Help us improve
Share bugs, ideas, or general feedback.
From desplega
Executes individual phases of implementation plans as autonomous background sub-agents, performing pre-flight checks, file changes, and automated verifications.
npx claudepluginhub desplega-ai/ai-toolbox --plugin desplegaHow this skill is triggered — by the user, by Claude, or both
Slash command
/desplega:phase-runningThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
Executes approved implementation plans with strict adherence to scope, sequence, and verification. Supports batch and interactive modes, phase tracking, and final reporting.
Orchestrates multi-phase implementation from plan documents using sub-agents with auto-detected parallel/sequential strategies based on dependencies.
Implements approved technical plans from a configured plans directory phase-by-phase, verifying each phase with success criteria checks and user review before proceeding.
Share bugs, ideas, or general feedback.
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.
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:
This skill activates when:
/run-phase command for manual phase executiondesplega:phase-runningPhase 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.
Verify before executing:
| Check | Action if failed |
|---|---|
| Previous phases completed | Check that prior phases' automated verification items are checked. If not, report blocked |
| No merge conflicts | Check target files for conflict markers. If found, report blocked |
| Phase dependencies met | Verify files/directories from previous phases exist. If missing, report blocked |
Implement all changes described in the phase:
blocked with detailsExecute the automated verification commands from the phase's "Success Criteria" section:
### QA Spec (optional): section:
cli-verification, execute the test steps and record resultsbrowser-automation or manual, report QA: pending — the caller handles theseQA: n/a- [x]) automated verification items that passedlast_updated and last_updated_by frontmatter fieldsOPTIONAL SUB-SKILL: If significant learnings emerged during this phase, note them in the phase completion report for the parent session to capture via /learning capture.
The agent's return message MUST include:
If completed:
Status: completed
Phase: [N] - [Phase name]
Files changed: [list of files created/modified]
Automated checks: [N/M passed]
- [x] [Check 1] — passed
- [x] [Check 2] — passed
QA: passed | pending | n/a
Manual verification needed:
- [ ] [Manual check 1]
- [ ] [Manual check 2]
If blocked:
Status: blocked
Phase: [N] - [Phase name]
Reason: [Clear description of what's blocking]
Partial progress: [What was completed before blocking]
QA status: [status at time of block]
Suggested action: [How the caller/user can unblock]
If failed:
Status: failed
Phase: [N] - [Phase name]
Error: [Error details]
Partial progress: [What was completed before failure]
QA status: [status at time of failure]
Files modified: [List of files that were changed before failure]
Phase agents are atomic — they run to completion or stop:
| Direction | Data |
|---|---|
| Caller → Phase Agent | Plan path + phase number + autonomy mode |
| Phase Agent reads | Plan file + all source files referenced in the phase |
| Phase Agent → Caller | Status + changed files + verification results |
| Caller handles | Manual verification, cross-phase coordination, human checkpoints |