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/jim4226/claude-workspace-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/commands/jim4226/claude-workspace-brain/brain)<a href="https://agentmods.dev/commands/jim4226/claude-workspace-brain/brain"><img src="https://agentmods.dev/badge/commands/jim4226/claude-workspace-brain/brain.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00185 |
| Opus 5 | $0.00007 | $0.00093 |
| Sonnet 5 | $0.00003 | $0.00037 |
| Haiku 4.5 | $0.00001 | $0.00018 |
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
Read WORKSPACE_BRAIN.md at the project root, then:
-
Summarise it back to me in ~10 lines: current focus, top 3 active threads, most recent decision, any open questions. Note any sections that look stale (no edits in >2 weeks) or overfull (>50 lines).
-
If I asked to update a specific section in my arguments, use the Edit tool to apply that change in place — never rewrite the whole file. Preserve the section structure and the inline HTML comments.
-
If I didn't ask for an edit, ask which section I want to touch and what the change is.
Do not invent content. If a section is empty, say so rather than filling it with plausible-looking text.
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 First seen · 20 lines · 14 tokens per session scan A 53e32ec87212
brain is a command published in the GitHub repository jim4226/claude-workspace-brain (1 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 185 once invoked, about $0.0001 per session on Opus 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 commands, from other repositories
load-session
Load a synced session summary for context.
capture
Model-driven lesson capture — read recent work in a role, distill genuine insights, append tagged bullets to pending.md. The real capture path; complements the Stop-hook's cheap regex fast-lane.
role-promote
Autonomously reconcile a role's memory — merge pending + recent learnings into ROLE.md, dedupe and declutter. The auto-promotion step fired when a role is stale (>7 days) with pending activity.
update-memory
Check and update CLAUDE.md memory based on changes to skills, commands, agents, and hooks.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
export-closedloop-learnings
Exports pending ClosedLoop learnings to global location with deduplication.