Node / meshtastic / Meshtastic-Android / files / .github / agents / speckit.plan.agent.md

Displaying Raw • View rendered • Download

---

description: Execute the implementation planning workflow using the plan template to generate design artifacts.

handoffs:

Tff7b72- label: Create Tasks

agent: speckit.tasks

prompt: Break the plan into tasks

send: true

Tff7b72- label: Create Checklist

agent: speckit.checklist

Tc9d1d9 prompt: Create a checklist for the following domain...

Tc9d1d9---

Tc9d1d9## User Input

Ta5d6ff```Ta5d6fftext

$ARGUMENTS

Ta5d6ff```

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

Tc9d1d9## Pre-Execution Checks

**Check for extension hooks (before planning)**:

Tff7b72- Check if Ta5d6ff`.specify/extensions.yml` exists in the project root.

Tff7b72- If it exists, read it and look for entries under the Ta5d6ff`hooks.before_plan` key

Tff7b72- If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally

Tff7b72- Filter out hooks where Ta5d6ff`enabled` is explicitly Ta5d6ff`false`. Treat hooks without an Ta5d6ff`enabled` field as enabled by default.

Tff7b72- For each remaining hook, do **not** attempt to interpret or evaluate hook Ta5d6ff`condition` expressions:

Tff7b72- If the hook has no Ta5d6ff`condition` field, or it is null/empty, treat the hook as executable

Tff7b72- If the hook defines a non-empty Ta5d6ff`condition`, skip the hook and leave condition evaluation to the HookExecutor implementation

Tff7b72- For each executable hook, output the following based on its Ta5d6ff`optional` flag:

Tff7b72- **Optional hook** (Ta5d6ff`optional: true`):

Ta5d6ff ```

## Extension Hooks

**Optional Pre-Hook**: {extension}

Command: `/{command}`

Description: {description}

Prompt: {prompt}

To execute: `/{command}`

```

Tff7b72- **Mandatory hook** (Ta5d6ff`optional: false`):

Ta5d6ff ```

## Extension Hooks

**Automatic Pre-Hook**: {extension}

Executing: `/{command}`

EXECUTE_COMMAND: {command}

Wait for the result of the hook command before proceeding to the Outline.

```

Tff7b72- If no hooks are registered or Ta5d6ff`.specify/extensions.yml` does not exist, skip silently

Tc9d1d9## Outline

Tff7b721. **Setup**: Run Ta5d6ff`.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").

Tff7b722. **Load context**: Read FEATURE_SPEC and Ta5d6ff`.specify/memory/constitution.md`. Load IMPL_PLAN template (already copied).

Tff7b723. **Execute plan workflow**: Follow the structure in IMPL_PLAN template to:

Tff7b72- Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")

Tff7b72- Fill Constitution Check section from constitution

Tff7b72- Evaluate gates (ERROR if violations unjustified)

Tff7b72- Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION)

Tff7b72- Phase 1: Generate data-model.md, contracts/, quickstart.md

Tff7b72- Phase 1: Update agent context by running the agent script

Tff7b72- Re-evaluate Constitution Check post-design

Tff7b724. **Stop and report**: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.

Tff7b725. **Check for extension hooks**: After reporting, check if Ta5d6ff`.specify/extensions.yml` exists in the project root.

Tff7b72- If it exists, read it and look for entries under the Ta5d6ff`hooks.after_plan` key

Tff7b72- If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normally

Tff7b72- Filter out hooks where Ta5d6ff`enabled` is explicitly Ta5d6ff`false`. Treat hooks without an Ta5d6ff`enabled` field as enabled by default.

Tff7b72- For each remaining hook, do **not** attempt to interpret or evaluate hook Ta5d6ff`condition` expressions:

Tff7b72- If the hook has no Ta5d6ff`condition` field, or it is null/empty, treat the hook as executable

Tff7b72- If the hook defines a non-empty Ta5d6ff`condition`, skip the hook and leave condition evaluation to the HookExecutor implementation

Tff7b72- For each executable hook, output the following based on its Ta5d6ff`optional` flag:

Tff7b72- **Optional hook** (Ta5d6ff`optional: true`):

Ta5d6ff ```

## Extension Hooks

**Optional Hook**: {extension}

Command: `/{command}`

Description: {description}

Prompt: {prompt}

To execute: `/{command}`

```

Tff7b72- **Mandatory hook** (Ta5d6ff`optional: false`):

Ta5d6ff ```

## Extension Hooks

**Automatic Hook**: {extension}

Executing: `/{command}`

EXECUTE_COMMAND: {command}

```

Tff7b72- If no hooks are registered or Ta5d6ff`.specify/extensions.yml` does not exist, skip silently

Tc9d1d9## Phases

Tc9d1d9### Phase 0: Outline & Research

Tff7b721. **Extract unknowns from Technical Context** above:

Tff7b72- For each NEEDS CLARIFICATION → research task

Tff7b72- For each dependency → best practices task

Tff7b72- For each integration → patterns task

Tff7b722. **Generate and dispatch research agents**:

Ta5d6ff ```Ta5d6fftext

For each unknown in Technical Context:

Task: "Research {unknown} for {feature context}"

For each technology choice:

Task: "Find best practices for {tech} in {domain}"

Ta5d6ff ```

Tff7b723. **Consolidate findings** in Ta5d6ff`research.md` using format:

Tff7b72- Decision: [what was chosen]

Tff7b72- Rationale: [why chosen]

Tff7b72- Alternatives considered: [what else evaluated]

**Output**: research.md with all NEEDS CLARIFICATION resolved

Tc9d1d9### Phase 1: Design & Contracts

**Prerequisites:** Ta5d6ff`research.md` complete

Tff7b721. **Extract entities from feature spec** → Ta5d6ff`data-model.md`:

Tff7b72- Entity name, fields, relationships

Tff7b72- Validation rules from requirements

Tff7b72- State transitions if applicable

Tff7b722. **Define interface contracts** (if project has external interfaces) → Ta5d6ff`/contracts/`:

Tff7b72- Identify what interfaces the project exposes to users or other systems

Tff7b72- Document the contract format appropriate for the project type

Tff7b72- Examples: public APIs for libraries, command schemas for CLI tools, endpoints for web services, grammars for parsers, UI contracts for applications

Tff7b72- Skip if project is purely internal (build scripts, one-off tools, etc.)

Tff7b723. **Agent context update**:

Tff7b72- Update the plan reference between the Ta5d6ff`<!-- SPECKIT START -->` and Ta5d6ff`<!-- SPECKIT END -->` markers in Ta5d6ff`.github/copilot-instructions.md` to point to the plan file created in step 1 (the IMPL_PLAN path)

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

Tc9d1d9## Key rules

Tff7b72- Use absolute paths for filesystem operations; use project-relative paths for references in documentation and agent context files

Tff7b72- ERROR on gate failures or unresolved clarifications