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 jessepinkman9900/claude-second-brain --skill brain-searchgit clone --depth 1 https://github.com/jessepinkman9900/claude-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/jessepinkman9900/claude-second-brain/brain-search)<a href="https://agentmods.dev/skills/jessepinkman9900/claude-second-brain/brain-search"><img src="https://agentmods.dev/badge/skills/jessepinkman9900/claude-second-brain/brain-search/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/jessepinkman9900/claude-second-brain/brain-search"><img src="https://agentmods.dev/badge/skills/jessepinkman9900/claude-second-brain/brain-search.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 | $0.00063 | $0.00583 |
| Opus 5.5 | $0.00025 | $0.00233 |
| Sonnet 5.5 | $0.00013 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
brain-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Brain Search
Runs the 4-step query workflow defined in CLAUDE.md. Answers come with inline [[wiki/page]] citations — not a list of files.
Brain Discovery
All commands target the default brain registered in ~/.claude-second-brain/config.toml.
Resolve paths and run qmd via the claude-second-brain CLI — do not bake paths into this file:
BRAIN_PATH=$(npx -y claude-second-brain path) # absolute path to the default brain's directory
npx -y claude-second-brain qmd -- query -c wiki "<question>"
Pass --brain <name> before the -- to target a non-default brain.
Workflow
Step 1 — Search the wiki
- Run hybrid search:
npx -y claude-second-brain qmd -- query -c wiki "<question>" - Read
$BRAIN_PATH/wiki/index.mdto confirm coverage and catch any pages qmd didn't surface - Read the 2–5 most relevant pages in full before synthesizing (paths relative to
$BRAIN_PATH)
Step 2 — Synthesize an answer
- Write the answer with inline
[[wiki/page]]citations throughout - Be explicit about confidence: flag gaps with "The wiki doesn't have coverage on X."
- If relevant pages are sparse, say so — don't pad with speculation
Step 3 — Offer to file
- If the answer draws together multiple pages in a novel way, ask:
"This answer synthesizes several pages in a useful way — want me to file it as a Q&A page?"
- If yes:
- Create
$BRAIN_PATH/wiki/qa/[slug].mdwith frontmattertype: qa - Add to the Q&A section in
wiki/index.md - Add
[[wiki/qa/slug]]cross-links from the relevant topic pages
- Create
Step 4 — Log (if significant)
- For queries that reveal new understanding or surface a gap worth tracking, append to
$BRAIN_PATH/wiki/log.md:## [YYYY-MM-DD] query | Brief question summary Filed as: [[wiki/qa/slug]] (or "not filed") - Skip logging for routine lookups
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 · 51 lines · 63 tokens per session scan A e8dd200d6e7e
brain-search is a skill published in the GitHub repository jessepinkman9900/claude-second-brain (46 stars, last pushed 6mo ago), licensed MIT. It adds 63 tokens to every session and 583 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
knowit
Persistent, structured project memory for AI coding agents via the Knowit MCP server. Use before planning or editing code to load relevant rules, architecture, decisions, patterns, and conventions; use after finishing work to save durable learnings. Triggers on "remember this", "what are our conventions", "project…
debrief
Use at the end of a session (or midway through a long one) to deliberately capture what was learned — lessons, decisions, workflows, state changes, and facts — into the knowledge base. The nightly harvest is a safety net for lessons; unless the host opted into KBHARVESTFACTS, /debrief is the only thing that records…
kb-workflow
Use before starting any non-trivial task to search the knowledge base for context, and after completing work to capture findings. Teaches the token-efficient retrieval pattern and self-learning loop.
kmd-ingest
The write protocol for a markdown knowledge base (Obsidian-compatible, the LLM-wiki pattern) — personal or shared. Use for EVERY write into the KB — distilling a new or scraped source, promoting a finished artifact/report/lesson into the KB, filing a durable learning, insight, or query answer, or correcting/updating…
loredex-curate
Write a Start-Here brief for a project or a recent session's findings, and flag stale/duplicate/orphaned notes. Use when the user says "curate my dex/research", "where do I start", "make sense of this project", or just finished a session that produced several markdown files and wants a handoff.