | $0.00237 |
| Haiku 4.5 | $0.00000 | $0.00119 |
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 1mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brain OS : Project Scanner
Instant project intelligence. Where things are, what's stale, what decisions are pending, where to go next.
REQUIRED FIRST READ
Before any tool call, read ~/.claude/brain-os/PROTOCOL.md. It governs tool routing for every Brain OS skill. Pulse files are stale by design; MCP tools read the live .brain/ store.
Input
Arguments: $ARGUMENTS (format: <entity-name> or --resume). If no argument, show the master overview.
Resume mode (--resume)
When the argument is --resume (or contains --resume):
- Detect the current project slug from the working directory.
- Read the bookmark file at the user's Claude project memory path for
last-session-<slug>.md. If no project-specific one exists, trylast-session.md. - Extract the
**Transcript:**path from the bookmark. - Read the JSONL transcript and extract the last 15 user/assistant text exchanges (skip tool_use and tool_result blocks).
- Present a "Resuming from last session" block showing:
- When the session was saved
- The tail of the conversation (so the user can see what was discussed)
- THEN run the normal master overview (entity state + focus) to show current state on top of that context.
This ensures that even if /wrap wasn't run, the user gets their conversation context back plus live project state.
Primary tool sequence
With entity name:
mcp__brain-os__entity_read(entity_id): status, mode, momentum, blockers, decisionsmcp__brain-os__plan_read(entity_id): active step and progressmcp__brain-os__decision_check("scan", entity_id): surface any alerts
Without argument (master overview):
mcp__brain-os__entity_read(): all entities at oncemcp__brain-os__pattern_detect(): active patternsmcp__brain-os__focus_get(max_results=3): top priorities
Staleness rules
Calculate from each entity's last_updated:
- Fresh: 0 to 7 days
- Aging: 8 to 21 days
- Stale: 22 to 45 days
- Dormant: 45+ days
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.
- 1mo ago First seen · 131 lines · 0 tokens per session scan A 9040ce062d38
brain is a command published in the GitHub repository brainOS-HQ/brain-os (6 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,185 tokens. 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 commands, from other repositories
gsd-remove-phase
Remove a future phase from roadmap and renumber subsequent phases.
feature
Create a new feature via SDLC-based multi-agent collaboration.
slm-mesh
Cross-session peer coordination via the SLM mesh network. Lets multiple AI agent sessions on the same machine, and web apps the owner has allowed (ChatGPT, Claude on the web, Grok Bot, Muse, Composio), discover each other, send messages, wait for replies with meshwait, share lightweight state, and lock files to avoid…
slm-governance
Governed-workspace behavior for SuperLocalMemory. Covers roles (admin/member/viewer) and company mode, who administers a company-mode workspace (a signed-in admin, or slm team on the SLM computer), slm token show in strict mode, what remote web apps can never see or change, retention and lifecycle settings, the audit…
tree-ring-recall
Recall durable Tree Ring Memory context before starting or resuming work.
tree-ring-status
Check receipt-backed Tree Ring harness readiness without claiming configuration is activation.