Structure

When to use

• The user wants to fix structural violations autonomously using the refactor agent.

Goal

• Run refactoring subagents sequentially to fix structural violations in target code.

Input

• Accept optional arguments (file or folder paths).

Workflow

Halt on any Halt conditions entry after every spawn.

1. Refactoring Loop:
   • Spawn a refactor subagent with the optional argument; await its result.
   • Complete: repeat step 1.
   • No Changes: proceed to step 2.
2. Report: emit the result per Result directives:
   • Result: Completed when the workflow reaches Report without a halt; Halted when a subagent reports Failed; Failed on any other Halt conditions entry.

Directives

• Always use the subagent tool for subagent invocation.
• Pass the argument verbatim to each subagent; never read or expand file-path arguments.
• Route only from each subagent's Result value.
• Spawn only the subagents the workflow names.

Constraints

• Restrict activities to spawning subagents, reading their results, and reporting; never write files, run git operations, activate skills, or prompt the user mid-run.
• Never run subagents in parallel or concurrently.
• Halt conditions: halt immediately; report per Report, listing the diagnostic under Findings:
  • A subagent Failed result.
  • A subagent result missing or outside the workflow's literals.
  • A process failure (crash, timeout, AgentError).

Verification

• Subagents ran one at a time, in workflow order.
• Every run, halted or not, ended in Report.
• The orchestrator wrote no file.

Result directives

• Minimum words. Maximum signal.
• Return the final execution status block.
• Keep prose terse while ensuring clarity.
• Optimize prose for agent, token, and context efficiency.
• Split actions, findings, and summaries into terse bullet points.
• Use lists and sub-lists for long sentences and dense paragraphs.
• Emit the result template as live markdown—never in a code fence.
• Output nothing outside the template.

Result template

### Execution Summary

- **Actions**:
  - [Terse list of actions from spawned subagents]
- **Files**:
  - [Terse list of files affected by spawned subagents]
- **Findings**:
  - [Terse list of findings from spawned subagents]
- **Summary**:
  - [Terse list of summary from spawned subagents]

> **Structure Status** • `[scope]`
> **Result**: [Completed | Halted | Failed]
> **Impact**: [Terse impact statement]