create-plan

create-plan is a command for Claude Code from davistroy/claude-marketplace. It costs 22 tokens per session (6,894 once invoked), scanned A, original, MIT.

A command that turns requirements and design documents—such as a business requirements document, product requirements document, or technical design document—into a phased implementation plan.

In plain words
What is it for?
Use it to discover project specifications, survey the codebase, summarize scope for approval, and create an IMPLEMENTATION_PLAN.md for later execution.
Why use it?
It connects written requirements to the existing codebase, reducing the chance of missing existing functionality, test constraints, assumptions, or acceptance criteria.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

Part of the personal-plugin plugin — 29 skills, 23 commands, 10 agents, 2 hooks shipped together

Good fit Use it to discover project specifications, survey the codebase, summarize scope for approval, and create an IMPLEMENTATION_PLAN.md for later execution.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/davistroy/claude-marketplace/create-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/davistroy/claude-marketplace

Made for: Claude Code.

Or install personal-plugin, the plugin that ships this one along with the rest of its 29 skills, 23 commands, 10 agents, 2 hooks.

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 create-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/davistroy/claude-marketplace/create-plan/github.svg)](https://agentmods.dev/commands/davistroy/claude-marketplace/create-plan)
Your own site
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/create-plan"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/create-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 create-plan

Your own site · 80×15
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/create-plan"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/create-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,894 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 $0.00022 $0.06894
Opus 5 $0.00011 $0.03447
Sonnet 5 $0.00004 $0.01379
Haiku 4.5 $0.00002 $0.00689

Measured 9d ago against content hash 87a506812f87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

create-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 9d 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/personal-plugin/commands/create-plan.md · 471 lines

How it starts

The opening of the file, as written. The whole thing — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Plan Command

Generate a comprehensive, phased implementation plan from requirements and design documents in the project. This command discovers and analyzes BRDs, PRDs, TDDs, and other specification documents, then produces an actionable IMPLEMENTATION_PLAN.md ready for execution with /implement-plan.

Overview

This command:

  1. Discovers requirements and design documents in the project
  2. Surveys the existing codebase to detect tech stack, test infrastructure, and already-implemented features
  3. Analyzes and synthesizes requirements across all documents, accounting for existing code
  4. Presents a scope summary (features, phases, assumptions) and waits for user approval before proceeding
  5. Breaks down work into appropriately-sized phases
  6. Generates detailed work items with acceptance criteria
  7. Outputs IMPLEMENTATION_PLAN.md to the repository root

See also: /plan-improvements for codebase-driven improvement analysis. /ultra-plan for deep pre-planning when requirements are vague, scope is ambiguous, or the problem needs investigation before a plan can be written. Use /implement-plan to execute the generated plan; for large plans (6+ phases or 20+ independent work items), set Execution Mode: Parallel or Worktree-Isolated in the Phase Summary Table so /implement-plan dispatches those phases as concurrent background agents in isolated worktrees.

Input Validation

Arguments: None required

Optional Arguments:

  • <document-paths> - Specific documents to use (space-separated)
  • --output <path> - Custom output path (default: IMPLEMENTATION_PLAN.md)
  • --phases <n> - Target number of phases (default: auto-calculated)
  • --max-phases <n> - Maximum number of phases to generate (default: 8). Overrides --phases if --phases exceeds this limit.
  • --verbose - Show detailed analysis during generation

Examples:

/create-plan                              # Auto-discover documents
/create-plan PRD.md TDD.md               # Use specific documents
/create-plan --phases 5                   # Target 5 phases
/create-plan docs/requirements/*.md       # Use glob pattern

Read the full file on GitHub · 471 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. 9d ago First seen · 471 lines · 22 tokens per session scan A 87a506812f87

Subscribe to this mod's changes

create-plan is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 6,894 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.