Skip to main content
subagent CX Codex

speckit.tasks — Claude Code subagent: what it does, how to install

speckit.tasks turns a feature into tasks.md: reads plan.md and spec.md from the feature folder and lays out the work per user story with dependencies.

MIT ★ 110 updated 2026-10-19

Install into GitHub Copilot · Manually: put the files in place All methods and platforms ↓
.github/agents/speckit.tasks.agent.md
Open on GitHub

What speckit.tasks does

The agent expects a project on the .specify layout. It calls .specify/scripts/bash/setup-tasks.sh --json from the repo root, takes FEATURE_DIR and the tasks.md template from the result, then pulls the stack and structure out of plan.md and the prioritised stories out of spec.md. Anything else in the folder, such as data-model.md, contracts/, research.md or .specify/memory/constitution.md, is used when present.

You get a phased tasks.md: setup, a foundational block, one phase per story in priority order, and a closing pass for polish. Tasks come with file paths and a checklist format, and the file carries a dependency graph plus parallel-run examples for each story. The agent finishes by offering handoffs to speckit.analyze and speckit.implement.

Both plan.md and spec.md must exist, or there is nothing to derive tasks from. The agent also reads .specify/extensions.yml and runs mandatory before_tasks and after_tasks hooks. A YAML that fails to parse gets reported with the parser error, and every hook check is skipped, mandatory ones included.

What it helps with

  • turn a feature into a task list with file paths and dependencies
  • attach tasks to user stories in priority order
  • spot which stories can be built in parallel
  • hook custom scripts into task generation
  • confirm each story has an independently testable set of tasks

Example prompts for the agent

  • Generate tasks.md for the current feature from plan.md and spec.md
  • Lay out the tasks by user story and show what can run in parallel
  • Check that every story gets its own tasks with file paths

How to install speckit.tasks

Manually: put the files in place

.github/agents/speckit.tasks.agent.md

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about speckit.tasks

How do I install speckit.tasks in Claude Code?

Copy the agent file into your project at .claude/agents/speckit.tasks.md. On Codex the same agent lives at .codex/agents/speckit.tasks.toml.

What does speckit.tasks do?

It reads the feature plan and spec, then writes tasks.md with phases, per-story tasks and a dependency graph. At the end it offers to hand off to speckit.analyze or speckit.implement.

Which documents does it need?

plan.md and spec.md are required. data-model.md, contracts/ and research.md are picked up when they sit in the feature folder.

Source text

speckit.tasks.agent.md · MIT
---
description: Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
handoffs:
  - label: Analyze For Consistency
    agent: speckit.analyze
    prompt: Run a project analysis for consistency
    send: true
  - label: Implement Project
    agent: speckit.implement
    prompt: Start the implementation in phases
    send: true
---

## User Input

```text
$ARGUMENTS
```

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

## Pre-Execution Checks

**Check for extension hooks (before tasks generation)**:
- Check if `.specify/extensions.yml` exists in the project root.
- If it exists, read it and look for entries under the `hooks.before_tasks` key
- If the YAML cannot be parsed or is invalid, do not skip silently: tell the user that `.specify/extensions.yml` could not be read (include the parser error) and that no hooks were checked, including any mandatory (`optional: false`) hooks registered there, then 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.
    ```
    After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent/session (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `/skill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.
- If no hooks are registered or `.specify/extensions.yml` does not exist, skip silently

## Outline

1. **Setup**: Run `.specify/scripts/bash/setup-tasks.sh --json` from repo root and parse FEATURE_DIR, TASKS_TEMPLATE_CONTENT, TASKS_TEMPLATE, and AVAILABLE_DOCS list. `FEATURE_DIR` and `TASKS_TEMPLATE` must be absolute paths when provided. `AVAILABLE_DOCS` is a list of document names/relative paths available under `FEATURE_DIR` (for example `research.md` or `contracts/`). 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 design documents**: Read from FEATURE_DIR:
   - **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities)
   - **Optional**: data-model.md (entities), contracts/ (interface contracts), research.md (decisions), quickstart.md (test scenarios)
   - **IF EXISTS**: Load `.specify/memory/constitution.md` for project principles and governance constraints
   - Note: Not all projects have all documents. Generate tasks based on what's available.

3. **Execute task generation workflow**:
   - Load plan.md and extract tech stack, libraries, project structure
   - Load spec.md and extract user stories with their priorities (P1, P2, P3, etc.)
   - If data-model.md exists: Extract entities and map to user stories
   - If contracts/ exists: Map interface contracts to user stories
   - If research.md exists: Extract decisions for setup tasks
   - Generate tasks organized by user story (see Task Generation Rules below)
   - Generate dependency graph showing user story completion order
   - Create parallel execution examples per user story
   - Validate task completeness (each user story has all needed tasks, independently testable)

4. **Generate tasks.md**: Use TASKS_TEMPLATE_CONTENT (from the JSON output above) as the structure. For compatibility with older setup scripts that omit TASKS_TEMPLATE_CONTENT, read TASKS_TEMPLATE instead. Fill with:
   - Correct feature name from plan.md
   - Phase 1: Setup tasks (project initialization)
   - Phase 2: Foundational tasks (blocking prerequisites for all user stories)
   - Phase 3+: One phase per user story (in priority order from spec.md)
   - Each phase includes: story goal, independent test criteria, tests (if requested), implementation tasks
   - Final Phase: Polish & cross-cutting concerns
   - All tasks must follow the strict checklist format (see Task Generation Rules below)
   - Clear file paths for each task
   - Dependencies section showing story completion order
   - Parallel execution examples per story
   - Implementation strategy section (MVP first, incremental delivery)

## Mandatory Post-Execution Hooks

**You MUST complete this section before reporting completion to the user.**

Check if `.specify/extensions.yml` exists in the project root.
- If it does not exist, or no hooks are registered under `hooks.after_tasks`, skip to the Completion Report.
- If it exists, read it and look for entries under the `hooks.after_tasks` key.
- If the YAML cannot be parsed or is invalid, do not skip silently: tell the user that `.specify/extensions.yml` could not be read (include the parser error) and that no hooks were checked, including any mandatory (`optional: false`) hooks registered there, then continue to the Completion Report.
- 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:
  - **Mandatory hook** (`optional: false`) — **You MUST emit `EXECUTE_COMMAND:` for each mandatory hook**:
    ```
    ## Extension Hooks

    **Automatic Hook**: {extension}
    Executing: `/{command}`
    EXECUTE_COMMAND: {command}
    ```
    After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent/session (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `/skill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.
  - **Optional hook** (`optional: true`):
    ```
    ## Extension Hooks

    **Optional Hook**: {extension}
    Command: `/{command}`
    Description: {description}

    Prompt: {prompt}
    To execute: `/{command}`
    ```

## Completion Report

Output path to generated tasks.md and summary:
- Total task count
- Task count per user story
- Parallel opportunities identified
- Independent test criteria for each story
- Suggested MVP scope (typically just User Story 1)
- Format validation: Confirm ALL tasks follow the checklist format (checkbox, ID, labels, file paths)

Context for task generation: $ARGUMENTS

The tasks.md should be immediately executable - each task must be specific enough that an LLM can complete it without additional context.

## Task Generation Rules

**CRITICAL**: Tasks MUST be organized by user story to enable independent implementation and testing.

**Tests are OPTIONAL**: Only generate test tasks if explicitly requested in the feature specification or if user requests TDD approach.

### Checklist Format (REQUIRED)

Every task MUST strictly follow this format:

```text
- [ ] [TaskID] [P?] [Story?] Description with file path
```

**Format Components**:

1. **Checkbox**: ALWAYS start with `- [ ]` (markdown checkbox)
2. **Task ID**: Sequential number (T001, T002, T003...) in execution order
3. **[P] marker**: Include ONLY if task is parallelizable (different files, no dependencies on incomplete tasks)
4. **[Story] label**: REQUIRED for user story phase tasks only
   - Format: [US1], [US2], [US3], etc. (maps to user stories from spec.md)
   - Setup phase: NO story label
   - Foundational phase: NO story label
   - User Story phases: MUST have story label
   - Polish phase: NO story label
5. **Description**: Clear action with exact file path

**Examples**:

- ✅ CORRECT: `- [ ] T001 Create project structure per implementation plan`
- ✅ CORRECT: `- [ ] T005 [P] Implement authentication middleware in src/middleware/auth.py`
- ✅ CORRECT: `- [ ] T012 [P] [US1] Create User model in src/models/user.py`
- ✅ CORRECT: `- [ ] T014 [US1] Implement UserService in src/services/user_service.py`
- ❌ WRONG: `- [ ] Create User model` (missing ID and Story label)
- ❌ WRONG: `T001 [US1] Create model` (missing checkbox)
- ❌ WRONG: `- [ ] [US1] Create User model` (missing Task ID)
- ❌ WRONG: `- [ ] T001 [US1] Create model` (missing file path)

### Task Organization

1. **From User Stories (spec.md)** - PRIMARY ORGANIZATION:
   - Each user story (P1, P2, P3...) gets its own phase
   - Map all related components to their story:
     - Models needed for that story
     - Services needed for that story
     - Interfaces/UI needed for that story
     - If tests requested: Tests specific to that story
   - Mark story dependencies (most stories should be independent)

2. **From Contracts**:
   - Map each interface contract → to the user story it serves
   - If tests requested: Each interface contract → contract test task [P] before implementation in that story's phase

3. **From Data Model**:
   - Map each entity to the user story(ies) that need it
   - If entity serves multiple stories: Put in earliest story or Setup phase
   - Relationships → service layer tasks in appropriate story phase
   - For each field with constraints in data-model.md (max length, nullable/required, enum values, validation rules), quote the constraint verbatim in the task description so it is not left to implementation-time discretion

4. **From Setup/Infrastructure**:
   - Shared infrastructure → Setup phase (Phase 1)
   - Foundational/blocking tasks → Foundational phase (Phase 2)
   - Story-specific setup → within that story's phase

### Phase Structure

- **Phase 1**: Setup (project initialization)
- **Phase 2**: Foundational (blocking prerequisites - MUST complete before user stories)
- **Phase 3+**: User Stories in priority order (P1, P2, P3...)
  - Within each story: Tests (if requested) → Models → Services → Endpoints → Integration
  - Each phase should be a complete, independently testable increment
- **Final Phase**: Polish & Cross-Cutting Concerns

## Done When

- [ ] tasks.md generated with all phases, task IDs, and file paths
- [ ] Extension hooks dispatched or skipped according to the rules in Mandatory Post-Execution Hooks above
- [ ] Completion reported to user with task count, story breakdown, and MVP scope

© alfredoperez · MIT · alfredoperez/speckit-companion

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

From the same set83

The whole set →
feature-clip feature-clip builds SpecKit Companion looping clips through capture, composition, rendering, and media sync for the site and documentation. CX Codex +1 ★ 110repo stars publish-speckit-ext publish-speckit-ext — a command to publish the spec-kit extension to a GitHub release. Lets other developers install the extension via catalog without cloning the repository. CX Codex +1 ★ 110repo stars speckit.constitution speckit.constitution is a Claude Code subagent that creates and updates the project constitution at .specify/memory/constitution.md based on team principles. CX Codex +1 ★ 110repo stars ship-ticket The ship-ticket command takes an implemented ticket from branch review through PR creation and merge. Use it when the code is already built in SpecKit Companion. CX Codex +1 ★ 110repo stars speckit.clarify speckit.clarify pins down underspecified details in your feature spec with up to five targeted questions, saving choices directly to disk. CX Codex GP ChatGPT ★ 110repo stars speckit.analyze The speckit.analyze subagent checks spec.md, plan.md, and tasks.md for gaps and conflicts. Run it after task generation, before implementation. CX Codex +1 ★ 110repo stars speckit.implement speckit.implement — a subagent that reads the task list from tasks.md and executes it step by step, checking prerequisites, loading project artifacts, and following the architecture defined in plan.md. CX Codex +1 ★ 110repo stars speckit.specify speckit.specify turns plain-text feature descriptions into structured specifications, allocates numbered Git branches, and generates requirements checklists. CX Codex GP ChatGPT ★ 110repo stars

Project sponsors

Companies that keep this analytics open