create_plan

A command for turning a coding task into a detailed implementation plan through codebase research, questions, design choices, and review.

In plain words
What is it for?
Use it before starting a substantial change when you need to locate relevant code, understand how it works, compare approaches, and agree on the steps.
Why use it?
It reduces unknowns before coding and records both automated checks and hands-on checks needed to confirm the work is complete.

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/pyrex41/skill-manager/create_plan
Clone the repo
git clone --depth 1 https://github.com/pyrex41/skill-manager

Made for: Claude Code.

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 746 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 $0.00746
Opus 5 $0.00005 $0.00373
Sonnet 5 $0.00002 $0.00149
Haiku 4.5 $0.00001 $0.00075

Measured yesterday against content hash de7c79090991, 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 yesterday.

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/commands/cl/create_plan.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Implementation Plan

You are tasked with creating a detailed, actionable implementation plan through collaborative research and iteration.

Philosophy

Be skeptical and thorough. Plans should:

  • Eliminate all open questions before finalization
  • Be based on deep understanding of the existing codebase
  • Include both automated and manual success criteria
  • Be iterative - seek feedback at each phase

Process

Phase 1: Context Gathering

  1. Read all mentioned files completely - Never use limit/offset, you need full context
  2. Spawn parallel research agents to understand the codebase:
    • Use codebase-locator to find WHERE relevant code lives
    • Use codebase-analyzer to understand HOW specific code works
    • Use thoughts-locator to find existing documentation
  3. Present your understanding with focused questions for clarification

Phase 2: Research & Discovery

  1. Verify any user corrections through new research
  2. Create a todo list to track exploration
  3. Spawn concurrent sub-tasks for comprehensive investigation
  4. Present findings with design options when multiple approaches exist

Phase 3: Plan Structure Development

  1. Propose phasing before detailed writing
  2. Seek feedback on organization and granularity
  3. Identify dependencies between phases

Phase 4: Detailed Plan Writing

Create a markdown document with this structure:

# Plan: [Feature/Task Name]

## Overview
[2-3 sentence summary of what this plan accomplishes]

## Current State Analysis
[What exists today, relevant code locations]

## Desired End State
[Clear description of the goal]

## Implementation Approach
[High-level strategy]

## Phases

### Phase 1: [Name]
**Goal**: [What this phase accomplishes]

**Changes**:
- [ ] Change 1 (`file:line`)
- [ ] Change 2 (`file:line`)

**Success Criteria - Automated**:
- [ ] `make check` passes
- [ ] `make test` passes
- [ ] Specific test case passes

**Success Criteria - Manual**:
- [ ] UI shows expected behavior
- [ ] Edge case X works correctly

### Phase 2: [Name]
[Continue pattern...]

## Open Questions
[MUST be empty before plan is finalized]

## Risks and Mitigations
[Known risks and how to handle them]

Read the full file on GitHub · 122 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. yesterday First seen · 122 lines · 9 tokens per session scan A de7c79090991

Subscribe to this mod's changes

create_plan is a command published in the GitHub repository pyrex41/skill-manager (3 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 746 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.