forge-mindmap
Skill2 starsChanged 5 days agoMITView on GitHub
Use when a plan reads better as a mind map (nodes and edges).
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- ForgeyClap/claude-forgeedited, first seen Oct 11, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- ForgeyClap/claude-forge★ 294% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository99 other files it gives its agents.
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brainstormingSkill
- claude-md-improverSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- forge-a11ySkill
- forge-agent-reportSkill
- forge-agentSkill
- forge-apiSkill
- forge-authSkill
- forge-autoresearchSkill
- forge-botsSkill
- forge-brainstormSkill
- forge-cliSkill
- forge-cmsSkill
- forge-code-reviewSkill
- forge-contextSkill
- forge-councilSkill
- forge-craftSkill
- forge-databaseSkill
- forge-dataSkill
- forge-debugSkill
- forge-deeplearnSkill
- forge-devopsSkill
- forge-docdriftSkill
- forge-doctorSkill
- forge-ecc-adapterSkill
- forge-ecommerceSkill
- forge-electronSkill
- forge-extensionSkill
- forge-figmaSkill
- forge-fullstackSkill
- forge-gameSkill
- forge-graded-verifySkill
- forge-guardianSkill
- forge-heartbeatSkill
- forge-i18n-docsSkill
- forge-intakeSkill
- forge-integrationSkill
- forge-long-form-writingSkill
- forge-mcp-clientsSkill
- forge-memorySkill
- forge-migrationSkill
- forge-mlopsSkill
- forge-mobileSkill
- forge-n8nSkill
- forge-nightshiftSkill
- forge-observabilitySkill
- forge-paymentsSkill
- forge-plan-largeSkill
- forge-prdSkill
- forge-predictionSkill
- forge-projectbrainSkill
- forge-prompt-coachSkill
- forge-qualitySkill
- forge-ragSkill
- forge-registrySkill
- forge-releaseSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Not needed for a trivial, single-path task.
- Distinctive: line 17
Write the structure as an indented plain-text outline (2-space or tab indent = depth.
- Distinctive: line 38
Real structure only: Every node reflects an actual part of the plan/architecture the Lead decided on — no filler branches, no invented …
- Very specific: line 39
Secrets are auto-redacted: Every string in the map is redacted (forge-store.cjs's redactValue) before it is written to disk — never write a …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Forge Mind Map (WP4)
A Forge mind map is a small node/edge graph — a root idea with branches and leaves — that the Lead generates to visualize a plan, an architecture, or a mission decomposition. It is built and stored by .claude/forge-bin/forge-mindmap.cjs, a zero-dependency writer that stores the structured JSON (and optional Mermaid/markdown sidecars) under .claude/forge-mindmaps/.
When the Lead generates one
- To visualize a plan, architecture, or mission decomposition once it has real branching structure (a root idea with several sub-areas) — not for a flat 2-3 item list where prose is clearer.
- Typically right after a Master Plan or Deep Learn Mode pass, so the map reflects real decisions already made, not a guess.
- Not needed for a trivial, single-path task.
How
- Write the structure as an indented plain-text outline (2-space or tab indent = depth; the first line is the root):
Mission Control Phase 2 WP4 Mind Map Writer (forge-mindmap.cjs) Radial lens (dashboard) WP5 Next Work Package - Build + store it:
node .claude/forge-bin/forge-mindmap.cjs from-outline '<outline-text>' <map_id> --write --run <run_id> --mermaid- Omit
--writeto preview the parsed{nodes, edges}JSON without persisting anything. --mermaidalso writes a<map_id>.mmdMermaid sidecar (graph TD, guarded — never crashes on odd input).--run <run_id>logsmindmap_generatedto that run's dashboard events — only fires once the map was actually written.- Already have a built
{map_id, title?, nodes, edges}object instead of an outline? Usewritedirectly:node .claude/forge-bin/forge-mindmap.cjs write '<map-json>' --write --run <run_id>.
- Omit
What it produces
.claude/forge-mindmaps/<map_id>.json (the stored {map_id, title, nodes, edges, _generated}), optionally <map_id>.mmd (Mermaid) and <map_id>.md (nested outline), and an appended row in .claude/forge-mindmaps/index.jsonl. The dashboard's MIND MAP lens reads the latest stored map read-only and renders it as a root-centered radial graph (root at the center, branches/leaves on rings by depth, no node overlap).
Honesty rule (non-negotiable)
- Real structure only. Every node reflects an actual part of the plan/architecture the Lead decided on — no filler branches, no invented depth just to make the map look bigger.
- Secrets are auto-redacted. Every string in the map is redacted (
forge-store.cjs'sredactValue) before it is written to disk — never write a raw secret into a mind map. - The MIND MAP lens is read-only. There is no write endpoint on the dashboard for mind maps; the only way to create or change one is
forge-mindmap.cjs write/from-outline. With no stored map yet, the lens shows an honest empty state — it never fabricates nodes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

