second-brain CLAUDE.md

second-brain CLAUDE.md is an instructions file for coding agents from slowww-ai/second-brain. It costs 1,991 tokens per session, scanned A, original, MIT.

Repository instructions for a personal wiki, or “second brain,” built from captured Markdown files. They explain separate folders for raw material, edited notes, generated documents, and the databases used for links and semantic search.

In plain words
What is it for?
Use them when ingesting material, editing linked notes, generating briefs or other documents, rebuilding indexes, or searching the wiki.
Why use it?
They keep original captures safe while making it clear where notes, outputs, links, and search data belong.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/slowww-ai/second-brain/claude-md
Clone the repo
git clone --depth 1 https://github.com/slowww-ai/second-brain

Wrote 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.

agentmods badge for second-brain CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/slowww-ai/second-brain/claude-md.svg)](https://agentmods.dev/instructions/slowww-ai/second-brain/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/slowww-ai/second-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/slowww-ai/second-brain/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,991 This file is loaded in full into every session.
When invoked 1,991 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01991 $0.01991
Opus 5 $0.00996 $0.00996
Sonnet 5 $0.00398 $0.00398
Haiku 4.5 $0.00199 $0.00199

Measured 5d ago against content hash b63e5c627bd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

second-brain CLAUDE.md 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 5d 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.

CLAUDE.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Second Brain

A personal wiki built from raw captured markdown. Claude Code helps ingest, link, index, and synthesize.

Folder layout

  • wiki/raw/ — append-only dumps. Never edit or delete files here. Anything captured goes here first: clipped articles, meeting notes, transcripts, half-formed thoughts.
  • wiki/notes/ — the distilled wiki. Interlinked markdown notes derived from raw/. Safe to edit and rewrite.
  • wiki/outputs/ — generated deliverables (briefs, memos, docs, decks). Disposable.
  • scripts/ — Python helpers (ingest.py, reindex.py, search.py, dashboard.py).
  • wiki/lancedb/ — LanceDB vector store (table notes) holding Gemini embeddings. Used for semantic search.
  • wiki/index.db — SQLite side-table for links, ingested ledger, and note_meta (mtime tracking).

Storage split

The index is deliberately split across two stores. Vectors live in LanceDB (wiki/lancedb/) for on-disk ANN search without loading every embedding into memory. Graph and ledger metadata lives in SQLite (wiki/index.db): links (wikilink edges, rebuilt every reindex), ingested (raw-file ledger keyed by filename, with content hash + produced notes), and note_meta (per-note mtime for incremental reindex). When changing the schema in one store, check whether the other needs a matching change.

Semantic search uses the Gemini gemini-embedding-2-preview model via google-genai, stored in LanceDB for on-disk vector search (no loading all embeddings into memory). scripts/reindex.py only re-embeds notes whose mtime changed.

GEMINI_API_KEY is read from os.environ directly — the scripts do not auto-load .env. Either export the key in your shell, or run with:

set -a; source .env; set +a
python scripts/reindex.py

Slash commands

The workflow is driven by skill-backed slash commands:

Read the full file on GitHub · 138 lines

Changes

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.

  1. 5d ago First seen · 138 lines · 1,991 tokens per session scan A b63e5c627bd5

Subscribe to this mod's changes

second-brain CLAUDE.md is an instructions file published in the GitHub repository slowww-ai/second-brain (10 stars, last pushed 21d ago), licensed MIT. It adds 1,991 tokens to every session, about $0.0100 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.