Agent Plugins Marketplace
← All plugins

ideation

v0.26.1

One /ideation entry point, at the right depth: just do it, a short plan, an evidence-gated interview stress-tested by four adversarial plan critics, or a map for foggy multi-session work, opening with a no-files 'should we?' conversation when the question is whether to build at all. Every depth writes a living, versioned plan (plan.json) you answer on a page or in the terminal. Approval is always a terminal confirmation, and it hands the run contract to a deterministic workflow engine that builds, reviews and commits each unit. Watched runs teach the next interview.

Claude Code4 Skills

By Nick Nisi15 GitHub starsUpdated last week

Directory evidence

Runtimes
Claude Code
Parsed components
4 skill or MCP entries
Source updated
Oct 12, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install ideation for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install ideation-2@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/nicknisi/ideation

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

ideation/
├── .claude-plugin/plugin.json
├── skills/autopilot/SKILL.md
├── skills/execute-spec/SKILL.md
├── skills/get-goal-prompt/SKILL.md
└── skills/ideation/SKILL.md

Included Skills4

autopilotskills/autopilot/SKILL.md

Orchestrate full execution of an ideation project — reads an approved plan's run contract (or a 0.x contract), builds an execution manifest, and runs all units on the deterministic Workflow engine (parallel for independent units, sequential for dependent ones). Auto-continues on success, gates on failure. Invoke only when the user explicitly asks to run an approved plan or contract, or when an active /goal directs /ideation:autopilot.

execute-specskills/execute-spec/SKILL.md

Execute an implementation spec generated by ideation. Invokes Scout for codebase exploration, builds components with feedback loops, then runs a Verify-Review-Fix cycle with the Reviewer agent before committing. Invoke only when the user explicitly asks to execute an ideation spec, or when an autopilot Workflow builder directs /ideation:execute-spec.

get-goal-promptskills/get-goal-prompt/SKILL.md

Generate a /goal command that runs an ideation project to completion UNATTENDED by driving /ideation:autopilot. The /goal string is owned by scripts/plan-goal.mjs; this skill resolves the project (an approved plan folder, or a 0.x contract), prints the goal, and copies it to the clipboard. Use when the user says 'goal', 'run as goal', 'goal prompt', or wants to run the project long-haul/unattended rather than watching /ideation:autopilot interactively.

ideationskills/ideation/SKILL.md

The single ideation entry point, run only when explicitly invoked. Picks a planning depth (just do it, short plan, interview, or map), says why in one line, and switches when the user overrules it in a word. When the user is still deciding whether to build at all, it opens with a 'should we?' conversation that writes no files. Every depth writes plan data (docs/ideation/<slug>/plan.json). Pages and terminal forms answer it. Approval is always a terminal confirmation, and it hands the run contract to the engine. Use only when the user invokes /ideation or explicitly asks for this workflow. Ordinary feature requests and planning questions do not start it.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "ideation",
  "version": "0.26.1",
  "homepage": "https://ideation.engineering/",
  "description": "One /ideation entry point, at the right depth: just do it, a short plan, an evidence-gated interview stress-tested by four adversarial plan critics, or a map for foggy multi-session work, opening with a no-files 'should we?' conversation when the question is whether to build at all. Every depth writes a living, versioned plan (plan.json) you answer on a page or in the terminal. Approval is always a terminal confirmation, and it hands the run contract to a deterministic workflow engine that builds, reviews and commits each unit. Watched runs teach the next interview.",
  "author": {
    "name": "Nick Nisi",
    "email": "[email protected]"
  },
  "keywords": [
    "ideation",
    "planning",
    "brain-dump",
    "interview",
    "plan-review",
    "approval",
    "execution",
    "orchestration",
    "workflow",
    "pi",
    "claude-code"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[ideation on Agent Plugins Marketplace](https://pluginsmp.com/plugins/ideation-2)