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/michaeljauk/brain-starter/claude-mdgit clone --depth 1 https://github.com/michaeljauk/brain-starterWrote 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/michaeljauk/brain-starter/claude-md)<a href="https://agentmods.dev/instructions/michaeljauk/brain-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/michaeljauk/brain-starter/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 | $0.00715 | $0.00715 |
| Opus 5 | $0.00358 | $0.00358 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
brain-starter 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brain Repo - Claude Instructions
Purpose
This repo is a personal second brain - reference docs, project notes, meeting notes, and knowledge. Your task manager (Todoist, Linear, etc.) is the task source of truth.
Not set up yet?
If this file still describes a generic vault, the fork has not been personalised. Run /kickoff.
It walks through identity, first project, semantic search, integrations, indexes, and the first
commit, and verifies each phase before moving on.
File Placement Rules
Directory Guide
| Directory | Content | Examples |
|---|---|---|
projects/ |
Project knowledge, one subdir per project | projects/my-saas/, projects/side-project/ |
research/ |
Non-project research, topic-grouped | research/ai-agents/, research/infrastructure/ |
knowledge/ |
Curated long-lived reference | knowledge/tools.md |
decisions/ |
Cross-cutting decisions with context + alternatives | YYYY-MM-DD-short-slug.md |
docs/ |
Repo meta, templates, skill output | templates.md, integrations.md |
meetings/ |
Meeting notes (read-only if managed by Granola or similar) | - |
sources/ |
Third-party reference material (gitignored) | - |
tasks/ |
Task manager sync (managed) | - |
tmp/ |
Truly ephemeral files with no project association | - |
archive/ |
Done/inactive projects | - |
What does NOT belong in this repo
- New project repos / codebases - keep those in their own repos
How to choose the right directory
- Project overview, working file, or anything project-specific? →
projects/{project}/ - Non-project research, analysis, or tool evaluation? →
research/{topic}/ - Curated reference material? →
knowledge/ - Non-trivial choice with alternatives? →
decisions/(cross-cutting only; project-specific go inprojects/{project}/decisions/) - Stable reference, convention, or template? →
docs/ - Output files (email drafts, PDFs, data files)? →
projects/{project}/outputs/ - Truly ephemeral, no project association? →
tmp/
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.
- 5d ago First seen · 59 lines · 715 tokens per session scan A a53143d3f2c6
brain-starter CLAUDE.md is an instructions file published in the GitHub repository michaeljauk/brain-starter (5 stars, last pushed 9d ago), licensed MIT. It adds 715 tokens to every session, about $0.0036 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
obsidian-pkm-plugin CLAUDE.md
Instructions for AdrianV101/obsidian-pkm-plugin, covering pkm: 01-projects/obsidian-mcp, claude.md, project overview, commands and install dependencies.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
obsidian-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/obsidian-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool — obsidianlisttags.
pi-llm-wiki AGENTS.md
AGENTS.md instructions for zosmaai/pi-llm-wiki, covering agents.md, project, tech stack, file layout and conventions.
vault-operator AGENTS.md
AGENTS.md instructions for pssah4/vault-operator, covering vault operator, projekt-regeln, navigation, zuerst lesen, projekt, tech stack and build und deploy.
third-brain-v7-skills CLAUDE.md
Instructions for Mark393295827/third-brain-v7-skills, covering third brain v8.1 skills — claude code, v8.1 multi-domain taxonomy specification, 20 core skills overview, 📥 knowledge pipeline and 🔄 daily loop.