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 skills/togo-framework/cabrain-cli/memory-firstnpx skills add togo-framework/cabrain-cli --skill memory-firstgit clone --depth 1 https://github.com/togo-framework/cabrain-cliWhat 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 | $0.00056 | $0.00560 |
| Opus 5 | $0.00028 | $0.00280 |
| Sonnet 5 | $0.00011 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
memory-first 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 yesterday.
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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory-first
You have a CaBrain brain available through MCP tools. Treat it as your source of truth. The loop, every turn: recall → answer/act → retain.
1. Recall BEFORE you answer or act
For any question or task touching durable knowledge (a person, project, venture, issue, decision, learning, or a "who/what/why"), call memory_recall first — even if you think you already know. Before writing/planning/drafting on a topic, recall its context so you build on what's known.
- Query style: concise and keyword-forward (
"Sentra","PDPL kit","auth gate learning") — these rank cleaner than full sentences. - If the first query is thin, try another phrasing, or recall a second brain and merge. Use
brain_listif you're unsure which brain holds it.
2. Answer FROM what recall returns, and cite it
Base the answer on the recalled memories and point to the ones you used. If recall returns nothing relevant, say so plainly ("the brain has no memory of X") — do not invent facts to fill the gap. A truthful "not in the brain" is more valuable than a confident guess.
3. Retain what's new
After you produce something durable — a decision and its rationale ("chose X over Y because Z"), a correction, a learned constraint or gotcha, a new fact about a person/system, or an interface/contract detail — call memory_retain so the brain grows.
- Distill first: store a crisp, self-contained sentence or two. The write-decision de-dupes automatically, so a clean fact recalls far better than a raw dump.
- When unsure whether something is worth keeping, retain a short distilled line rather than nothing.
4. Prefer the brain over asking
If information is likely already in the brain, recall it instead of asking the user to repeat it. Only ask for what the brain genuinely lacks — then retain what you learn.
Namespaces
Pick the one brain that matches the question; don't mix scopes in a single query. Respect a session's default brain when one is configured (CABRAIN_DEFAULT_NAMESPACE). Recall more than one brain only when it's genuinely ambiguous, then merge.
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.
- yesterday First seen · 32 lines · 56 tokens per session scan A fc903cb570ba
memory-first is a skill published in the GitHub repository togo-framework/cabrain-cli (0 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 560 once invoked, about $0.0003 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 skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
a-evolve
Apply A-Evolve's agentic evolution methodology to improve AI agent performance across runs. Use when the user wants to diagnose agent failures, generate targeted skills from error patterns, evolve system prompts, or accumulate episodic knowledge. Works standalone or inside AutoResearchClaw pipelines. Triggers on…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.