plan

An interactive command for creating a detailed implementation plan before changing a codebase.

In plain words
What is it for?
Use it with a task description or research document to prepare a structured plan, including relevant project notes and referenced files.
Why use it?
It makes requirements, project context, related research, and planned work explicit before implementation begins.

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/eveld/claude/plan
Clone the repo
git clone --depth 1 https://github.com/eveld/claude
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 806 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 $0.00000 $0.00806
Opus 5 $0.00000 $0.00403
Sonnet 5 $0.00000 $0.00161
Haiku 4.5 $0.00000 $0.00081

Measured 2d ago against content hash 1582ba8520d6, 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.

commands/plan.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Plan

You are creating a detailed implementation plan through an interactive process.

Initial Response

Check if parameters were provided:

  • If file path provided: Read FULLY and check format
    • Personal format: thoughts/{namespace}/NNNN-description/research.md
    • Shared format: thoughts/shared/NNNN-description/research.md
    • Old format: thoughts/shared/research/YYYY-MM-DD-NN-*.md
  • If no parameters: Show usage message and wait

Usage message:

I'll help you create a detailed implementation plan. Please provide:
1. The task/ticket description (or path to research/ticket file)
2. Any relevant context or requirements
3. Links to related research

Tip: You can invoke with a file: `/plan thoughts/erik/0005-authentication/research.md`
Tip: Shared docs work too: `/plan thoughts/shared/0042-authentication/research.md`
Tip: Old paths also work: `/plan thoughts/shared/research/2026-02-03-01-auth.md`

Workflow

Step 1: Read Context

  • Read ticket and any mentioned files FULLY (no limit/offset)
  • Read in main context before spawning agents

Step 2: Discover Project Context (if needed)

  • Check if thoughts/notes/commands.md exists
    • If not: Use discover-project-commands skill to create it
  • Check if thoughts/notes/testing.md exists
    • If not: Use discover-test-patterns skill to create it
  • These reference docs improve plan quality and success criteria

Step 3: Initial Research

  • Use spawn-planning-agents skill to gather context
  • Spawn parallel agents to find existing code, patterns, documentation
  • Wait for all agents to complete

Step 4: Read Agent Findings

  • Read all files identified by research agents FULLY
  • Verify understanding against actual code

Step 5: Ask Clarifying Questions

  • Present informed understanding
  • Ask only questions that code can't answer
  • Use AskUserQuestion tool for technical choices

Step 6: Deeper Research (if needed)

  • If user corrects misunderstanding, spawn new research
  • Verify facts before proceeding

Read the full file on GitHub · 93 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 · 93 lines · 0 tokens per session scan A 1582ba8520d6

Subscribe to this mod's changes

plan is a command published in the GitHub repository eveld/claude (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 806 tokens. 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.