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 skills add letrplB/second-brain --skill learngit clone --depth 1 https://github.com/letrplB/second-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/skills/letrplb/second-brain/learn)<a href="https://agentmods.dev/skills/letrplb/second-brain/learn"><img src="https://agentmods.dev/badge/skills/letrplb/second-brain/learn/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/letrplb/second-brain/learn"><img src="https://agentmods.dev/badge/skills/letrplb/second-brain/learn.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00038 | $0.01102 |
| Opus 5.5 | $0.00015 | $0.00441 |
| Sonnet 5.5 | $0.00008 | $0.00220 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
learn 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/learn
Intent. End-to-end ingestion. The user-facing composite for "learn this source properly."
What it does (default mode)
Sequential, all inline:
/extract <source>. Atomic claim notes written tonotes/claims/. Paper note created innotes/papers/.- For each new claim,
/connect <claim>. Sequential pass. Forward + backward links + MOC membership. - For each new claim,
/audit <claim>(quick mode). Schema + link check. Skip cold-read in this loop. - Move source. From
inbox/<source>toarchive/<YYYY-MM-DD>-<source-slug>/<source>. Untouched copy preserved. - Print summary. Claims created, links added, MOCs touched, audit issues, archive path.
If extraction returns 0 claims, stop after step 1 and report.
Deep mode (--deep)
For papers and other dense sources where parallelism helps and the model genuinely needs full audit including cold-read.
/extract <source>. Same as above — inline; the lead does extraction.- Spawn one subagent per new claim. Each subagent does:
/connect <its-claim>(full forward + backward + MOC)/audit <its-claim> --mode=full(schema + link + cold-read) Each subagent is fresh-context for its own claim. One claim, one subagent, end-to-end — not one subagent per phase.
- Lead waits for all subagents. Collects their summaries.
- Cross-connect pass (lead, inline). Walk the new claim set; for each claim, check whether it should link to another new claim whose note didn't exist when its sibling's connect ran. Add missed sibling links.
- Move source, print summary.
Subagent count cap: N (claims) × 1. Hard cap of 16 concurrent (Task tool platform limit). If extraction returned >16 claims, queue: spawn first 16, wait for all, then spawn next batch.
When to use which mode
| Source class | Mode |
|---|---|
| Tweet, single-paragraph note | default. Often 0–1 claim; sequential is fine. |
| Blog essay (≤2K words) | default. 3–8 claims; sequential takes < a minute. |
| Long essay / chapter (~3–8K words) | default unless user wants thorough audit. |
| Paper (peer-reviewed, dense) | --deep recommended. |
| Anything where the user said "thorough" or "deep" | --deep. |
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.
- 1mo ago First seen · 98 lines · 38 tokens per session scan A 6f313e52c976
learn is a skill published in the GitHub repository letrplB/second-brain (1 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 1,102 once invoked, about $0.0002 per session on Opus 5.5. 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
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.
curate
Power-user audit of Wenlan's pending surfaces: accept or dismiss pending revisions (conflicts/merges), or audit pending captures (not yet confirmed). Most users want /brief for revisions; that handles the daily flow. Use /wenlan curate only for explicit deep-walk audits after bulk imports, or to walk the full queue…
pages
Browse, open, or print distilled pages, reusing the wenlan pages CLI for the actual open (one implementation on your PATH, no setup). /wenlan pages opens the page when one matches, or shows a small native picker when 2-4 match. /wenlan pages --print reads the page here instead of opening an editor. /wenlan pages lists…
forget
Delete a memory from Wenlan by ID. Destructive and cannot be undone — prefer /capture with supersedes for corrections. Invoked as /wenlan forget .
llm-wiki
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate…
raytsystem-save
Stage a cited synthesis as a typed raytsystem DRAFT bundle and escaped preview. Use for SAVE, preserving a verified query answer, preparing a knowledge proposal, or creating a reviewable draft; never treat SAVE as canonical promotion or publication.