Speckit Plan

Overview

Create technical implementation plans with your chosen tech stack.

Execution Hooks

• •Bash: $CODEX_HOME/skills/speckit-plan/assets/scripts/bash/setup-plan.sh --json
• •PowerShell: $CODEX_HOME/skills/speckit-plan/assets/scripts/powershell/setup-plan.ps1 -Json
• •Agent script (bash): $CODEX_HOME/skills/speckit-plan/assets/scripts/bash/update-agent-context.sh __AGENT__
• •Agent script (PowerShell): $CODEX_HOME/skills/speckit-plan/assets/scripts/powershell/update-agent-context.ps1 -AgentType __AGENT__

Notes

• •Run from repo root.
• •Where the instructions mention {SCRIPT}, use the Bash command above.
• •Where the instructions mention {AGENT_SCRIPT}, use the agent script above.

Scripts

These scripts are bundled with this skill for cohesion:

• •assets/scripts/bash/
• •assets/scripts/powershell/

Zero-copy mode: run scripts directly from the skill path.

If you're in a non-git repo, run commands from the repo root so the scripts can infer it.

Templates

These templates are bundled with this skill for cohesion:

• •assets/templates/plan-template.md
• •assets/templates/agent-file-template.md

Zero-copy mode: templates are auto-detected from the skill path when running scripts.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Outline

1. •

   Setup: Run $CODEX_HOME/skills/speckit-plan/assets/scripts/bash/setup-plan.sh --json from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'''m Groot' (or double-quote if possible: "I'm Groot").

2. •

   Load context: Read FEATURE_SPEC and memory/constitution.md. Load IMPL_PLAN template (already copied).

3. •

   Execute plan workflow: Follow the structure in IMPL_PLAN template to:

   • •Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")
   • •Fill Constitution Check section from constitution
   • •Evaluate gates (ERROR if violations unjustified)
   • •Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION)
   • •Phase 1: Generate data-model.md, contracts/, quickstart.md
   • •Phase 1: Update agent context by running the agent script
   • •Re-evaluate Constitution Check post-design
4. •

   Stop and report: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.

Phases

Phase 0: Outline & Research

1. •

   Extract unknowns from Technical Context above:

   • •For each NEEDS CLARIFICATION → research task
   • •For each dependency → best practices task
   • •For each integration → patterns task
2. •

   Generate and dispatch research agents:

   text

   For each unknown in Technical Context:
     Task: "Research {unknown} for {feature context}"
   For each technology choice:
     Task: "Find best practices for {tech} in {domain}"
   

3. •

   Consolidate findings in research.md using format:

   • •Decision: [what was chosen]
   • •Rationale: [why chosen]
   • •Alternatives considered: [what else evaluated]

Output: research.md with all NEEDS CLARIFICATION resolved

Phase 1: Design & Contracts

Prerequisites: research.md complete

1. •

   Extract entities from feature spec → data-model.md:

   • •Entity name, fields, relationships
   • •Validation rules from requirements
   • •State transitions if applicable
2. •

   Generate API contracts from functional requirements:

   • •For each user action → endpoint
   • •Use standard REST/GraphQL patterns
   • •Output OpenAPI/GraphQL schema to /contracts/
3. •

   Agent context update:

   • •Run $CODEX_HOME/skills/speckit-plan/assets/scripts/bash/update-agent-context.sh __AGENT__
   • •These scripts detect which AI agent is in use
   • •Update the appropriate agent-specific context file
   • •Add only new technology from current plan
   • •Preserve manual additions between markers

Output: data-model.md, /contracts/*, quickstart.md, agent-specific file

Key rules

• •Use absolute paths
• •ERROR on gate failures or unresolved clarifications