What is agent-brain CLAUDE.md?

A personal context template for an agent, covering identity, work, goals, preferred technology, knowledge storage, and recurring workflows.

Use it to record personal and work context, set quarterly and yearly goals, define a technology stack, organize notes, and document commands such as morning briefings.

It gives the agent background about the person and project, so its work can follow the user's priorities and preferred tools.

agent-brain CLAUDE.md — Instructions file by Railly

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/railly/agent-brain/claude-md

Clone the repo

git clone --depth 1 https://github.com/Railly/agent-brain

Per session 815 This file is loaded in full into every session.

When invoked 815 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5	$0.00815	$0.00815
Opus 5	$0.00407	$0.00407
Sonnet 5	$0.00163	$0.00163
Haiku 4.5	$0.00081	$0.00081

Measured 2d ago against content hash f653788fbfe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 2d 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.

Origin

This is a copy

100% identical to agent-brain AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{Your Name}'s Brain

Identity

{Your name}. {Age}. {Location}. {Languages you speak}.

Work

{Primary Role}

{Your role}. {Company/project}. {What you're working on}.

{Secondary Role} (optional)

{Side project, freelance, open source}.

Goals

This Quarter

{Goal 1}
{Goal 2}
{Goal 3}

This Year

{Goal 1}
{Goal 2}

3-5 Years

{Vision statement}

Stack

Always Use

{Runtime}: {e.g., Bun, Node, Deno}
{Framework}: {e.g., Next.js, Astro}
{Database}: {e.g., Postgres, SQLite}
{Deploy}: {e.g., Vercel, Cloudflare}

Avoid

{Things you don't want the AI suggesting}

Knowledge System

Vault Structure

01_Inbox/           -> Raw captures (Web Clipper)
02_Journal/         -> Daily logs, weekly plans, reflections
03_Garden/          -> Evergreen atomic notes
04_Projects/        -> Active project work
05_Areas/           -> Ongoing life contexts
06_Content/         -> Ready-to-publish drafts
07_System/          -> System config and references

Full reference: 07_System/context-files/knowledge-system.md

Workflows

Command	Purpose
`/init`	Guided setup wizard for new users
`/morning`	Morning briefing: calendar, tasks, MITs
`/today`	Daily log + end-of-day reflection + tomorrow prep
`/log`	Quick timestamped entry to daily file
`/ship`	Commit + push + log to daily
`/week`	Weekly planning with MITs
`/inbox`	Process Web Clipper clips into atomic notes
`/relink`	Find missing connections between notes
`/vault-search`	Search vault by keyword and synthesize
`/meeting`	Process meeting notes or recordings (uses trx)
`/challenge`	Argue against your own thinking (anti-sycophancy)
`/pulse`	Weekly Pareto analysis + goal alignment
`/draft`	Create content drafts from ideas
`/de-ai`	Remove AI-generated jargon from text
`/research`	Web research saved to vault

Runtime Surfaces

.agents/skills/ is the canonical workflow source
.claude/skills/ exposes the workflows to Claude Code
.claude/commands/ preserves slash command compatibility

Read the full file on GitHub · 111 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.

2d ago First seen · 111 lines · 815 tokens per session scan A f653788fbfe0

Subscribe to this mod's changes

agent-brain CLAUDE.md is an instructions file published in the GitHub repository Railly/agent-brain (22 stars, last pushed 1mo ago), licensed MIT. It adds 815 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agent-brain AGENTS.md, differing in 0 lines, and is treated as a copy.

Memory and context

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

agent-brain CLAUDE.md