planner
am-will/codex-skills
Create comprehensive, phased implementation plans with sprints and atomic tasks.
What is planner?
The planner skill helps you break down complex features, bugs, or tasks into detailed, phased implementation plans. Use it when you need structured guidance on how to approach a project, with clear sprints, atomic tasks, and validation steps.
- Investigates codebase architecture and similar implementations to inform planning
- Clarifies requirements through targeted questions before drafting the plan
- Retrieves official documentation for external libraries and frameworks to ensure accuracy
- Structures plans into logical sprints that each produce demoable, testable increments
- Breaks sprints into atomic, committable tasks with clear inputs, outputs, and acceptance criteria
- Identifies potential risks, gotchas, and edge cases after plan creation
How to install planner
npx skills add https://github.com/am-will/codex-skills --skill plannerHow to use planner
- 1.Describe what you want to plan (feature, bug fix, task, or refactor)
- 2.Answer clarifying questions about goals, scope, constraints, and success criteria
- 3.Review the generated plan with sprints, tasks, and validation steps
- 4.Use the plan to guide implementation, checking off tasks as you complete them
Use cases
- Planning the implementation of a new feature across multiple sprints
- Breaking down a bug fix into specific, testable tasks with clear dependencies
- Designing a phased rollout for integrating a third-party API or library
- Structuring a refactoring effort with validation checkpoints between phases
- Creating a detailed roadmap for authentication or payment system implementation
- Software engineers planning complex features or refactors
- Technical leads designing phased implementation strategies
- Developers working on unfamiliar codebases who need structured guidance
- Teams coordinating parallel work across multiple sprints
planner FAQ
A sprint is a logical phase that produces a demoable, runnable increment. A task is an atomic, committable unit of work within a sprint—small enough to complete and test independently.
No. Answer the questions most relevant to your project. The planner uses best judgment to prioritize ambiguity and risk reduction, so focus on areas of uncertainty.
No. The planner only creates the plan document. You use it as a guide for implementation.
The planner skips the documentation retrieval phase and focuses on codebase investigation and requirement clarification instead.
Tasks are specific and actionable, including file paths, dependencies, acceptance criteria, and validation methods—detailed enough to guide implementation without ambiguity.
Full instructions (SKILL.md)
Source of truth, from am-will/codex-skills.
name: planner description: > Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.
Planner Agent
Create detailed, phased implementation plans for bugs, features, or tasks.
Process
Phase 0: Research
-
Investigate the codebase:
- Architecture and patterns
- Similar existing implementations
- Dependencies and frameworks
- Related components
-
Analyze the request:
- Core requirements
- Challenges & edge cases
- Security/performance/UX considerations
Phase 1: Clarify Requirements
Before doing ANY documentation search: clarify requirements with user. This will narrow and aid you in finding the right docs.
Think of 5-10 questions that will help you generate the best plan possible.
Here are suggested example categories, but not a strict or exhaustive list. You may ask anything helpful. Use best judgement & prioritize ambiguity and risk reduction:
- Goals & success criteria
- Scope & non‑goals
- Users & core workflows
- Platforms & environments
- Tech constraints
- Data & integrations
- Auth & permissions
- Performance & reliability
- Testing & validation
- Ask any helpful question
Phase 2: Retrieve Documentation
When the plan involves any external library, API, framework, or service, use the Context7 skill to fetch the latest official docs before drafting tasks. This ensures version‑accurate steps, correct parameters, and current best practices. If no external dependencies apply, skip this phase.
Phase 3: Create Plan
Structure
- Overview: Brief summary and approach
- Sprints: Logical phases that build on each other
- Tasks: Specific, actionable items within sprints
Sprint Requirements
Each sprint must:
- Result in demoable, runnable, testable increment
- Build on prior sprint work
- Include demo/verification checklist
Task Requirements
Each task must be:
- Atomic and committable (small, independent)
- Specific with clear inputs/outputs
- Independently testable
- Include file paths when relevant
- Include dependencies for parallel execution
- Include tests or validation method
Bad: "Implement Google OAuth" Good:
- "Add Google OAuth config to env variables"
- "Install passport-google-oauth20 package"
- "Create OAuth callback route in src/routes/auth.ts"
- "Add Google sign-in button to login UI"
Phase 3: Save
Save the file
Generate filename from request:
- Extract keywords
- Convert to kebab-case
- Add
-plan.mdsuffix
Examples:
- "fix xyz bug" →
xyz-bug-plan.md
Phase 4: Gotchas
AFTER it is saved. Identify potential issues & edge cases in plan. Address proactively. Where could smth go wrong? What about the plan is ambiguous? Missing step, dependency, or pitfall?
If any gotchas found, stop & ask up to 3 more questions. (either w/ request_user_input or directly)
Refine the plan if any additional useful info is provided.
Plan Template
# Plan: [Task Name]
**Generated**: [Date]
**Estimated Complexity**: [Low/Medium/High]
## Overview
[Summary of task and approach]
## Prerequisites
- [Dependencies or requirements]
- [Tools, libraries, access needed]
## Sprint 1: [Name]
**Goal**: [What this accomplishes]
**Demo/Validation**:
- [How to run/demo]
- [What to verify]
### Task 1.1: [Name]
- **Location**: [File paths]
- **Description**: [What to do]
- **Dependencies**: [Previous tasks]
- **Acceptance Criteria**:
- [Specific criteria]
- **Validation**:
- [Tests or verification]
### Task 1.2: [Name]
[...]
## Sprint 2: [Name]
[...]
## Testing Strategy
- [How to test]
- [What to verify per sprint]
## Potential Risks & Gotchas
- [What could go wrong]
- [Mitigation strategies]
## Rollback Plan
- [How to undo if needed]
Important
- Think about full lifecycle: implementation, testing, deployment
- Consider non-functional requirements
- Show user summary and file path when done
- Do NOT implement - only create the plan
Related skills
More from am-will/codex-skills and the wider catalog.

read-github
Read and search GitHub repository documentation via gitmcp.io MCP service.

role-creator
Create and manage custom Codex agents via standalone TOML configuration files.

super-swarm-spark
Orchestrate parallel task execution across up to 12 concurrent Sparky subagents from a markdown plan.

swarm-planner
Creates dependency-aware implementation plans optimized for parallel multi-agent execution.

tdd-test-writer
Writes failing tests first for test-driven development and hands off a strict implementation contract that requires agents to make those tests pass without weakening the tests. Use when users ask for test-first workflows, RED/GREEN cycles, or behavior-gating tasks with automated tests.

vega-multi-tv-migration
Migrate Fire TV apps to multi-platform React Native monorepos supporting Android TV, Apple TV, and Vega OS.