create_plan

create_plan is a command for Claude Code from spideynolove/claude-dotfiles. It costs 9 tokens per session (793 once invoked), scanned A, original, MIT.

A command for researching a coding task and producing a detailed implementation plan before code is written. It reads relevant files, checks existing patterns and tests, and asks only questions that the code cannot answer.

In plain words
What is it for?
Use it to plan a feature, bug fix, or larger code change, especially when several files, tests, or design choices are involved.
Why use it?
It reduces the risk of designing against an outdated or incomplete understanding of the project. The result records the requirements, constraints, and intended changes for review.

Command for Claude Code

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/spideynolove/claude-dotfiles/create_plan
Clone the repo
git clone --depth 1 https://github.com/spideynolove/claude-dotfiles

Made for: Claude Code.

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/spideynolove/claude-dotfiles/create_plan.svg)](https://agentmods.dev/commands/spideynolove/claude-dotfiles/create_plan)
Your own site
<a href="https://agentmods.dev/commands/spideynolove/claude-dotfiles/create_plan"><img src="https://agentmods.dev/badge/commands/spideynolove/claude-dotfiles/create_plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 793 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 $0.00009 $0.00793
Opus 5 $0.00005 $0.00396
Sonnet 5 $0.00002 $0.00159
Haiku 4.5 $0.00001 $0.00079

Measured 4d ago against content hash 816a3df3822d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

.claude-global-backup/commands/create_plan.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Plan

You are tasked with creating a detailed implementation plan through an interactive, iterative process. Be skeptical, thorough, and work collaboratively to produce a high-quality technical specification before any code is written.

Initial Response

If no parameters provided:

I'll help you create a detailed implementation plan. Please provide:
1. The task/feature description
2. Any relevant context or constraints
3. Links to related files or prior research

Tip: You can invoke directly with a description: `/create_plan add rate limiting to the API`

If parameters provided, proceed immediately to Step 1.

Process Steps

Step 1: Context Gathering

  1. Read ALL mentioned files COMPLETELY — no limit/offset, no partial reads
  2. Spawn parallel research agents to find relevant code, patterns, and tests
  3. Cross-reference requirements with actual codebase state
  4. Only ask questions that code investigation cannot answer:
    Based on my research, I understand we need to [accurate summary].
    
    Discovered:
    - [Finding with file:line reference]
    - [Pattern or constraint]
    
    Questions code can't answer:
    - [Business logic or design preference]
    

Step 2: Design Options

Present design alternatives with trade-offs before committing to an approach:

Design Options:
1. [Option A] — pros/cons
2. [Option B] — pros/cons

Which aligns with your vision?

Step 3: Plan Structure Approval

Before writing details, get buy-in on phasing:

Proposed phases:
1. [Phase] — [what it accomplishes]
2. [Phase] — [what it accomplishes]

Does this phasing make sense?

Step 4: Write the Plan

Save to .claude/plans/YYYY-MM-DD-description.md using this template:

# [Feature] Implementation Plan

## Overview
[1-2 sentence summary]

## Current State Analysis
[What exists, what's missing, key constraints with file:line refs]

### Key Discoveries:
- [Finding: file:line]

## Desired End State
[Specification of done state and how to verify it]

## What We're NOT Doing
[Explicit scope exclusions]

## Implementation Approach
[Strategy and reasoning]

## Phase 1: [Name]

### Changes Required:
#### 1. [Component]
**File**: `path/to/file`
**Changes**: [summary]

### Success Criteria:

#### Automated Verification:
- [ ] Tests pass: `[command]`
- [ ] Type/lint checks pass: `[command]`

#### Manual Verification:
- [ ] [Human-required check]

**Implementation Note**: Pause after automated verification passes. Human confirms manual steps before Phase 2.

---

## Phase 2: [Name]
[Same structure]

---

## Testing Strategy
[Unit, integration, manual steps]

## References
- [file:line or research doc]

Read the full file on GitHub · 138 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. 4d ago First seen · 138 lines · 9 tokens per session scan A 816a3df3822d

Subscribe to this mod's changes

create_plan is a command published in the GitHub repository spideynolove/claude-dotfiles (2 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 793 once invoked, about $0.0000 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.