disambiguate-plan

disambiguate-plan is a command for Claude Code from jimmc414/claude-code-plugin-marketplace. It costs 15 tokens per session (1,540 once invoked), scanned A, original, MIT.

A planning command that keeps asking questions until the requirements are sufficiently clear for a plan.

In plain words
What is it for?
Use it when a task has unclear goals or several possible interpretations and needs thorough requirements gathering first.
Why use it?
It prevents unresolved ambiguity about scope, technical choices, constraints, and edge cases from reaching implementation.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

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

Good fit Use it when a task has unclear goals or several possible interpretations and needs thorough requirements gathering first.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jimmc414/claude-code-plugin-marketplace/disambiguate-plan
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.

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

Made for: Claude Code.

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 disambiguate-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/jimmc414/claude-code-plugin-marketplace/disambiguate-plan/github.svg)](https://agentmods.dev/commands/jimmc414/claude-code-plugin-marketplace/disambiguate-plan)
Your own site
<a href="https://agentmods.dev/commands/jimmc414/claude-code-plugin-marketplace/disambiguate-plan"><img src="https://agentmods.dev/badge/commands/jimmc414/claude-code-plugin-marketplace/disambiguate-plan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for disambiguate-plan

Your own site · 80×15
<a href="https://agentmods.dev/commands/jimmc414/claude-code-plugin-marketplace/disambiguate-plan"><img src="https://agentmods.dev/badge/commands/jimmc414/claude-code-plugin-marketplace/disambiguate-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,540 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 $0.00015 $0.01540
Opus 5 $0.00008 $0.00770
Sonnet 5 $0.00003 $0.00308
Haiku 4.5 $0.00002 $0.00154

Measured 10d ago against content hash 7d898269fb8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

disambiguate-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 10d 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/disambiguate-plan.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Collaborative Planning Session with Iterative Disambiguation

You are entering a collaborative planning mode where your primary goal is to deeply understand the user's requirements before proposing any implementation plan. Ambiguity is the enemy of good planning.

Core Principle

Never proceed with planning until YOU are confident that all ambiguities have been resolved. Your job is to be thorough, not fast. The user trusts you to ask the right questions—do not proceed prematurely.


Phase 1: Initial Analysis

Immediately upon receiving the task, perform a silent analysis:

  1. Read and analyze the user's request carefully
  2. Identify ALL areas of potential ambiguity, including:
Category Examples
Requirements Unclear acceptance criteria, undefined behavior, missing constraints
Technical Performance targets, security requirements, compatibility needs
Scope What's in vs out of scope, MVP vs full feature, integration boundaries
Context Assumed knowledge, existing patterns to follow, dependencies
Interpretation Multiple valid readings of the request, implicit assumptions
Edge Cases Error handling, failure modes, boundary conditions
Preferences UI/UX choices, naming conventions, architectural patterns

Phase 2: Iterative Disambiguation Loop

CRITICAL: You MUST use the AskUserQuestion tool repeatedly until ALL ambiguities are resolved.

Loop Instructions

For each disambiguation round:

  1. Group related ambiguities together (up to 4 questions per AskUserQuestion invocation)
  2. Prioritize the most impactful ambiguities—those that would most significantly change the plan
  3. Invoke AskUserQuestion with clear, specific questions
  4. Analyze responses for:
    • Direct answers that resolve ambiguities
    • NEW ambiguities that arose from the answers
    • Remaining ambiguities that still need resolution
  5. Continue the loop if ANY ambiguities remain

Read the full file on GitHub · 174 lines

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. 10d ago First seen · 174 lines · 15 tokens per session scan A 7d898269fb8d

Subscribe to this mod's changes

disambiguate-plan is a command published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,540 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.