# Execute Task

Execute the next TaskMaster task using the implementation plan with CDD verification.

- Repository: https://github.com/anombyte93/prd-taskmaster (606 stars)
- Category: Design
- License: MIT
- Last updated: 2026-08-14
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add anombyte93/prd-taskmaster --skill execute-task -g -a claude-code -y`
Codex: `npx skills add anombyte93/prd-taskmaster --skill execute-task -g -a codex -y`
Cursor: `npx skills add anombyte93/prd-taskmaster --skill execute-task -g -a cursor -y`
Gemini CLI: `npx skills add anombyte93/prd-taskmaster --skill execute-task -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add anombyte93/prd-taskmaster`

## Description

Execute the next TaskMaster task using the implementation plan with CDD verification. Picks the next ready task, matches it to the plan step, implements via a dispatched subagent, verifies subtasks with evidence, marks the task done, and loops until every task is complete. Wraps the TaskMaster next -> in-progress -> done lifecycle with CDD GREEN / RED / BLUE verification and the plugin's triple-verification rule. Autonomous by design, no user prompts inside the loop.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# execute-task

The execution loop. Three sources converge:

- **Plan** (HOW), `docs/superpowers/plans/*.md` produced by GENERATE
- **TaskMaster** (WHAT), `.taskmaster/tasks/tasks.json` with
  dependencies and complexity scores
- **CDD** (PROOF), acceptance cards per task, evidence-gated

execute-task is the single skill that runs the full build from "tasks are
ready" to SHIP_CHECK_OK. It is autonomous, no AskUserQuestion inside the
loop. Any gap that would require user input is surfaced through the recon
escalation ladder (step 11) or the inbox (steps 4 and 8), never via a modal
prompt.

## Entry

This skill is invoked either:

1. Directly by the user once HANDOFF has completed and a task-execution
   mode (A/B/C) has been dispatched, **or**
2. By the `prd-taskmaster` orchestrator when `current_phase` is `EXECUTE`.

On entry, confirm that:

- `.atlas-ai/state/pipeline.json` exists and records `phase: EXECUTE`
- `.taskmaster/tasks/tasks.json` exists with at least one ready task
- `.atlas-ai/customizations/system-prompt-template.md` is present (may be
  empty, absence is a setup bug, empty is fine)

If any of the above are missing, report the gap and halt. Do NOT attempt to
bootstrap the missing artifact from inside this loop, that is the
orchestrator's job.

## Cycle (per iteration)

Each pass through this cycle moves exactly one TaskMaster task from `pending`
to `done`. Do the 13 steps in order. Do not skip.

> **Task-start SHA**, at the very beginning of each iteration (before step 2),
> capture the current git HEAD:
>
> ```bash
> task_start_sha=$(git rev-parse HEAD)
> ```
>
> Record `$task_start_sha` in the execute-log row for this iteration.  It is the
> oracle of truth for every reachability sweep in step 9b below: "what modules
> did THIS task add?" is `diff $task_start_sha..HEAD`.  The oracle flow already
> issues per-task start commits; this surfaces the same value in the loop prose.

The rest: https://github.com/anombyte93/prd-taskmaster/blob/HEAD/skills/execute-task/SKILL.md