brain-plan

brain-plan is a skill for Claude Code, Codex from SanderMoon/local-brain. It costs 53 tokens per session (1,365 once invoked), scanned A, original, MIT.

A collaborative project-planning workflow that breaks a goal into concrete tasks with priorities, deadlines, and an order of work.

In plain words
What is it for?
Use it when starting a project, figuring out how to achieve a goal, or breaking existing work into actionable tasks. It supports planning both new projects and work already in progress.
Why use it?
It turns a vague project into manageable next steps and makes missing scope or decisions easier to spot.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sandermoon/local-brain/brain-plan
Any agent
npx skills add SanderMoon/local-brain --skill brain-plan
Clone the repo
git clone --depth 1 https://github.com/SanderMoon/local-brain

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for brain-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandermoon/local-brain/brain-plan.svg)](https://agentmods.dev/skills/sandermoon/local-brain/brain-plan)
Your own site
<a href="https://agentmods.dev/skills/sandermoon/local-brain/brain-plan"><img src="https://agentmods.dev/badge/skills/sandermoon/local-brain/brain-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.01365
Opus 5 $0.00026 $0.00682
Sonnet 5 $0.00011 $0.00273
Haiku 4.5 $0.00005 $0.00136

Measured 4d ago against content hash 303c080b9c57, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brain-plan 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 4d 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.

pkg/skillscatalog/skills/brain-plan/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

brain-plan: Project Planning

Help the user decompose a goal into concrete, actionable tasks with priorities, deadlines, and logical ordering. This is collaborative planning — the agent facilitates, the user decides.

Trigger Phrases

  • "Let's plan [project]", "Help me plan..."
  • "Break this down", "How should I approach this?"
  • "I need to figure out how to..."
  • "New project: ...", "I want to start..."
  • "What are the steps for...?"

Workflow

Step 1 — Identify the Scope

Determine if this is:

  • A new project that needs to be created
  • An existing project that needs task breakdown
  • A vague goal that needs clarification first

If new: ask for a one-sentence description of what "done" looks like. If existing: call get_project_context to see current state. If vague: help clarify with one question — "What would it look like if this was finished?"

Step 2 — Brainstorm Tasks

Ask:

"What are the main things that need to happen to get this done?"

Let the user brain-dump. Then help structure their response:

  1. Break large items into smaller tasks — if something takes more than a day of effort, it probably should be 2-3 tasks
  2. Make tasks actionable — each should start with a verb: "Write", "Build", "Research", "Contact", "Deploy"
  3. Identify dependencies — "What needs to happen first?"
  4. Spot missing steps — "I notice you mentioned X but not Y — do we need that?"

Present the proposed task list and ask for confirmation before creating anything.

Step 3 — Add Metadata

For the confirmed tasks:

  1. Sequence — order tasks logically (dependencies first)
  2. Priority — ask about the first 2-3 most important tasks: "Which of these is the most critical to get right?"
  3. Deadlines — if the project has an overall deadline, work backwards: "If this needs to be done by [date], when should each piece be finished?"
  4. First task — identify the single next action: "If you were starting right now, what would you do first?"

Read the full file on GitHub · 116 lines

Changes

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.

  1. 4d ago First seen · 116 lines · 53 tokens per session scan A 303c080b9c57

Subscribe to this mod's changes

brain-plan is a skill published in the GitHub repository SanderMoon/local-brain (9 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 1,365 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.

Related

Other skills, from other repositories

review-sweep

Review oh-my-hermes pull requests that have not been reviewed at their current head commit. Run manually to sweep the open backlog, or pass a number to review one PR. Applies the repository's REVIEW.md policy and posts findings as a GitHub review with inline comments.

rlaope/oh-my-hermes · 58 tokens

triage-sweep

Backfill labels across oh-my-hermes issues and pull requests. Run manually to sweep everything currently unlabeled, or pass a number to triage one item. Use when issues and PRs have accumulated without labels, after adding a new label to .github/labels.yml, or before a release when the backlog needs to be readable by…

rlaope/oh-my-hermes · 74 tokens

team-workflow

Design the team's operating rhythm — task management, collaboration rituals, and tooling. Use when the day-to-day cadence needs structure. For a time-boxed sprint, use design-sprint-plan.

Owl-Listener/designer-skills · 43 tokens

alive:create-walnut

Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.

alivecontext/alive · 63 tokens

implement

End-to-end workflow for taking MCP work items from backlog to merged PR. Handles git branching, schema-driven planning, implementation, independent review, and PR creation. Composes spec-quality, review-quality, and schema-workflow skills into a single pipeline. Use when a user says "implement this", "work on this…

jpicklyk/task-orchestrator · 101 tokens

review-proposals

Triages pending improvement-proposal MCP items — presents each with its scope and evidence, collects an accept/reject/defer decision per proposal, and carries out the disposition: project-scoped acceptances get their exact YAML applied to .taskorchestrator/config.yaml and pushed per-root; global acceptances get a…

jpicklyk/task-orchestrator · 129 tokens