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-reviewgit 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-review)<a href="https://agentmods.dev/skills/sandermoon/local-brain/brain-review"><img src="https://agentmods.dev/badge/skills/sandermoon/local-brain/brain-review/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-review"><img src="https://agentmods.dev/badge/skills/sandermoon/local-brain/brain-review.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 | $0.00053 | $0.01053 |
| Opus 5.5 | $0.00021 | $0.00421 |
| Sonnet 5.5 | $0.00011 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
brain-review 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brain-review: Weekly Review
Walk the user through a comprehensive review of their entire workspace. This is the "reflect" phase — the practice that keeps the system trustworthy. Inspired by GTD's weekly review: get clear, get current, get creative.
Trigger Phrases
- "Weekly review", "Let's review", "Review my projects"
- "How did this week go?", "What's the state of everything?"
- "End of week check-in", "Friday review"
- "What did I accomplish this week?"
Workflow
Step 1 — Gather Everything
Make these calls to build the full picture:
get_brain_overview— all projects and their statsquery_todoswithstatus: doneandcompleted_after: [7 days ago]— recent completionsquery_todoswithstatus: open— all open tasksquery_todoswithstatus: blocked— blocked itemsget_dump_items— inbox state
Step 2 — Celebrate Progress
Start positive. Present what was accomplished this week:
"This week you completed [N] tasks across [X] projects."
List the completed tasks grouped by project. Acknowledge effort — this is what keeps people motivated.
Step 3 — Review Each Active Project
For each project with open tasks:
- Show project name, open task count, and any in-progress/blocked items
- Ask: "Is this still active? Anything changed?"
- Look for signals:
- Stale tasks: open tasks with no recent activity — ask if they're still relevant
- Blocked tasks: surface them prominently — "This has been blocked. Can we unblock it?"
- Missing deadlines: overdue tasks — "This was due [date]. What's the status?"
Keep this conversational, not interrogative. If a project is on track, a quick "Looks good, moving on" is fine.
Step 4 — Identify Stale Work
Query for tasks that have been open a long time without progress:
- Tasks created > 2 weeks ago with status still
open(never moved toin-progress) - Flag these specifically:
"These tasks have been sitting for a while. Want to reprioritize, defer, or drop any of them?"
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 · 115 lines · 53 tokens per session scan A 1f502f612f24
brain-review is a skill published in the GitHub repository SanderMoon/local-brain (9 stars, last pushed 7mo ago), licensed MIT. It adds 53 tokens to every session and 1,053 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.