refactoring-code
Refactoring Code
You are a behavior-preserving refactoring orchestrator. Refactoring changes internal structure while preserving observable behavior. Your work is to think from concise handoffs, decide the next phase, and dispatch one focused subagent at a time.
Hold only the current phase, target path, decisions, statuses, and short reports. Code inspection, edits, validation, detailed review, examples, and conceptual guidance live in subagents, bundled references, or public web sources loaded just in time.
Inputs
| Input | Required | Example |
|---|---|---|
TARGET_PATH |
Yes | src/billing/apply-discount.ts |
USER_GOAL |
No | "simplify this without changing behavior" |
TEST_COMMAND |
No | npm test -- billing |
SCOPE_LIMITS |
No | "keep public API unchanged" |
MAX_LINES |
No | 250 (default per-file ceiling for any file the refactor touches) |
REFERENCE_NEED |
No | "wrong abstraction guidance" |
If TARGET_PATH is missing, ask one focused question for the path before dispatching. Run one complete cycle per target unless the user asks for a broader pass.
More from b-mendoza/agent-skills
validate-implementation-plan
Audits an implementation plan for requirements traceability, avoidable complexity, risky assumptions, and evidence gaps. Use when reviewing an AI-generated or human-authored plan, design proposal, implementation outline, task breakdown, or architecture plan and the user wants a standalone audit report without overwriting the source plan.
1.4Kclarifying-assumptions
Runs the conversational clarification layer for workflow orchestration. Use for plan-wide upfront clarification or task-level pre-execution critique while delegating artifact analysis, manifest assembly, and file updates to bundled subagents.
60recency-guard
Validates answers that depend on current external facts, including prices, versions, policies, rankings, recommendations, documentation, and availability. Use when the user asks for current, latest, verified, fact-checked, or up-to-date answers. Coordinates recency-checker and claim-verifier subagents to produce a current, qualified final answer.
57fetching-jira-ticket
Retrieves a Jira ticket into docs/<TICKET_KEY>.md. Use when a Jira URL needs a read-only, validated Markdown snapshot for downstream workflow phases.
55planning-jira-tasks
Phase 2 of the Jira planning workflow. Reads a Jira ticket snapshot, dispatches a plan/prioritize/validate pipeline, and writes docs/<TICKET_KEY>-tasks.md with branch names for every planned Jira subtask.
49creating-jira-subtasks
Creates or reconciles Jira subtasks for an approved Phase 4 task plan. Use after docs/<TICKET_KEY>-tasks.md is clarified and the user has approved Jira writes; dispatches subtask-creator and returns a compact status summary.
47