Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jim4226/claude-workspace-brainnpx agentmods add commands/jim4226/claude-workspace-brain/brain-gradeWrote 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-grade)<a href="https://agentmods.dev/commands/jim4226/claude-workspace-brain/brain-grade"><img src="https://agentmods.dev/badge/commands/jim4226/claude-workspace-brain/brain-grade/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/jim4226/claude-workspace-brain/brain-grade"><img src="https://agentmods.dev/badge/commands/jim4226/claude-workspace-brain/brain-grade.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 | $0.00011 | $0.00356 |
| Opus 5 | $0.00005 | $0.00178 |
| Sonnet 5 | $0.00002 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
brain-grade 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 9d 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
You are reviewing the brain file for quality. Do this:
Step 1 — run the static linter
python .claude/scripts/brain_lint.py WORKSPACE_BRAIN.md
Report the score and the top 3 findings verbatim.
Step 2 — read the brain and grade it on five axes (0-10 each)
Then read WORKSPACE_BRAIN.md yourself and grade:
- Freshness — When was each section last meaningfully updated? Stale threads at the top are worse than stale entries at the bottom.
- Signal-to-noise — Does every line carry weight, or is there filler that future-Claude will skim past?
- Specificity — Are decisions and threads concrete (named files, dates, owners), or vague ("improve UX", "fix the auth thing")?
- Reason coverage — Do decisions explain why (not just what)? A decision without a reason rots in two weeks.
- Section balance — Is one section dominating? Are required sections empty? Should anything be archived?
For each axis: score 0-10, one-line justification, one concrete suggestion.
Step 3 — propose specific edits
Pick the 1-3 highest-leverage edits (entries to remove, rewrite, or move to archive). Show the exact Edit-tool calls you'd make. Wait for my approval before applying any of them.
Step 4 — overall verdict
End with one line: Brain quality: <score>/100. <One-sentence recommendation>.
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.
- 9d ago First seen · 41 lines · 11 tokens per session scan A 25d4152cae1d
brain-grade is a command published in the GitHub repository jim4226/claude-workspace-brain (1 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 356 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.