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 instructions/hanshgoyal/second_brain/claude-mdgit clone --depth 1 https://github.com/HanshGoyal/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/instructions/hanshgoyal/second_brain/claude-md)<a href="https://agentmods.dev/instructions/hanshgoyal/second_brain/claude-md"><img src="https://agentmods.dev/badge/instructions/hanshgoyal/second_brain/claude-md.svg" alt="Measured on agentmods" 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 | $0.00880 | $0.00880 |
| Opus 5 | $0.00440 | $0.00440 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
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 4d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - LLM Wiki Agent Guide
This file provides guidance to LLM agents working with this wiki.
Project Overview
This is a hybrid LLM Wiki combining:
- Karpathy's LLM Wiki pattern - AI synthesizes and maintains knowledge
- Stephen Kanegan's Obsidian structure - organized folders and templates
Core Philosophy
- Raw sources in
raw/are immutable - never modify them - Wiki pages are AI-generated synthesis - LLM creates and maintains
- Human role: Add sources, ask questions, think about meaning
- LLM role: Do all the work - ingest, synthesize, cross-reference, maintain
Directory Structure
llm-wiki/
├── raw/ # Your sources - ADD FILES HERE
├── wiki/
│ ├── index.md # Catalog - check this first
│ ├── log.md # Activity history
│ ├── daily/ # Session notes
│ ├── templates/ # Page templates
│ ├── sources/ # Source summaries
│ ├── entities/ # People, places, organizations
│ ├── concepts/ # Topics, ideas, theories
│ ├── analyses/ # Answers to questions
│ └── comparisons/ # Comparison tables
└── schemas/
└── wiki-agent-guide.md # Detailed instructions (READ THIS)
Key Workflows
1. INGEST - Adding Sources
- User drops file in
raw/ - Read the source
- Create source page in
wiki/sources/ - Extract/update entities in
wiki/entities/ - Extract/update concepts in
wiki/concepts/ - Update
wiki/index.md - Append to
wiki/log.mdwith format:## [YYYY-MM-DD] ingest | Title - Create/update daily note in
wiki/daily/
2. ANSWER - Responding to Questions
- Read
wiki/index.mdto find relevant pages - Read those pages
- Synthesize answer
- File answer as new page in
wiki/analyses/(critical!) - Update index.md
- Append to log.md:
## [YYYY-MM-DD] query | Question summary
3. DAILY - Session Notes
At end of every session:
- Create
wiki/daily/YYYY-MM-DD.md - Document: learnings, questions, wiki updates, ideas
- Template in
wiki/templates/daily-template.md
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.
- 4d ago First seen · 121 lines · 880 tokens per session scan A 16781cd381fe
second_brain CLAUDE.md is an instructions file published in the GitHub repository HanshGoyal/second_brain (6 stars, last pushed 4mo ago), licensed MIT. It adds 880 tokens to every session, about $0.0044 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 instructions, from other repositories
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.