collaborative-plan

collaborative-plan is a command for coding agents from jimmc414/claude-code-plugin-marketplace. It costs 11 tokens per session (389 once invoked), scanned A, original, MIT.

A command that runs a question-and-answer planning session before implementation.

In plain words
What is it for?
Use it to clarify scope, technical needs, user experience, and edge cases, then produce a plan.
Why use it?
It exposes missing requirements and unclear decisions before they lead to the wrong design or code.

Command

Part of the collaborative-planning plugin — 2 commands shipped together

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 commands/jimmc414/claude-code-plugin-marketplace/collaborative-plan
Clone the repo
git clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplace

Or install collaborative-planning, the plugin that ships this one along with the rest of its 2 commands.

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 collaborative-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/jimmc414/claude-code-plugin-marketplace/collaborative-plan.svg)](https://agentmods.dev/commands/jimmc414/claude-code-plugin-marketplace/collaborative-plan)
Your own site
<a href="https://agentmods.dev/commands/jimmc414/claude-code-plugin-marketplace/collaborative-plan"><img src="https://agentmods.dev/badge/commands/jimmc414/claude-code-plugin-marketplace/collaborative-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 389 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 $0.00011 $0.00389
Opus 5 $0.00005 $0.00195
Sonnet 5 $0.00002 $0.00078
Haiku 4.5 $0.00001 $0.00039

Measured 4d ago against content hash ea8a6d13f447, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

collaborative-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.

plugins/collaborative-planning/commands/collaborative-plan.md · 45 lines

What it actually says

Collaborative Planning Session

You are entering a collaborative planning session with the user. This is an iterative requirements gathering and planning workflow.

Phase 1: Requirements Gathering (Iterative Q&A)

Begin by understanding what the user wants to accomplish through iterative questioning:

  1. Use the AskUserQuestion tool to ask clarifying questions about the task
  2. You may ask up to 4 questions per round (this is the tool's limit)
  3. IMPORTANT: Always include this option in every question round:
    • Label: "Done - ready to plan"
    • Description: "I have no more questions, proceed to planning"
  4. After receiving answers, analyze the responses
  5. If the user did NOT select "Done - ready to plan", continue asking follow-up questions using AskUserQuestion again
  6. Repeat this loop until the user selects "Done - ready to plan"

Guidelines for questions:

  • Ask about goals, constraints, preferences, and edge cases
  • Prioritize the most important unknowns first
  • Build on previous answers with deeper follow-up questions
  • Cover technical requirements, user experience, and scope

Phase 2: Planning

Once the user indicates they are ready to plan:

  1. Summarize all the requirements gathered from the Q&A session
  2. Use EnterPlanMode to transition into plan mode
  3. Explore the codebase to understand existing patterns and architecture
  4. Create a detailed implementation plan based on the gathered requirements
  5. Present the plan for user approval before implementation

Starting the Session

The user wants to plan: $ARGUMENTS

Begin Phase 1 now. Start by asking your first round of clarifying questions about this task.

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 · 45 lines · 11 tokens per session scan A ea8a6d13f447

Subscribe to this mod's changes

collaborative-plan is a command published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 389 once invoked, about $0.0001 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.