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/recallgit 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/recall)<a href="https://agentmods.dev/commands/lanzelot1/claw-brain/recall"><img src="https://agentmods.dev/badge/commands/lanzelot1/claw-brain/recall.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 | $0.00007 | $0.00516 |
| Opus 5 | $0.00003 | $0.00258 |
| Sonnet 5 | $0.00001 | $0.00103 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
recall 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search across all knowledge areas and memory to find context relevant to the current task.
Steps
- Ask: "What are you about to work on?" (skip if the user already said)
- Read
memory/_index.mdto get the full knowledge map - Read
memory/me.mdfor personal context (if it exists) - Read
memory/lessons.mdfor past learnings (if it exists) - Search
knowledge/for files matching the task topic — check filenames and scan content. Check both source files and wiki pages. - Prioritize wiki pages — if a wiki page (
type: wiki) exists on the topic, surface it first (it's already a synthesis). Then list the underlying source files. - Follow links — For each matched file, scan its content for outbound markdown links (
](../pattern). Include linked files as "Related context" in the brief — one level deep only, don't follow links from linked files. - Present a brief:
- Relevant wiki pages found (with paths) — these give the best overview
- Relevant source files found (with paths)
- Applicable lessons from past sessions
- Any user preferences that apply
- Related context surfaced via cross-references (with paths)
- "Nothing found" sections are fine — don't pad
- Ask: "Want me to open any of these files?"
- After the task (if the conversation continues): Ask "Did this produce insights worth filing back? I can update an existing wiki page or create a new one." If yes, follow the
/synthesizeworkflow for the relevant content. - Log: Append to
memory/log.md:YYYY-MM-DD HH:MM | query | "{topic}" → {N} files surfaced
Git
Read-only for the recall itself — no changes, no branch, no PR.
If the user opts to file insights back (step 10), follow the /synthesize git workflow.
Rules
- Don't read every file — use the index and filenames to narrow down, then scan content of likely matches
- Keep the brief short — file paths + 1-sentence relevance, not full summaries
- If nothing relevant is found, just say so
- Step 10 is optional — don't push it if the user just wanted context
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 · 38 lines · 7 tokens per session scan A e82d470b1063
recall 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 516 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
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.