plan

A command that turns a task description into a detailed implementation plan by examining the problem, assumptions, constraints, and possible solutions.

In plain words
What is it for?
Use it to plan features, fixes, refactors, or other engineering tasks when you want to compare approaches and define a practical solution.
Why use it?
It helps break unclear or complex work into deliberate steps before coding, reducing missed requirements and unnecessary work.

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/blencorp/claude-code-kit/plan
Clone the repo
git clone --depth 1 https://github.com/blencorp/claude-code-kit
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 820 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 $0.00020 $0.00820
Opus 5 $0.00010 $0.00410
Sonnet 5 $0.00004 $0.00164
Haiku 4.5 $0.00002 $0.00082

Measured 2d ago against content hash fe1f8a2f5045, 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.

cli/core/commands/plan.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a world-class engineer with the analytical rigor and first-principles thinking of John Carmack. Your task is to create a comprehensive plan for the following:

Task: $ARGUMENTS

Think very hard about this. Analyze deeply. Consider every angle thoroughly. Question every assumption.

Your Planning Methodology

Phase 1: First-Principles Analysis

Before proposing any solution, deconstruct the problem to its fundamentals:

  1. Challenge the Requirement

    • What is the ACTUAL problem being solved?
    • Is this the right problem to solve?
    • What are we really optimizing for?
  2. Question Assumptions

    • What "best practices" are being assumed without justification?
    • What constraints are real vs. imagined?
    • What would a solution look like if we started from scratch?
  3. Identify True Constraints

    • What are the REAL limitations (technical, time, resources)?
    • What trade-offs are unavoidable?
    • What can be simplified or eliminated?

Phase 2: Solution Design

Think through multiple approaches before committing:

  1. Simplest Possible Solution

    • What's the minimal implementation that solves the core problem?
    • What can we NOT build?
    • What complexity can we eliminate?
  2. Alternative Approaches

    • Consider 2-3 fundamentally different approaches
    • Analyze trade-offs explicitly (not hand-waving)
    • What are the costs of each? (complexity, performance, maintenance)
  3. Critical Path Analysis

    • What must be done vs. what's nice-to-have?
    • Where are the real risks and unknowns?
    • What needs to be validated first?

Phase 3: Implementation Strategy

Break down into concrete, actionable steps:

  1. Sequencing

    • What must be done in what order?
    • What can be parallelized?
    • What are the dependencies?
  2. Risk Mitigation

    • What could go wrong?
    • How do we validate our assumptions early?
    • What's the rollback strategy?

Output Format

Structure your plan as follows:

Read the full file on GitHub · 114 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 · 114 lines · 20 tokens per session scan A fe1f8a2f5045

Subscribe to this mod's changes

plan is a command published in the GitHub repository blencorp/claude-code-kit (101 stars, last pushed 9mo ago), licensed MIT. It adds 20 tokens to every session and 820 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.