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 agentmods add commands/lanzelot1/claw-brain/onboardgit clone --depth 1 https://github.com/Lanzelot1/claw-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/lanzelot1/claw-brain/onboard)<a href="https://agentmods.dev/commands/lanzelot1/claw-brain/onboard"><img src="https://agentmods.dev/badge/commands/lanzelot1/claw-brain/onboard.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 | $0.00013 | $0.00410 |
| Opus 5 | $0.00006 | $0.00205 |
| Sonnet 5 | $0.00003 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
onboard 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 4d 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're onboarding a new user to this brain. Your goal is to create their personal profile at memory/me.md.
Have a natural conversation — don't dump all questions at once. Ask 2-3 at a time, respond to their answers, then ask more.
What to learn
- Name and role/context — Who are they and what do they do?
- Writing style — How do they communicate? Formal/casual? Direct/diplomatic? Any phrases or patterns they prefer?
- Language preferences — Which language for what context? (e.g. German for customer comms, English for technical)
- Current priorities — What are they focused on right now?
- Anything else they want Claude to know about how they work
- Agent role — Are they the orchestrator (main agent, commits to main), a repo-agent (works on branches + PRs), or external? See
memory/roles.mdfor role definitions.
After the conversation
Write the profile to memory/me.md with all gathered information, including their agent role. Keep it concise and useful — this file is read before every task.
Also check
If CLAUDE.md still has placeholder values in the About section ([What this brain is for], [Team, company, or personal use]), ask the user if they want to fill those in too. If yes, update CLAUDE.md as well.
Git
memory/me.mdis gitignored — no branch or PR needed for it- If
CLAUDE.mdwas also updated: commit on a branch and open a PR
Important
memory/me.mdis gitignored — it's personal and never committed- Be conversational, not robotic. This should feel like a quick onboarding chat.
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.
- 4d ago First seen · 35 lines · 13 tokens per session scan A a1cf5bb5f487
onboard is a command published in the GitHub repository Lanzelot1/claw-brain (11 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 410 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 2026-08-30.
Other commands, from other repositories
tech-debt
Run bun run check:fix and then bunx knip and identify unused files and functions to refactor the project and simplify. Look at the deprecated features and confirm with the user to delete them. Look at the dependencies and remove the ones that are not needed based on knip results.
memory-forget
Command "memory-forget" from waittim/MemoryCustodian, covering memory-forget and review the preview, then apply its plan id.
speckit.archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.
ingest
Route a new artifact into the brain. Four shapes, one verb.
refresh-context
Re-snapshot Core Context.md from (optional) mothership system files + key personal essays. Run when mothership files change, when new essays signal philosophy shift, or when snapshot is older than 30 days.
memory
Browse, search, and manage your saved technique library.