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/hamchowderr/braynee/setupnpx skills add hamchowderr/braynee --skill setupgit clone --depth 1 https://github.com/hamchowderr/brayneeWhat 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 | $0.00088 | $0.01538 |
| Opus 5 | $0.00044 | $0.00769 |
| Sonnet 5 | $0.00018 | $0.00308 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
setup 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 yesterday.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Skill
Onboarding wizard that turns an empty machine into a fully wired second brain. User types 4 things. Everything else is auto-detected, researched, or confirmed with a Yes/No popup.
Required Toolchain
Braynee has hard dependencies. Setup verifies all of them up front (Step 1A) and guides cross-platform installation for any that are missing — none are assumed to exist:
| Tool | Why it's required |
|---|---|
git |
Vault is a git repo; the plugin configures Obsidian Git auto-commit/push |
node |
Runs every braynee hook, monitor, and bundled script |
python3 |
Runs the setup, scaffold, and migration scripts |
bd |
Beads issue tracking is mandatory for all code projects |
| QMD | Search index (ships via the bundled qmd-wrapper.mjs) |
If any are missing, setup offers to install them (OS-appropriate commands) or stops with instructions — it never silently proceeds and fails later.
What It Does
- Verifies required toolchain (git, node, python3, bd, QMD) — installs/guides if missing
- Collects 4 inputs: name, company, website, social handle
- Scans filesystem for git repos (all folder names, not just ~/code)
- Runs web research sub-agent to seed company knowledge
- Scaffolds PARA vault + company structure + PRD section + Development section
- Installs Obsidian community plugins
- Initializes Git, Beads, QMD — and provisions braynee's workflow formulas (autonomous-ship, project, engagement, braynee-release) into
~/.beads/formulas/sobd mol pourworks with no manual copy - Migrates notes from detected source apps (Apple Notes, Notion, OneNote)
- Writes CLAUDE.md seeded with user context
Workflow
See workflows/setup.md for the full step-by-step process.
Usage
/setup
/setup --reset # Re-run, overwrite existing structure
/setup --company-only # Only scaffold company section
/setup --projects-only # Only scan and scaffold projects
Inputs Collected
| # | Question | Used for |
|---|---|---|
| 1 | Your name | CLAUDE.md personalization |
| 2 | Company name (or "personal") | Business folder naming, web research |
| 3 | Company website URL | Research sub-agent seed |
| 4 | LinkedIn or Twitter/X handle (optional) | Personal CLAUDE.md context |
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- rules-templates/beads-conventions.md 9.0 KB
- rules-templates/commit-pr-conventions.md 5.5 KB
- rules-templates/dev-defaults.md 3.1 KB
- rules-templates/secrets.md 2.0 KB
- scripts/detect-env.py 13 KB runs code
- scripts/install-obsidian-plugins.py 11 KB runs code
- scripts/migrate-apple-notes.py 6.8 KB runs code
- scripts/migrate-notion.py 8.9 KB runs code
- scripts/migrate-onenote.py 6.9 KB runs code
- scripts/provision-formulas.py 2.0 KB runs code
- scripts/scaffold.py 17 KB runs code
- scripts/scan-projects.py 7.8 KB runs code
- scripts/settings-writer.py 10 KB runs code
- workflows/setup.md 14 KB
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.
- yesterday First seen · 151 lines · 88 tokens per session scan A 1531b5e1ba87
setup is a skill published in the GitHub repository hamchowderr/braynee (2 stars, last pushed 5d ago), licensed MIT. It adds 88 tokens to every session and 1,538 once invoked, about $0.0004 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 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…