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 skills/railly/agent-brain/initnpx skills add Railly/agent-brain --skill initgit clone --depth 1 https://github.com/Railly/agent-brainWhat 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 | $0.00012 | $0.01516 |
| Opus 5 | $0.00006 | $0.00758 |
| Sonnet 5 | $0.00002 | $0.00303 |
| Haiku 4.5 | $0.00001 | $0.00152 |
Grade A, and why
init 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.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive setup wizard for your personal OS. Asks questions, builds your vault, generates your CLAUDE.md.
WAVE 0: Welcome
Print:
Welcome to your Personal OS.
I'll ask you a few questions to set everything up.
This takes about 2 minutes.
WAVE 1: Questions
Ask these directly, one at a time. Wait for each answer before asking the next.
- "What's your name and what do you do? (e.g. 'Sarah, frontend engineer at Stripe')"
- "What's your main stack? (e.g. 'TypeScript, React, Next.js, Tailwind, PostgreSQL')"
- "What are your top 3 goals right now? (career, learning, personal, anything)"
- "What's one recurring failure you keep repeating? Be honest, nobody reads this except your AI. (e.g. 'I start side projects and never finish them')"
- "Where should I create your vault? (default: ~/brain)"
Store all answers for WAVE 2.
WAVE 2: Create vault structure
Use the path from question 5 (default ~/brain).
Before writing, check whether the destination already contains CLAUDE.md, AGENTS.md, or 01_Inbox/. If it does, stop without changing it and direct the user to docs/MIGRATION-v2.md.
mkdir -p "{path}/01_Inbox/processed"
mkdir -p "{path}/02_Journal/daily"
mkdir -p "{path}/02_Journal/weekly"
mkdir -p "{path}/02_Journal/reflections"
mkdir -p "{path}/03_Garden/_MOCs"
mkdir -p "{path}/03_Garden/concepts"
mkdir -p "{path}/03_Garden/people"
mkdir -p "{path}/03_Garden/tools"
mkdir -p "{path}/03_Garden/meetings"
mkdir -p "{path}/04_Projects"
mkdir -p "{path}/05_Areas/content-creation/ideas"
mkdir -p "{path}/05_Areas/health/daily"
mkdir -p "{path}/06_Content"
mkdir -p "{path}/07_System/context-files"
WAVE 3: Install workflows
Copy the canonical skills and Claude Code adapters:
cp -R .agents "{path}/.agents"
cp -R .claude "{path}/.claude"
Keep /init installed so the user can inspect the setup contract later. Do not run it against the initialized vault again.
WAVE 4: Generate CLAUDE.md + AGENTS.md
Create {path}/CLAUDE.md using the answers from WAVE 1. Then copy it to {path}/AGENTS.md so Codex and other agents read the same context. Follow this structure:
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 · 201 lines · 12 tokens per session scan A 58e82ffc9735
init is a skill published in the GitHub repository Railly/agent-brain (22 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 1,516 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…