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/newgit clone --depth 1 https://github.com/Lanzelot1/claw-brainWhat 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 | $0.00007 | $0.00474 |
| Opus 5 | $0.00003 | $0.00237 |
| Sonnet 5 | $0.00001 | $0.00095 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
new 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 3d 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 create a new area in the brain. An area is a knowledge domain (e.g. research, projects, notes, reading, health, recipes — anything).
Steps
- Ask: "What area do you want to create?" — Get a short name (lowercase, no spaces) and a one-line description.
- Ask: "What should be tracked in this area?" — Understand what kind of information goes here (e.g. reading list, project log, weekly notes, reference links).
- Create the knowledge file:
- Create
knowledge/{area}/folder - Write an initial
.mdfile (named after the primary concern, e.g.reading-list.md,log.md,notes.md) withsource:frontmatter and sections based on what they described - The
source:field should describe where the initial content came from (e.g."user input","onboarding") - Cross-reference: Search existing knowledge areas for related content. If found, suggest adding a
## Relatedsection in the new file with standard markdown links using[title](../other-area/file.md)format, and add reciprocal links in the related file(s)
- Create
- Update
memory/_index.md:- Add a new section header for the area
- Add a link to the main file with a 1-sentence description
- Add an entry under "Recently Added"
- Update
CLAUDE.md:- Add the new area to the Areas table (between the
<!-- Auto-updated by /new -->comment and the end of the table)
- Add the new area to the Areas table (between the
Git
After all file changes are done:
- Commit everything on a new branch (e.g.
add-{area}-area) - Push and open a PR titled "Add {area} area"
- Share the PR link with the user
Guidelines
- Keep area names lowercase, short, and descriptive
- The knowledge file should have useful section headers based on what the user described — not empty boilerplate
- If an area with that name already exists, tell the user and ask if they want to update it instead
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.
- 3d ago First seen · 35 lines · 7 tokens per session scan A a9a70aa451e7
new is a command published in the GitHub repository Lanzelot1/claw-brain (11 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 474 once invoked, about $0.0000 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
triage-pr
Triage a PR — classify, optionally fix, optionally enable auto-merge.
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.
commit-and-pr
Let's commit the changes. Run tests, typechecks, and format checks. Then commit, push, and create a pull request.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.