planning
v0.45.1Pre-implementation planning pipeline: chart a too-big, foggy effort as a decision map, diverge on candidate approaches, lock product intent and the engineering contract, route resolved domain language to the domain-driven-design glossary steward, explore the design space, stress-test adversarially, and produce a structured implementation plan with an approval gate.
By Melodic SoftwareLicense: MIT20 GitHub starsUpdated 1 hour ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 12 skill or MCP entries
- Source updated
- Sep 28, 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 planning for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install planning-3@agent-plugin-marketplacePaste 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/melodic-software/claude-code-pluginsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/planning/.
Plugin files
├── .claude-plugin/plugin.json├── skills/audit-answers/SKILL.md├── skills/brainstorm/SKILL.md├── skills/design/SKILL.md├── skills/design-handoff/SKILL.md├── skills/devils-advocate/SKILL.md├── skills/draft-goal-condition/SKILL.md├── skills/interview/SKILL.md├── skills/plan/SKILL.md├── skills/prd/SKILL.md├── skills/questionnaire/SKILL.md├── skills/setup/SKILL.md└── skills/wayfind/SKILL.md
Included Skills12
Validate a filled /planning:interview ledger with fresh-context agents that re-check each answer blind to its rationale; only doubtful ones come back. Use when: 'audit my interview answers', 'validate the interview answers', 'have agents check the answers', 'accept all and have agents check them', 'agent-validated interview', 'have subagents second-guess the recommendations', 'auto-answer then verify the ledger'. Plans: '/planning:devils-advocate'; first-time questions: '/planning:interview'.
Diverge before scoping. Turn a rough engineering/product problem into codebase-grounded candidate approaches ordered cheapest→most ambitious, capture which resonate, and hand off scoped. Use when: 'brainstorm', 'what are my options', 'places we could intervene', 'how could we approach X', 'ideas for this', 'explore some approaches', 'what could we do here', or any rough technical problem with no locked scope; skip when scope is already locked or the options are visual variations.
Resolve design decisions (types, contracts, package topology, module boundaries) in discussion rounds before /planning:plan, producing design artifacts. Use when: 'design this', 'type modeling', 'figure out the abstractions', 'model this domain', 'what should the types look like', 'how should I structure this', 'where do the module boundaries go', or entering /planning:plan without exploring the design space. Handoff gate: /planning:design-handoff.
Gate a finished design for /planning:plan: FAILs on any design thread left unresolved and untagged, then emits a coverage table, the plan-ready summary, and a resume prompt. Use when: 'design handoff', 'hand off the design', 'is the design ready', 'plan-ready summary', 'design gate', or design rounds stop surfacing gaps. Still exploring: /planning:design. Mid-session save-point: a session-handoff capability.
Stress-test a plan or proposal adversarially before implementation: assumptions, evidence, failure scenarios, operational gotchas. Use when: 'devil's advocate', 'stress test', 'poke holes', 'what could go wrong', or before new dependencies, CI/build changes, or cross-module architecture. `incumbent` mode attacks the status quo: 'is there a better way now', 'should we still use X'. Not for code bugs or pre-PR verification.
Pick the repetition lever (/goal, /loop, routines and /schedule, a workflow, a Stop hook, or a one-shot prompt) and, when /goal fits, draft a transcript-demonstrable completion condition, checked against the documented limit by a deterministic counter. Use when: 'which loop should I use', 'pick the right autonomy lever', 'craft a /goal', 'make Claude keep working until X', 'my goal is not measurable', 'my /goal is too long'.
Interview to shared understanding on a plan, decision, or idea, in rounds of numbered, recommended questions. An engineering task locks a PLAN.md Brief (goal, constraints, acceptance criteria, assumptions). Use when: 'interview me', 'lock the brief', 'spec this task', 'grill me', 'this is underspecified', 'ask me questions first', 'what do you need to know', 'acceptance criteria', 'how will we know this is done', or before behavior-changing work with ambiguous intent. Skip mechanical work.
Produce structured implementation plans with goal, approach, test strategy, blast-radius assessment, parallelism analysis, and a user approval gate before any code is written. Persisting PLAN.md for fresh-session handoff. Use when: 'plan this', 'architect this', 'how should we implement', 'implementation plan', 'write a plan for this', 'what's the approach here', 'review this plan' (audits an existing plan's completeness), or proactively before executing without a formalized plan.
Write a Product Requirements Document that locks product intent (problem, users, success metrics) before any engineering plan, in three tiers with a review mode. Use when: 'write a PRD', 'spec out a feature', 'product brief', 'product requirements doc', 'define the requirements', 'what are we actually building', 'acceptance criteria', 'how will we know it worked', or a user-facing change needs written alignment. Engineering-internal work: /planning:interview or /planning:plan.
Turn a decision another person holds into an async Markdown questionnaire, interviewing the user only about the send, never the subject. Use when: 'make a questionnaire for X', 'I need to ask my DBA/the client/legal about this', 'turn this into a doc someone else fills in', 'I don't know, that's the client's call', 'send this to someone else to answer', 'write up questions for our security team', or an interview branch defers to a person. Self-answerable: /planning:interview.
Verify and configure the planning plugin for this repository across its two concerns. check inspects read-only the topic-docs seam (.claude/topic-docs.yaml effective values, committed-tier conflict) and the standards index presence; apply resolves where topic documents land (persisting .claude/topic-docs.yaml) and bootstraps the standards index (docs/standards/ and, on relocation, .claude/standards.yaml). Use when: 'set up planning', 'is planning configured', 'configure the planning plugin', 'planning setup', 'where do planning artifacts land', 'set up standards', 'bootstrap the standards index', or a planning skill reports missing or thin config. Re-runnable. Safe to invoke again to reconfigure or migrate.
Chart a too-big, still-foggy effort as a decision map on the work-item tracker and work its frontier one decision at a time until it graduates to a Brief, PRD, or PLAN. Use when: 'this is a huge foggy effort', 'I don't even know the questions yet', 'map this out', 'chart this program', 'plan-the-plan'. Already sharp tickets: /planning:interview or /work-items.
Plugin manifests1
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "planning",
"version": "0.45.1",
"userConfig": {
"surface": {
"type": "string",
"title": "Question surface for planning:interview",
"description": "Where /planning:interview renders its question rounds: terminal (default, inline in the conversation) or page (a local 127.0.0.1 page the session watches, where each question is answered and every save reaches the session). Applies only to /planning:interview. Any other value falls back to terminal.",
"default": "terminal"
},
"use_ask_user_question": {
"type": "boolean",
"title": "Use AskUserQuestion for interview rounds",
"description": "When enabled, the planning skills' question rounds (interview, prd, design, plan) render a round of up to 4 independent questions through the AskUserQuestion tool instead of inline prose. Default: inline prose (dictation-friendly).",
"default": false
},
"use_emoji_question_markers": {
"type": "boolean",
"title": "Emoji anchors on interview round questions",
"description": "When enabled, each interview round question leads with a ❓ anchor on its Q<N> line and its 'My recommendation:' line leads with ➡️, inline in the terminal and, on the page surface, on the question title and the Recommendation heading. Purely presentational. Q<N> numbering stays the functional handle, and persisted artifacts (ledger, register, Brief) never carry the emoji. Default: plain text. A user instruction against emoji wins over this option, and the page is then started with --emoji-markers false so it matches the terminal.",
"default": false
}
},
"description": "Pre-implementation planning pipeline: chart a too-big, foggy effort as a decision map, diverge on candidate approaches, lock product intent and the engineering contract, route resolved domain language to the domain-driven-design glossary steward, explore the design space, stress-test adversarially, and produce a structured implementation plan with an approval gate.",
"author": {
"name": "Melodic Software",
"email": "[email protected]"
},
"license": "MIT",
"keywords": [
"planning",
"wayfind",
"decision-map",
"brainstorm",
"prd",
"interview",
"questionnaire",
"design",
"design-handoff",
"devils-advocate",
"audit-answers",
"validate",
"plan",
"stress-test",
"incumbent",
"alternatives",
"status-quo",
"implementation-plan",
"draft-goal-condition",
"goal",
"completion-condition",
"autonomous-goal",
"skill"
]
}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.
[planning on Agent Plugins Marketplace](https://pluginsmp.com/plugins/planning-3)