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 skills add SanderMoon/local-brain --skill brain-capturegit clone --depth 1 https://github.com/SanderMoon/local-brainWrote 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/skills/sandermoon/local-brain/brain-capture)<a href="https://agentmods.dev/skills/sandermoon/local-brain/brain-capture"><img src="https://agentmods.dev/badge/skills/sandermoon/local-brain/brain-capture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sandermoon/local-brain/brain-capture"><img src="https://agentmods.dev/badge/skills/sandermoon/local-brain/brain-capture.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.01044 |
| Opus 5.5 | $0.00022 | $0.00418 |
| Sonnet 5.5 | $0.00011 | $0.00209 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
brain-capture 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 1mo 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brain-capture: Smart Quick Capture
Capture thoughts, tasks, and notes instantly with minimal friction. Speed is everything — the capture must be faster than the thought fading. Infer metadata from natural language; do not interrogate.
Trigger Phrases
- "Remind me to...", "Don't let me forget..."
- "Add a task: ...", "Save this: ..."
- "I need to...", "Note to self: ..."
- "Quick thought: ...", "Idea: ..."
- Any statement that implies something should be remembered
Workflow
Step 1 — Parse the Input
Extract from the user's natural language:
| Signal | Example | Inference |
|---|---|---|
| Action verb | "Ship the feature" | Task (not note) |
| Time reference | "by Friday", "next week", "before March" | Due date |
| Urgency words | "urgent", "ASAP", "critical", "important" | Priority 1 |
| Project mention | "for the website", "re: backend" | Project association |
| "idea", "thought", "note" | "Idea for the landing page" | Note (not task) |
| Multiple items | "I need to X, Y, and Z" | Multiple captures |
Step 2 — Route the Capture
If a project is clearly identified (user mentions it by name or context is unambiguous):
- Call
create_todo_in_projectdirectly with inferred metadata - Confirm: "Added to [project]: [task] (due Friday, P1)"
If the project is ambiguous or no project context:
- Call
add_to_dumpto send to inbox - Confirm: "Captured to inbox: [task]"
- Do NOT ask "which project?" — that breaks the speed contract. Inbox exists for this.
If it's a note, not a task:
- Call
add_to_dumpwith type "note" and a title - Confirm: "Saved note: [title]"
If multiple items are mentioned:
- Parse each one separately
- Capture all in a single batch call
- Confirm with a list: "Captured 3 items: ..."
Step 3 — Confirm and Return
Confirmation must be one line. Examples:
"Captured: 'Review PR for auth module' -> inbox"
"Added to backend-v2: 'Fix rate limiting bug' (P1, due 2026-02-18)"
"Saved 3 tasks to inbox: 'Update docs', 'Email Sarah', 'Book flight'"
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.
- 1mo ago First seen · 111 lines · 55 tokens per session scan A c7ac92bcc75c
brain-capture is a skill published in the GitHub repository SanderMoon/local-brain (9 stars, last pushed 7mo ago), licensed MIT. It adds 55 tokens to every session and 1,044 once invoked, about $0.0002 per session on Opus 5.5. 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
alive:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
scope-lock
Use when you want to lock the session to a specific scope description, injecting it into purpose-gate context and optionally blocking out-of-scope tool calls.
handoff-protocol
Structured handoff protocol for multi-session agent orchestration with evidence capture.
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
pm
Use when the user wants product requirements rather than code: 'write a PRD', 'product requirements', 'spec this feature for the team', 'ooo pm'. Runs a PM-focused interview with automatic question classification and produces a PRD/PM document. Not for implementation requests.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.