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/letrplb/second-brain/teachnpx skills add letrplB/second-brain --skill teachgit clone --depth 1 https://github.com/letrplB/second-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 | $0.00044 | $0.03690 |
| Opus 5 | $0.00022 | $0.01845 |
| Sonnet 5 | $0.00009 | $0.00738 |
| Haiku 4.5 | $0.00004 | $0.00369 |
Grade A, and why
teach 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/teach
Intent. Build the user's grip on a claim where /no-surrender revealed a gap. Socratic, not expository. Pedagogical sibling of /no-surrender: where /no-surrender measures, /teach constructs.
Critical architectural constraint: /teach does NOT write engagement values. The skill's allowed-tools list omits Edit and Write — the no-write contract is enforced at the tool level, not just by instruction. If you find yourself wanting to update a claim's engagement based on a productive-feeling teach session, that's exactly the surrender-blind state this system exists to prevent. Suggest /no-surrender to record. Never write yourself.
Read surrender-tracking-design.md §4.3 for the design rationale.
Gating — read every invocation, never cache
Step 1, always. Read vault/vault.yaml. Check surrender.enabled.
- If
surrender.enabledis missing,false, or anything other than literaltrue: print this and exit immediately:/teach is gated by surrender.enabled in vault.yaml. Set surrender.enabled: true to enable. - Do not proceed. Do not read claim files. The gate is the first action and the first thing to fail.
Re-read on every invocation — never assume it's still on from a prior call.
Target forms
Single argument forms (mutually exclusive):
| Form | Example | Behaviour |
|---|---|---|
[[wikilink]] |
/teach [[asymmetric-friction-...]] |
Resolve wikilink to file in notes/claims/ or notes/synthesis/; teach that one claim |
| Path | /teach notes/claims/some-claim.md |
Teach that one claim |
_<topic-map> |
/teach _knowledge-system-design |
Read MOC; pick weakest 3 claims (lowest aggregate engagement after decay), sequence by dependency, run sessions sequentially. User can /stop between claims. |
<concept-string> |
/teach how should the vault register surrender it absorbs |
Run /walk internally (or grep-fallback if qmd disabled). Pick top-3 results with aggregate engagement < 0.5. Offer a guided sequence. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 258 lines · 44 tokens per session scan A f5bb5cd6360b
teach is a skill published in the GitHub repository letrplB/second-brain (1 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 3,690 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 2026-08-31.
Other skills, from other repositories
capture-knowledge
将对话、项目文档、调试经验或用户指定材料沉淀到 Second Brain。用于“保存知识”“提取经验”“导入文档”“记录到知识库”“capture knowledge”等请求；先保存可追溯来源，再按一个稳定主题一张卡提取或更新 canonical 页面，禁止把 README、报告、故事或整段会话直接做成一张大卡。.
second-brain-learn
从当前 Agent 对话和工作轨迹中挖掘可长期保留的偏好、方法、Agent 角色事实、项目规则、知识与山脉进展；审计现有 owner，新增、纠错、缩限、替代、合并、迁移或退役规则，自动合并有证据的低风险变化，高风险变更先询问用户，并同步当前 Agent。用户说学习、记住、采纳或停止某种行为、修正规则、保存本次经验、从当前对话改进、运行 /learn，或要求未来 Agent 遵守某项教训时使用。.
scienceworld-circuit-builder
This skill constructs a simple electrical circuit by connecting components like batteries, wires, and light bulbs. Use when the agent needs to test electrical conductivity or create a functional circuit for an experiment. The input is a set of available components, and the output is a fully connected circuit ready for…
scienceworld-heating-apparatus-setup
This skill positions a container with a substance onto a heating device (stove, oven) and activates the device. It should be triggered when a task requires melting, boiling, or heating a substance. The skill moves the prepared container to the heating element and turns it on.
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
notebooklm-cli
Drives Google NotebookLM via the cli-web-notebooklm command-line tool — create and manage notebooks, add URL/text sources, ask questions grounded in the sources, and generate/download artifacts (audio overview, video, slide deck, mindmap, study guide, quiz, FAQ, briefing, infographic, data table). Use when the user…