mindmap-brainstorm

mindmap-brainstorm is a skill for Claude Code, Codex from ravi-labs/mindmap-mcp-server. It costs 86 tokens per session (530 once invoked), scanned A, original, Apache-2.0.

A brainstorming workflow that uses a shared mind map to carry idea history between AI tools such as Claude, Cursor, Copilot, and Cowork.

In plain words
What is it for?
Use it to brainstorm, explore options, or think through a problem while loading and building on earlier idea threads.
Why use it?
It avoids repeating background when an idea was started in another tool or session.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to brainstorm, explore options, or think through a problem while…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ravi-labs/mindmap-mcp-server/mindmap-brainstorm
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.

Any agent
npx skills add ravi-labs/mindmap-mcp-server --skill mindmap-brainstorm
Clone the repo
git clone --depth 1 https://github.com/ravi-labs/mindmap-mcp-server

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 mindmap-brainstorm

README.md
[![agentmods](https://agentmods.dev/badge/skills/ravi-labs/mindmap-mcp-server/mindmap-brainstorm.svg)](https://agentmods.dev/skills/ravi-labs/mindmap-mcp-server/mindmap-brainstorm)
Your own site
<a href="https://agentmods.dev/skills/ravi-labs/mindmap-mcp-server/mindmap-brainstorm"><img src="https://agentmods.dev/badge/skills/ravi-labs/mindmap-mcp-server/mindmap-brainstorm.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00086 $0.00530
Opus 5 $0.00043 $0.00265
Sonnet 5 $0.00017 $0.00106
Haiku 4.5 $0.00009 $0.00053

Measured 6d ago against content hash 0a2e143f696d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mindmap-brainstorm 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.

skills/mindmap-brainstorm/SKILL.md · 28 lines

What it actually says

Mind Map Brainstorm

Brainstorm with memory: continue idea-threads across Claude, Cursor, Copilot, and Cowork without ever re-explaining the idea. This skill orchestrates the flow; your own brainstorming ability does the thinking. Mind Map is the shared memory underneath — not a replacement for how you brainstorm.

When to use

Trigger when the user wants to brainstorm / ideate / "think through" / "explore options or approaches" / "what could we do about X" — and especially when the topic might already have history elsewhere.

Flow — do these in order

  1. Load prior context. Call the mindmap_brainstorm tool with the topic. It returns the user's persona plus prior brainstorms and related memories to build on, and promotes the brainstorms you reuse.

    • If the mindmap_* tools aren't available, tell the user the Mind Map MCP server isn't connected (so memory won't carry across tools), then continue without it.
  2. Brainstorm — your way. Using the returned context, brainstorm with your full capability (and any dedicated brainstorming technique you have). Build on the prior threads rather than repeating them. Diverge widely first, then converge to a few strong directions.

  3. Save what's worth keeping. When the session produces something durable — a decision, a shortlist, a plan — call mindmap_capture with kind: "brainstorm", a clear title, a portable summary, and key_points. That capture is what lets the idea resume in the user's next tool.

Principles

  • Memory layer, not puppeteer. Mind Map carries the context; it does not drive other tools' features. Use the portable context and your own ability — don't try to invoke another tool's skills.
  • Continue, don't duplicate. Prefer extending an existing brainstorm (the tool surfaces related ones with their ids) over starting a near-duplicate.
  • Write portably. Compose each capture so a different tool with zero prior context could pick it up cold.
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. 6d ago First seen · 28 lines · 86 tokens per session scan A 0a2e143f696d

Subscribe to this mod's changes

mindmap-brainstorm is a skill published in the GitHub repository ravi-labs/mindmap-mcp-server (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 86 tokens to every session and 530 once invoked, about $0.0004 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

grounded-knowledge-workflow

Use Grounded Knowledge Engine to select an isolated workspace, answer from local evidence, resume an explicitly identified project, create an explicit project checkpoint, and retain durable knowledge. Trigger when a user asks about their documents, workspace or client context, previous research, project state…

dimosgit/grounded-knowledge-engine · 91 tokens

ragcode-memory

Manage shared cross-AI memories for this project through RagCode MCP tools (memorywrite, memoryquery, memorylist, memorydelete), with ragcode memory CLI fallback when MCP is unavailable. Read prior decisions, user preferences, and feedback written by other AI agents, and record new insights so they persist across…

MarshallEriksen-Neura/ragcode · 101 tokens

pkm-explore

Use when researching what the vault knows about a topic — performs graph + semantic exploration with gap analysis to map existing knowledge and find missing connections. Primarily used via the vault-explorer agent. Not for routine session-start context loading (hooks handle that).

AdrianV101/obsidian-pkm-plugin · 55 tokens

memory

Use when sharpening a perception or observation you ALREADY formed about conversation state, user behavior, drift, emotional shifts, or cross-turn patterns. Trigger phrases include "what did you notice about X", "the user keeps doing Y", "I sense something has changed", "is the user X-ing", "what does this pattern…

ejentum/ejentum-mcp · 199 tokens

public

Skill "public" from shawnhack/exocortex, covering exocortex, tools, core, intelligence and knowledge graph.

shawnhack/exocortex · 0 tokens

research-wiki

A persistent research knowledge base for storing papers, ideas, experiments, claims, and the links between them.

wanshuiyin/Auto-claude-code-research-in-sleep · 73 tokens