plan

A command for creating a feature development plan through questions and codebase exploration. It examines a proposed change from several perspectives and produces an actionable plan.

In plain words
What is it for?
Use it to plan software features, investigate related code and documents, clarify requirements, and outline engineering, design, product, business, legal, and scalability concerns.
Why use it?
It helps turn an incomplete feature idea into clearer requirements and implementation steps. It also checks referenced files and asks for missing information before planning.

Command

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/jeffh/claude-plugins/plan
Clone the repo
git clone --depth 1 https://github.com/jeffh/claude-plugins
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 3,520 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 $0.03520
Opus 5 $0.00005 $0.01760
Sonnet 5 $0.00002 $0.00704
Haiku 4.5 $0.00001 $0.00352

Measured 2d ago against content hash 2af7b17e5040, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

discuss/commands/plan.md · 595 lines

How it starts

The opening of the file, as written. The whole thing — 595 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Development Plan

You are tasked with creating comprehensive feature development plans through an interactive, iterative process. Your goal is to thoroughly understand what the user wants to build by examining it from multiple perspectives, asking clarifying questions, and producing a detailed, actionable plan.

Initial Response

When this command is invoked:

  1. Check if a feature description was provided:

    • If provided, acknowledge it and proceed to Step 1 (Codebase Exploration)
    • Read any referenced files FULLY before proceeding (never use limit/offset parameters)
    • CRITICAL: Do NOT spawn sub-tasks before reading files yourself in the main context
  2. If no description provided, respond with:

I'll help you create a comprehensive feature development plan through discussion.

Please describe the feature or change you're considering. You can provide:
- A brief description of what you want to build
- A reference to a ticket, design doc, or requirements file
- Even just a rough idea you're exploring

I'll analyze it from multiple perspectives (engineering, design, product, business, legal, scalability) and ask clarifying questions to help refine your thinking.

Then wait for the user's input using AskUserQuestion.


Step 1: Codebase Exploration

Before asking any questions, understand the current state of the codebase.

1.1 Use the Explore Agent

Spawn a Task with the Explore agent (using subagent_type: Explore) to research:

  • Existing code related to the feature area
  • Current patterns and conventions used
  • Integration points and dependencies
  • Similar implementations that could serve as reference

Example prompt for Explore agent:

Research the codebase to understand how [feature area] currently works.
Find:
1. All files related to [specific component/area]
2. Current data models and schemas
3. API endpoints or interfaces
4. Existing patterns for similar features
5. Test coverage in this area

Return specific file:line references for all findings.

Read the full file on GitHub · 595 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. 2d ago First seen · 595 lines · 11 tokens per session scan A 2af7b17e5040

Subscribe to this mod's changes

plan is a command published in the GitHub repository jeffh/claude-plugins (12 stars, last pushed 17d ago), licensed Apache-2.0. It adds 11 tokens to every session and 3,520 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 2026-08-30.