Implement Task

Task Implementation Skill

Dispatches a previously planned task or feature to the task-executor agent for worktree-isolated TDD implementation.

Token Discipline

This skill orchestrates implementation dispatch. Every turn re-reads the full context window, so unnecessary turns are expensive.

1. No narration turns. Do not output text-only turns like "Let me dispatch the task" or "Now I'll launch the executor." Combine text with a tool call in the same turn, or skip the text entirely.
2. Batch tool calls. When multiple tool calls are independent, issue them all in one turn.
3. No waiting updates. Do not output "Waiting for results..." turns. Wait silently until results arrive.
4. Keep context lean. Do not read file contents you won't use directly. The task-executor agent has Read/Grep/Glob and will read files in its own context window.

Pre-flight: Model Recommendation

Your current effort level is {{effort_level}}.

Skip this step silently if effort is high, xhigh, or max (the scale is low | | OR: RESULT: FAILURE | [one-line reason]

IMPORTANT:

• Do NOT run validate or merge — the caller handles those
• Do NOT use AskUserQuestion for merge decisions
• Your LAST line of output MUST be the RESULT line

" )

### Feature mode (`identifier` starts with `FEATURE-`)

Agent( subagent_type="groundwork:task-executor:task-executor", description="Implement {identifier}", prompt="You are implementing a feature that has already been fully planned.

PROJECT ROOT: [absolute path to project root]

FEATURE:

• Identifier: [FEATURE-slug]

PLAN FILE: [planfilepath] Read this file first with the Read tool — it contains the validated implementation plan including full requirements, acceptance criteria, and spec paths.

INSTRUCTIONS:

1. Follow your preloaded skills to create a worktree, implement with TDD, and commit.
2. The plan file provides all session context including requirements, acceptance criteria, and spec paths. Read spec files referenced in the plan for architecture and design context. Do NOT re-ask the user for requirements.
3. When complete, output your final line in EXACTLY this format:

RESULT: IMPLEMENTED | | | OR: RESULT: FAILURE | [one-line reason]

IMPORTANT:

• Do NOT run validate or merge — the caller handles those
• Do NOT use AskUserQuestion for merge decisions
• Your LAST line of output MUST be the RESULT line

" )

## Step 4: Parse Result

**After the subagent returns**, parse the result:

- `RESULT: IMPLEMENTED |  |  | ` → Output:
  ```
  RESULT: IMPLEMENTED | worktree_path= | branch= | base_branch=
  ```
- `RESULT: FAILURE | ...` → Output:
  ```
  RESULT: FAILURE | 
  ```
- No parseable RESULT line → Output:
  ```
  RESULT: FAILURE | Implementation subagent did not return a structured result. Check worktree status manually.
  ```

**DO NOT proceed past this step. The caller handles validation, merge, and completion.**

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [etr](https://github.com/etr)
- **Source:** [etr/groundwork](https://github.com/etr/groundwork)
- **License:** MIT

Install and usage instructions live in the source repository linked above.