sdk: Skill for Claude Code

.agents/skills/project-planning/SKILL.md

project-planning is a skill for Claude Code, Codex from WaniWani-AI/sdk. It costs 71 tokens per session (1,414 once invoked), scanned A, original, MIT.

A Linear project planner that breaks a project into smaller implementation tickets arranged by technical layer and dependency. Linear is a tool for managing projects and issues.

In plain words
What is it for?
It reviews a project, plans schema, types, API, backend, and UI work, shows dependencies and parallel work, then creates tickets after approval.
Why use it?
It removes the manual effort of turning a broad project idea into actionable tasks with clear ordering and ownership boundaries.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool; installed under .agents/ (shared by several agents).

This is WaniWani-AI/sdk's own configuration. It tells Claude Code and Codex 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/.agents/skills/project-planning/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/WaniWani-AI/sdk

Made for: Claude Code, Codex.

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/skills/waniwani-ai/sdk/project-planning/github.svg)](https://agentmods.dev/skills/waniwani-ai/sdk/project-planning)
Your own site
<a href="https://agentmods.dev/skills/waniwani-ai/sdk/project-planning"><img src="https://agentmods.dev/badge/skills/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/skills/waniwani-ai/sdk/project-planning"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/project-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,414 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00071 $0.01414
Opus 5 $0.00036 $0.00707
Sonnet 5 $0.00014 $0.00283
Haiku 4.5 $0.00007 $0.00141

Measured 10d ago against content hash a971a02cad10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

.agents/skills/project-planning/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Linear Project Planning

Create implementation tickets for the Linear project the user specifies (the text after the command, e.g. /project-planning User Notifications). If no project is named, ask which one.

Steps

  1. Fetch project details using mcp__linear__get_project with the project name the user gave.
  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 · 189 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. 10d ago First seen · 189 lines · 71 tokens per session scan A a971a02cad10

Subscribe to this mod's changes

project-planning is a skill published in the GitHub repository WaniWani-AI/sdk (17 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 1,414 once invoked, about $0.0004 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.

Related

Other skills, from other repositories