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/sandermoon/local-brain/brain-setupnpx skills add SanderMoon/local-brain --skill brain-setupgit clone --depth 1 https://github.com/SanderMoon/local-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 | $0.00049 | $0.00900 |
| Opus 5 | $0.00024 | $0.00450 |
| Sonnet 5 | $0.00010 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade B, and why
brain-setup scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
Briefly explain what Local Brain does in one or two sentences. Do not lecture. Then ask: How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brain-setup: First-Time Setup Wizard
Guide the user through setting up their Local Brain workspace conversationally. This should feel like talking to a new executive assistant on their first day — curious, helpful, and efficient.
Trigger Phrases
- "Set up my brain", "Get started", "I'm new here"
- "Help me organize my projects"
- "I just installed brain"
- First interaction when the brain is empty
Pre-flight Check
Call get_brain_overview to assess the current state:
- If no brain exists or brain is completely empty (no projects, no dump items): run the full setup
- If projects already exist: offer to add more projects or refine existing ones — do not re-run full setup
- If only dump items exist: offer to organize them into projects as part of setup
Workflow
Step 1 — Welcome and Context
Briefly explain what Local Brain does in one or two sentences. Do not lecture. Then ask:
"What are you working on right now? Tell me about your projects — they can be work tasks, side projects, personal goals, anything."
Let the user talk naturally. Extract project names, descriptions, and any mentioned tasks or deadlines from their response.
Step 2 — Create Projects
For each project identified:
- Suggest a short, kebab-case name (e.g., "website-redesign", "q1-planning")
- Confirm the name and description with the user
- Call
create_projectfor each
Do not create more than 3-5 projects in the first pass. If the user mentions more, note them and say: "Let's start with these — you can always add more later."
Step 3 — Populate Initial Tasks
For each project, ask:
"What needs to happen next for [project]? Any deadlines?"
Convert responses into concrete tasks with:
- Clear, actionable descriptions (imperative form: "Ship v2", not "v2 shipping")
- Due dates when mentioned ("by Friday" → the actual date)
- Priority 1 for anything the user emphasizes as urgent or important
Call create_todo_in_project in batches per project.
Step 4 — Handle "I Don't Know"
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 · 98 lines · 49 tokens per session scan B e1831415891d
brain-setup is a skill published in the GitHub repository SanderMoon/local-brain (9 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 900 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
design-debt-audit
Inventory and prioritise accumulated design inconsistencies across a product. Use when drift has built up over time. For token coverage specifically use design-token-audit (designer-toolkit); for WCAG gaps use accessibility-audit (design-systems).
design-impact-reporting
Communicate design's contribution to business and user outcomes in stakeholder language. Use when reporting results upward. For choosing the metrics in the first place, use metrics-definition (ux-strategy).
localization-design
Design for multiple languages, writing directions, and cultural contexts — text expansion, RTL mirroring, and locale formats. Use when shipping beyond one locale. For the words themselves, use ux-writing (designer-toolkit).
motion-system
Define motion tokens — durations, easing vocabulary, and reduced-motion handling — for consistency product-wide. Use when standardising motion across a system. For crafting one specific animation, use animation-principles (interaction-design).