User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Pre-Execution Checks
Check for extension hooks (before planning):
- Check if
.specify/extensions.yml exists in the project root.
- If it exists, read it and look for entries under the
hooks.before_plan key
- If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
- Filter out hooks where
enabled is explicitly false. Treat hooks without an enabled field as enabled by default.
- For each remaining hook, do not attempt to interpret or evaluate hook
condition expressions:
- If the hook has no
condition field, or it is null/empty, treat the hook as executable
- If the hook defines a non-empty
condition, skip the hook and leave condition evaluation to the HookExecutor implementation
- For each executable hook, output the following based on its
optional flag:
- Optional hook (
optional: true):## Extension Hooks
**Optional Pre-Hook**: {extension}
Command: `/{command}`
Description: {description}
Prompt: {prompt}
To execute: `/{command}`
- Mandatory hook (
optional: false):## Extension Hooks
**Automatic Pre-Hook**: {extension}
Executing: `/{command}`
EXECUTE_COMMAND: {command}
Wait for the result of the hook command before proceeding to the Outline.
- If no hooks are registered or
.specify/extensions.yml does not exist, skip silently
Outline
Setup: Run .specify/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").
Load context: Read FEATURE_SPEC and .specify/memory/constitution.md. Load IMPL_PLAN template (already copied).
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
Stop and report: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.
Check for extension hooks: After reporting, check if .specify/extensions.yml exists in the project root.
- If it exists, read it and look for entries under the
hooks.after_plan key
- If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally
- Filter out hooks where
enabled is explicitly false. Treat hooks without an enabled field as enabled by default.
- For each remaining hook, do not attempt to interpret or evaluate hook
condition expressions:
- If the hook has no
condition field, or it is null/empty, treat the hook as executable
- If the hook defines a non-empty
condition, skip the hook and leave condition evaluation to the HookExecutor implementation
- For each executable hook, output the following based on its
optional flag:
- Optional hook (
optional: true):## Extension Hooks
**Optional Hook**: {extension}
Command: `/{command}`
Description: {description}
Prompt: {prompt}
To execute: `/{command}`
- Mandatory hook (
optional: false):## Extension Hooks
**Automatic Hook**: {extension}
Executing: `/{command}`
EXECUTE_COMMAND: {command}
- If no hooks are registered or
.specify/extensions.yml does not exist, skip silently
Phases
Phase 0: Outline & Research
Extract unknowns from Technical Context above:
- For each NEEDS CLARIFICATION → research task
- For each dependency → best practices task
- For each integration → patterns task
Generate and dispatch research agents:
For each unknown in Technical Context:
Task: "Research {unknown} for {feature context}"
For each technology choice:
Task: "Find best practices for {tech} in {domain}"
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
Extract entities from feature spec → data-model.md:
- Entity name, fields, relationships
- Validation rules from requirements
- State transitions if applicable
Define interface contracts (if project has external interfaces) → /contracts/:
- Identify what interfaces the project exposes to users or other systems
- Document the contract format appropriate for the project type
- Examples: public APIs for libraries, command schemas for CLI tools, endpoints for web services, grammars for parsers, UI contracts for applications
- Skip if project is purely internal (build scripts, one-off tools, etc.)
Agent context:
- Keep feature-specific implementation context in the feature's
plan.md. Do not write a feature-specific plan path into the repository-level AGENTS.md; repository-wide agent instructions must remain feature-neutral.
Output: data-model.md, /contracts/*, quickstart.md
Key rules
- Use absolute paths for filesystem operations; use project-relative paths for references in documentation and agent context files
- ERROR on gate failures or unresolved clarifications
1---2name: speckit-plan-43description: "Execute the implementation planning workflow using the plan template to generate design artifacts."4compatibility: "Requires spec-kit project structure with .specify/ directory"5metadata:6 author: "github-spec-kit"7 source: https://skillmd.com/skills/elsa-workflows/speckit-plan-48 upstream: "templates/commands/plan.md"9---101112## User Input1314```text15$ARGUMENTS16```1718You **MUST** consider the user input before proceeding (if not empty).1920## Pre-Execution Checks2122**Check for extension hooks (before planning)**:23- Check if `.specify/extensions.yml` exists in the project root.24- If it exists, read it and look for entries under the `hooks.before_plan` key25- If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally26- Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.27- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:28 - If the hook has no `condition` field, or it is null/empty, treat the hook as executable29 - If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation30- For each executable hook, output the following based on its `optional` flag:31 - **Optional hook** (`optional: true`):32 ```33 ## Extension Hooks3435 **Optional Pre-Hook**: {extension}36 Command: `/{command}`37 Description: {description}3839 Prompt: {prompt}40 To execute: `/{command}`41 ```42 - **Mandatory hook** (`optional: false`):43 ```44 ## Extension Hooks4546 **Automatic Pre-Hook**: {extension}47 Executing: `/{command}`48 EXECUTE_COMMAND: {command}4950 Wait for the result of the hook command before proceeding to the Outline.51 ```52- If no hooks are registered or `.specify/extensions.yml` does not exist, skip silently5354## Outline55561. **Setup**: Run `.specify/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").57582. **Load context**: Read FEATURE_SPEC and `.specify/memory/constitution.md`. Load IMPL_PLAN template (already copied).59603. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to:61 - Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")62 - Fill Constitution Check section from constitution63 - Evaluate gates (ERROR if violations unjustified)64 - Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION)65 - Phase 1: Generate data-model.md, contracts/, quickstart.md66 - Phase 1: Update agent context by running the agent script67 - Re-evaluate Constitution Check post-design68694. **Stop and report**: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.70715. **Check for extension hooks**: After reporting, check if `.specify/extensions.yml` exists in the project root.72 - If it exists, read it and look for entries under the `hooks.after_plan` key73 - If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally74 - Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.75 - For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:76 - If the hook has no `condition` field, or it is null/empty, treat the hook as executable77 - If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation78 - For each executable hook, output the following based on its `optional` flag:79 - **Optional hook** (`optional: true`):80 ```81 ## Extension Hooks8283 **Optional Hook**: {extension}84 Command: `/{command}`85 Description: {description}8687 Prompt: {prompt}88 To execute: `/{command}`89 ```90 - **Mandatory hook** (`optional: false`):91 ```92 ## Extension Hooks9394 **Automatic Hook**: {extension}95 Executing: `/{command}`96 EXECUTE_COMMAND: {command}97 ```98 - If no hooks are registered or `.specify/extensions.yml` does not exist, skip silently99100## Phases101102### Phase 0: Outline & Research1031041. **Extract unknowns from Technical Context** above:105 - For each NEEDS CLARIFICATION → research task106 - For each dependency → best practices task107 - For each integration → patterns task1081092. **Generate and dispatch research agents**:110111 ```text112 For each unknown in Technical Context:113 Task: "Research {unknown} for {feature context}"114 For each technology choice:115 Task: "Find best practices for {tech} in {domain}"116 ```1171183. **Consolidate findings** in `research.md` using format:119 - Decision: [what was chosen]120 - Rationale: [why chosen]121 - Alternatives considered: [what else evaluated]122123**Output**: research.md with all NEEDS CLARIFICATION resolved124125### Phase 1: Design & Contracts126127**Prerequisites:** `research.md` complete1281291. **Extract entities from feature spec** → `data-model.md`:130 - Entity name, fields, relationships131 - Validation rules from requirements132 - State transitions if applicable1331342. **Define interface contracts** (if project has external interfaces) → `/contracts/`:135 - Identify what interfaces the project exposes to users or other systems136 - Document the contract format appropriate for the project type137 - Examples: public APIs for libraries, command schemas for CLI tools, endpoints for web services, grammars for parsers, UI contracts for applications138 - Skip if project is purely internal (build scripts, one-off tools, etc.)1391403. **Agent context**:141 - Keep feature-specific implementation context in the feature's `plan.md`. Do not write a feature-specific plan path into the repository-level `AGENTS.md`; repository-wide agent instructions must remain feature-neutral.142143**Output**: data-model.md, /contracts/*, quickstart.md144145## Key rules146147- Use absolute paths for filesystem operations; use project-relative paths for references in documentation and agent context files148- ERROR on gate failures or unresolved clarifications