sdk: Command for Claude Code

.claude/commands/project-planning.md

project-planning is a command for Claude Code from WaniWani-AI/sdk. It costs 12 tokens per session (1,334 once invoked), scanned A, original, MIT.

A command that turns a Linear project description into small implementation tickets. Linear is a tool for tracking software projects and issues.

In plain words
What is it for?
Use it to plan database, type, API, backend, and user-interface work, review the proposed ticket breakdown, and request approval before ticket creation.
Why use it?
It breaks a broad project into individually actionable work, with dependencies showing which tasks must come first.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

This is WaniWani-AI/sdk's own configuration. It tells Claude Code how to work on sdk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to WaniWani-AI/sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/WaniWani-AI/sdk/main/.claude/commands/project-planning.md
Clone the repo
git clone --depth 1 https://github.com/WaniWani-AI/sdk

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 project-planning

README.md
[![agentmods](https://agentmods.dev/badge/commands/waniwani-ai/sdk/project-planning/github.svg)](https://agentmods.dev/commands/waniwani-ai/sdk/project-planning)
Your own site
<a href="https://agentmods.dev/commands/waniwani-ai/sdk/project-planning"><img src="https://agentmods.dev/badge/commands/waniwani-ai/sdk/project-planning/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for project-planning

Your own site · 80×15
<a href="https://agentmods.dev/commands/waniwani-ai/sdk/project-planning"><img src="https://agentmods.dev/badge/commands/waniwani-ai/sdk/project-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,334 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00012 $0.01334
Opus 5 $0.00006 $0.00667
Sonnet 5 $0.00002 $0.00267
Haiku 4.5 $0.00001 $0.00133

Measured 9d ago against content hash 0f2d761c2909, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

project-planning 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 9d 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/commands/project-planning.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create implementation tickets for the Linear project specified in $ARGUMENTS.

Steps

  1. Fetch project details using mcp__linear__get_project with the project name from $ARGUMENTS
  2. Fetch team info using mcp__linear__list_teams to get the team ID for creating issues
  3. Analyze the project description to understand:
    • The overall goal and scope
    • Key implementation areas (database, API, UI, etc.)
    • Dependencies between components
  4. Break down into atomic tickets following these principles:
    • Each ticket should be completable by a single agent in isolation
    • Tickets should have clear inputs and outputs
    • Dependencies should be explicit (use Linear's blocking relations)
    • Group by layer: Schema → Types → API → Backend Logic → UI
  5. Present the plan for approval - Show the user the complete ticket breakdown:
    • Display each planned ticket with title and description summary
    • Show the dependency graph (what blocks what)
    • Highlight parallelization opportunities
    • Ask the user to approve before proceeding
  6. Wait for user approval - Use AskUserQuestion to get explicit confirmation:
    • Option to approve and create all tickets
    • Option to request modifications to the plan
    • Option to cancel
  7. Create tickets in Linear (only after approval) using mcp__linear__create_issue for each ticket
  8. Set up dependencies using the blocks parameter when creating issues
  9. Summarize the created tickets to the user

Plan Presentation Format

Before creating tickets, present the plan to the user in this format:

## Proposed Implementation Plan for [Project Name]

### Summary
[Brief overview of the approach and total number of tickets]

### Ticket Breakdown

#### Layer 1: Database (X tickets)
1. **[Title]** - [One-line description]
2. **[Title]** - [One-line description]

#### Layer 2: Types (X tickets)
3. **[Title]** - [One-line description]
   - Blocked by: #1

#### Layer 3: API (X tickets)
4. **[Title]** - [One-line description]
   - Blocked by: #1, #3

[Continue for all layers...]

### Dependency Graph

    #1 Database Schema
     ├── #3 Types (blocked by #1)
     │    └── #5 Service (blocked by #3, #4)
     └── #4 API Endpoints (blocked by #1)
          └── #6 UI Components (blocked by #4)
    #2 Config Setup (independent)

### Parallelization Opportunities
- **Phase 1** (can start immediately): #1, #2
- **Phase 2** (after Phase 1): #3, #4
- **Phase 3** (after Phase 2): #5, #6

Read the full file on GitHub · 176 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. 9d ago First seen · 176 lines · 12 tokens per session scan A 0f2d761c2909

Subscribe to this mod's changes

project-planning is a command published in the GitHub repository WaniWani-AI/sdk (17 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 1,334 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.