Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add toroleapinc/claude-brain/plugin install claude-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/toroleapinc/claude-brain/brain-evolve)<a href="https://agentmods.dev/skills/toroleapinc/claude-brain/brain-evolve"><img src="https://agentmods.dev/badge/skills/toroleapinc/claude-brain/brain-evolve.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 | $0.00030 | $0.00344 |
| Opus 5 | $0.00015 | $0.00172 |
| Sonnet 5 | $0.00006 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
brain-evolve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
The user wants to evolve their brain by promoting stable patterns from memory.
Steps
-
Run the evolution analysis:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/evolve.sh" -
Read the analysis results from
~/.claude/brain-repo/meta/last-evolve.json. -
For each recommendation in
promotions, present it to the user:For claude_md promotions:
- Show the proposed addition
- Show the reason
- Ask: Accept / Skip / Edit first
- If accepted, append to ~/.claude/CLAUDE.md
For rule promotions:
- Show the proposed rule content
- Ask: Accept / Skip / Edit first
- If accepted, write to ~/.claude/rules/.md
For skill suggestions:
- Show the proposed skill
- Ask: Accept / Skip / Edit first
- If accepted, create in ~/.claude/skills//SKILL.md
-
For each entry in
stale_entries, ask:- Archive (remove from memory) / Keep
- If archived, note in the memory file that it was archived
-
After all changes are applied:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/push.sh" -
Show summary: "Brain evolved: X promotions accepted, Y stale entries archived."
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.
- 6d ago First seen · 46 lines · 30 tokens per session scan A 4d9ee1f1ed8e
brain-evolve is a skill published in the GitHub repository toroleapinc/claude-brain (85 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 344 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:capture-context
Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…