plan

A short planning command for analysing a task before implementation. It is intended for small planning jobs rather than a full software-development process.

In plain words
What is it for?
Planning a feature, bug fix, or refactor, identifying constraints, evaluating approaches, and waiting for the user's choice.
Why use it?
It encourages clarification, research, and comparison of options before any code is changed.

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/qwickapps/ai-sdlc-workflows/plan
Clone the repo
git clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflows

Made for: Claude Code.

Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 699 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 $0.00006 $0.00699
Opus 5 $0.00003 $0.00349
Sonnet 5 $0.00001 $0.00140
Haiku 4.5 $0.00001 $0.00070

Measured 2d ago against content hash bc660640127e, 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.

claude/.claude/commands/plan.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quick Planning Mode

You are now in Planning Mode. Use this for quick analysis before action.

Input: $ARGUMENTS (task description, question, or problem to analyze)

Purpose

This is a lightweight planning workflow for tasks that don't need full SDLC. Use /feature, /bug, /refactor for more structured workflows.

CRITICAL RULES

  1. Analyze before acting - never jump straight to implementation (see RESEARCH-DEPTH.md)
  2. Present options - don't assume one approach is correct
  3. Wait for approval - user decides the direction
  4. Think like architect + PM + UX designer
  5. When blocked or uncertain - STOP and discuss (see COMMUNICATION-PROTOCOL.md)
  6. Research thoroughly - use Explore agent, QwickBrain MCP (see RESEARCH-DEPTH.md)

Interactive Setup

Check if $ARGUMENTS is provided.

If $ARGUMENTS is empty, ask:

"What would you like me to plan or analyze? Please describe:

  • The task or problem
  • Any constraints or preferences
  • What outcome you're looking for"

Wait for response before proceeding.

Planning Process

Step 1: Understand the Request

Ask yourself (and user if unclear):

  • What is being asked?
  • What problem does this solve?
  • What are the constraints?
  • What existing solutions might help? (REUSE FIRST)

Step 2: Analyze Options

For any non-trivial task, identify:

  • Option A: [approach with pros/cons]
  • Option B: [approach with pros/cons]
  • Recommended: [which and why]

Consider:

  • Complexity vs simplicity
  • Breaking changes vs backwards compatibility
  • Time to implement
  • Risk and unknowns

Step 3: Present Plan

Format:

## Analysis

**Understanding:** [restate the request]

**Existing solutions:** [what can be reused]

## Options

### Option A: [name]

- Approach: [description]
- Pros: [list]
- Cons: [list]

### Option B: [name]

- Approach: [description]
- Pros: [list]
- Cons: [list]

## Recommendation

[Which option and why]

## Implementation Steps

1. [step 1]
2. [step 2]
3. [step 3]

---

Approve this plan to proceed, or provide feedback.

Read the full file on GitHub · 129 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 · 129 lines · 6 tokens per session scan A bc660640127e

Subscribe to this mod's changes

plan is a command published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 6 tokens to every session and 699 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.