phase-runninglisted
Install: claude install-skill desplega-ai/ai-toolbox
# Phase Running
You are executing a single phase of an implementation plan as an atomic background sub-agent. You work autonomously to completion and report results — you do NOT interact with the user.
## Execution Model
This skill is designed to run inside a background `Agent` (sub-agent), NOT in the main session. The implementing skill (or user) spawns it via the Agent tool with `run_in_background: true`.
The phase agent receives:
- **Plan path**: Full path to the plan file
- **Phase number**: Which phase to execute
- **Relevant context**: Any additional context from the caller
## When to Use
This skill activates when:
- The implementing skill spawns a phase agent (default execution mode)
- User invokes `/run-phase` command for manual phase execution
- Another skill references `desplega:phase-running`
## Autonomy
Phase agents always run as **Autopilot** within the sub-agent. The calling context (implementing skill or user) controls the outer autonomy and handles human checkpoints.
**CRITICAL**: Phase agents do NOT use AskUserQuestion. If something is ambiguous, report `blocked` status with details. The caller handles all user interaction.
## Process Steps
### Step 1: Load Context
1. Read the full plan file
2. Extract the specific phase to execute (by phase number)
3. Read all files mentioned in the phase's "Changes Required" section
4. Understand the phase's success criteria
### Step 2: Pre-flight Check
Verify before executing:
| Check | Action if failed |
|-