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-focusgit 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-focus)<a href="https://agentmods.dev/skills/sandermoon/local-brain/brain-focus"><img src="https://agentmods.dev/badge/skills/sandermoon/local-brain/brain-focus/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-focus"><img src="https://agentmods.dev/badge/skills/sandermoon/local-brain/brain-focus.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 | $0.00052 | $0.01086 |
| Opus 5.5 | $0.00021 | $0.00434 |
| Sonnet 5.5 | $0.00010 | $0.00217 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
brain-focus 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brain-focus: Deep Work Session
Set up and maintain a focused work context for a single project. The agent becomes a project-scoped collaborator — loading full context, suggesting next actions, and deflecting distractions to the inbox.
Trigger Phrases
- "Let's work on [project]", "Focus on [project]"
- "I'm going to work on [project] now"
- "Deep work time", "Focus mode"
- "What should I do next on [project]?"
Workflow
Step 1 — Set the Focus
Determine which project to focus on:
- If the user names a project: use it directly
- If ambiguous: call
get_brain_overviewand ask which project
Call set_context to set the focused project.
Step 2 — Load Project Context
Call get_project_context with include_note_content: "preview" to get:
- All open and in-progress tasks
- Recent notes
- Linked repositories
Present a concise project dashboard:
[Project Name] [Description]
In progress: [list] Up next: [highest priority open tasks] Blocked: [any blocked items] Backlog: [count] (not shown in detail — these are unplanned) Recent notes: [titles]
Step 3 — Suggest Next Action
Based on the project state, recommend what to work on:
- In-progress tasks first — continue what was already started
- Highest priority unblocked tasks — if nothing is in-progress
- Blocked items — if something could be unblocked quickly, suggest that
"You were working on [task]. Want to continue, or pick something else?"
Mark the chosen task as in-progress with update_todo.
Step 4 — During the Session
While the user is working in focus mode:
Capture stray thoughts to inbox: When the user mentions something unrelated to the current project:
"Got it — I'll save that to your inbox so you can deal with it later."
Call add_to_dump for the stray thought. Return focus to the project immediately. Do not switch context.
Track progress: When the user completes something:
- Update the task status to
doneviaupdate_todo - Suggest the next task from the project
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 · 126 lines · 52 tokens per session scan A 06e85eadebd3
brain-focus is a skill published in the GitHub repository SanderMoon/local-brain (9 stars, last pushed 7mo ago), licensed MIT. It adds 52 tokens to every session and 1,086 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
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.
community
Use when building or running a persistent two-way community space — Discord, Telegram, Circle: platform choice, structure, onboarding, native→bot→human moderation, rituals, growth loops, health metrics. NOT churn of paying product customers (that is retention), NOT broadcast email (that is newsletter), NOT one live…
parallel
Use when two or more pieces of work are genuinely independent — disjoint files, no shared state, no ordering edge — and should fan out across subagents, then be gathered and reconciled under a combined test suite. Decides WHAT can run concurrently; NOT the isolation it runs in (that is worktrees), NOT the per-unit TDD…
codebase-navigation
Use this skill when starting work in an unfamiliar codebase or area — finding where something is implemented, how a request flows, what depends on a piece of code, or where a change should go — before reading files one by one. Triggers: user says "where is", "how does this work", "find the code that", "explain this…
slackcli
Read, send, search, and manage Slack workspaces with the slackcli binary. Installs slackcli if missing and checks or proposes authentication first. Use whenever the user mentions Slack or pastes a slack.com link.
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.