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-triagenpx skills add SanderMoon/local-brain --skill brain-triagegit 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-triage)<a href="https://agentmods.dev/skills/sandermoon/local-brain/brain-triage"><img src="https://agentmods.dev/badge/skills/sandermoon/local-brain/brain-triage.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.00878 |
| Opus 5 | $0.00028 | $0.00439 |
| Sonnet 5 | $0.00011 | $0.00176 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
brain-triage 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 6d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brain-triage: Inbox Processing
Systematically process items in the inbox (00_dump.md), helping the user decide where each item belongs. This is the "clarify and organize" phase of the GTD loop.
Trigger Phrases
- "Process my inbox", "Triage my dump"
- "Clean up my inbox", "Organize my captures"
- "What's in my inbox?"
- After a daily briefing shows inbox items
Workflow
Step 1 — Fetch Inbox and Context
Call get_dump_items to retrieve all inbox items.
If the inbox is empty:
"Inbox zero — nothing to process. Nice work."
If items exist, also call get_brain_overview to get the list of existing projects for refile suggestions.
Step 2 — Group and Present
Before processing item-by-item, scan all items and group related ones:
- Items that mention the same project or topic
- Items captured close together that form a sequence
Present a summary:
"You have [N] items in your inbox. I see [X] that look related to [project], [Y] that might be new topics. Let's process them."
Step 3 — Process Each Item (or Group)
For each item or group of related items:
- Show the item with its ID and content
- Suggest an action based on content analysis:
- Refile to [project] — if it clearly matches an existing project
- Create new project — if it represents a distinct new effort
- Convert to note — if it's reference material, not an action
- Add metadata — if it's a task but needs priority/due date
- Discard — if it's stale, duplicate, or no longer relevant
- Wait for confirmation — never refile without the user agreeing
For batches of related items going to the same project, suggest a batch refile:
"These 4 items all look like they belong in [project]. Refile all of them?"
Step 4 — Execute Actions
Based on user decisions:
refile_item— for moves to existing projects (use batch array for multiple items)create_projectthenrefile_item— for new project creationcreate_project_note— for converting items to notesupdate_todo— for adding priority or due dates after refiledelete_todo— for discarding items (confirm first)
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.
- 6d ago First seen · 91 lines · 57 tokens per session scan A e30b8ff9d898
brain-triage is a skill published in the GitHub repository SanderMoon/local-brain (9 stars, last pushed 5mo ago), licensed MIT. It adds 57 tokens to every session and 878 once invoked, about $0.0003 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
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
handoff
Checkpoint work for recovery — fires on "handoff", "wrap up", context pressure, a closed phase, or before a long external wait or irreversible gate. Part of the Agentsmith harness; writes durable state plus a paste-ready kickoff block so a fresh session loses nothing.
cli-prompts-clack
Beautiful interactive CLI prompts with @clack/prompts and custom prompts with @clack/core.
tokenless-install
Install, upgrade, repair, and verify Tokenless, its agent skills, and local Playwright runtime. Use only when the user explicitly asks for installation, upgrade, repair, browser sign-in handoff, a failed doctor check, or an installation integrity check.
schedule
Use when scheduling recurring cron jobs or one-shot background notifications.
fable-spark
Predict the smallest atomic next engineering action from current workspace state, evidence gates, and mutation freshness with situational silence. Use when evaluating what immediate atomic step to take next, checking situational awareness, or determining if the current state requires action or silence — even if the…