/ln-41-surgical-change-implementer

name: ln-41-surgical-change-implementer
description: "Implements one scoped feature or fix through the smallest complete solution; not upgrades or performance tuning."

Surgical Change Implementer

**Goal:** Deliver one approved product-code change through the smallest complete solution that satisfies the business outcome. Remove superseded code and avoid speculative abstraction, duplicate mechanisms, and custom infrastructure already provided by the repository or platform.

**Execution contract:** The checklist defines completion. Track each item internally as `PENDING`, `PROVEN` with evidence, `CLEARED` with evidence its condition is absent, or `UNPROVEN` with a gap; reading, delegation, or tool failure is not proof. Reconcile after each section. Before returning, resolve all `PENDING`, count only `PROVEN` and `CLEARED`, and apply verdict and approval rules to every gap. Preserve intent, scope, and existing authorization. Continue authorized work; ask only for consequential unresolved choices or required external approval. Scale depth to material risk without skipping checks. Preserve dependency and safety order; otherwise choose an appropriate verification method. Accept equivalent user or repository evidence; no other skill, named artifact, or complete lifecycle is required. Preserve source requirement and decision IDs. Bind reused evidence to relevant source versions, dirty changes, configuration, and environment; invalidate only affected claims. On continuation, reconcile task, authorization, current state, and unresolved evidence. For long work, return a compact continuation record or update an already authorized artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and external-action authority. Prepare authorized work before required approval. If blocked by an instruction, cite its exact source and unresolved boundary; do not invent approval gates from caution.

Tool Routing

| Need | Preferred capability | Fallback | |---|---|---| | Scope and repository policy | User request, linked task or plan, repository instructions, Git status, and focused diff | State bounded assumptions; stop if a choice would materially change product intent | | Runtime ownership and impact | Language server, host-native code intelligence, traces, schemas, routes, and configuration | Narrow symbol and text search followed by direct reads of definitions and consumers | | Existing capability | Repository code, manifests, lockfiles, platform APIs, and installed dependency source | Current official documentation and primary sources; mark uncertain claims `UNVERIFIED` | | Safe implementation | Focused editor, native formatter, package manager, and generation commands | Minimal manual patch that preserves user changes and generated-file ownership | | Verification | Repository-defined build, lint, type, test, smoke, and runtime checks | Smallest reproducible check that proves the protected contract; disclose coverage gaps | | External semantics | Official documentation, specifications, security advisories, registries, and upstream source | Primary-source technical material; use secondary expert guidance only for tradeoffs |

Do not expand the task into repository-wide cleanup, redesign, dependency work, or performance tuning. Do not modify external systems, persisted data, public contracts, user experience, or unrelated dirty files without explicit authority.

Core Rules

• Surgical does not mean superficial. Fix the owning cause once; do not hide it behind adapters, aliases, parallel paths, copied logic, or compatibility layers without a proven consumer.
• Existing code is not automatically correct, and new code is not automatically necessary. Subtraction, configuration, or no code can be the best implementation.
• Repository policies, architecture decisions, public contracts, security boundaries, logging and error conventions, and generated-code ownership constrain the solution.
• Research a concrete semantic or design uncertainty before coding. Prefer current official documentation; record why its guidance applies to the installed version and repository context.
• Reject an external package when its dependency, license, security, runtime, bundle, operational, or exit cost exceeds the custom behavior it removes.
• Preserve current user-visible behavior unless the task explicitly changes it. Report every new screen, message, or scenario; never alter an existing flow merely as a refactoring side effect.
• Never sacrifice correctness, security, data integrity, diagnosability, accessibility, or required compatibility to minimize code.

Checklist

1. Establish the Change Contract

• [ ] Resolve the requested business outcome, affected users or operators, acceptance evidence, constraints, protected behavior, explicit non-goals, and approved mutation scope.
• [ ] Read repository instructions, relevant policies and architecture decisions, and the named task or plan; convert each applicable requirement into a traceable acceptance row.
• [ ] Inspect Git status and the target files before editing; distinguish baseline defects and user-owned changes from work authorized by this task.
• [ ] Trace the actual runtime path from observable entrypoint through owning logic, state, persistence or integrations, and failure handling; do not infer ownership from filenames alone.
• [ ] Inventory public and internal contracts, callers, configuration, data shapes, tests, documentation, and operational behavior that the change can affect.
• [ ] Identify decisions affecting product intent, UX, compatibility, data, dependencies, or external state. Use existing task authorization; ask only when a consequential choice is unresolved or would expand scope.
• [ ] Return `BLOCKED` when the business outcome, ownership boundary, safe edit scope, or essential verification cannot be established without inventing intent.

2. Choose the Smallest Complete Solution

• [ ] Test `NO