Planner
Turn a vague feature or bug request into a researched, phased plan with sprints and atomic tasks before your agent starts coding.
Overview
planner is an agent skill most often used in Build (also Validate scope, Ship launch prep) that researches the codebase, clarifies requirements, and writes phased sprint plans with atomic tasks.
Install
npx skills add https://github.com/am-will/codex-skills --skill plannerWhat is this skill?
- Explicit triggers: "make a plan", "/planner", "/plan", and similar natural-language planning requests
- Phase 0: codebase architecture scan, similar implementations, dependencies, related components
- Phase 1: 5–10 clarification questions across goals, scope, platforms, auth, testing, and risk before doc search
- Produces comprehensive phased implementation plans with sprints and atomic tasks
- Analyzes security, performance, UX, and edge cases before tasks are assigned
- Phase 0 research and Phase 1 clarification before documentation search
- 5–10 suggested clarification question categories
Adoption & trust: 1.2k installs on skills.sh; 941 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know what you want built but lack an ordered, repo-aware plan your agent can follow without thrashing.
Who is it for?
Solo builders starting a non-trivial feature or bugfix who want codebase-informed planning and explicit scope questions first.
Skip if: One-line tweaks with obvious steps, or situations where requirements and acceptance criteria are already frozen in an approved spec.
When should I use this skill?
User asks to make, create, design, draft, or write a plan, break work into tasks, or uses /planner or /plan.
What do I get? / Deliverables
You get a clarified, phased implementation plan with sprints and atomic tasks ready to hand off to coding or execution skills.
- Phased implementation plan
- Sprint breakdown with atomic tasks
- Clarification question list
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Implementation planning with codebase research is where builders most often invoke it, so Build / pm is the primary shelf even though planning starts earlier. PM subphase captures phased sprints, clarification questions, and task breakdown rather than frontend or backend implementation itself.
Where it fits
Clarify goals, non-goals, and success metrics before committing to a multi-week feature.
Map repo patterns and draft sprint-sized tasks for an API integration.
Plan a migration with dependency and auth questions resolved before touching schema code.
Outline launch steps, testing gates, and rollback tasks before release week.
How it compares
Use instead of ad-hoc chat planning when you want structured Phase 0 research and mandatory clarification before tasks are listed.
Common Questions / FAQ
Who is planner for?
Indie developers and small teams using Codex-style agents who need implementation plans grounded in the actual repo, not generic checklists.
When should I use planner?
In Validate when scoping a feature; in Build pm when breaking work into sprints; before large refactors or integrations; whenever you say "make a plan", "plan this out", or run /planner.
Is planner safe to install?
It guides research and questioning in your workspace; review the Security Audits panel on this Prism page and avoid pasting secrets into planning prompts.
SKILL.md
READMESKILL.md - Planner
# Planner Agent Create detailed, phased implementation plans for bugs, features, or tasks. ## Process ### Phase 0: Research 1. **Investigate the codebase:** - Architecture and patterns - Similar existing implementations - Dependencies and frameworks - Related components 2. **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: 1. Goals & success criteria 2. Scope & non‑goals 3. Users & core workflows 4. Platforms & environments 5. Tech constraints 6. Data & integrations 7. Auth & permissions 8. Performance & reliability 9. Testing & validation 10. 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: 1. Extract keywords 2. Convert to kebab-case 3. Add `-plan.md` suffix 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 ```markdown # 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 & Go