/ln-44-performance-optimizer

name: ln-44-performance-optimizer
description: "Profiles and improves a measured performance bottleneck; retains only verified improvements."

Performance Optimizer

**Goal:** Optimize only measured problems. Preserve correctness, isolate experiments, and retain a change only when comparable evidence shows that it improves the agreed metric without unacceptable regressions.

**Execution contract:** Track every checklist item as `PENDING`, `PROVEN` with observed outcome evidence, `CLEARED` with evidence its condition is absent, or `UNPROVEN` with a gap. Reading, delegation, tool failure, zero exit status, and self-reported success are 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, mode, and existing authorization. Complete authorized work before required external approval; ask only consequential unresolved choices. If nobody can answer, report the exact question and apply the skill's gap verdict without waiting or guessing. Cite any blocking instruction and unresolved boundary; never invent approval gates. Scale depth to material risk; preserve mandatory checks, dependencies, and safety order while choosing verification methods. Accept equivalent user or repository evidence without requiring another skill, named artifact, or full lifecycle. Preserve source requirement and decision IDs. Bind reused evidence to relevant versions, dirty changes, configuration, environment, and observation windows; invalidate only affected claims. Choose the primary workflow by outcome and explicit selection. Consume neighboring contracts and valid evidence without duplicating ownership or restarting audits. Split distinct deliverables by scope, not mandatory skill invocation. Broad independent assessments use audit workflows; focused domain reviews remain read-only. On continuation, reconcile task, authorization, state, and gaps. Return a compact continuation record for long work or update an already authorized artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and external-action authority. Trace applicable requirements to their authoritative owner, planned or implemented change, acceptance evidence and status in the existing artifact or response; no new registry is required. Explicit constraints remain binding until an authorized deviation; risk determines priority, not permission to ignore them. Investigate the causal flow beyond initially named files. Within implementation authority, include structural repair needed for the outcome; minimize total complexity and risk, not changed lines. This does not authorize unrelated cleanup or mutation during review. Before retrieval, define the evidence question; read selectively without skipping applicable instructions. Use tools for mechanical processing; summarize bounded results, errors, coverage, and source paths, keeping full output outside context. Before technical decisions, establish applicability and actual versions; verify version-dependent assumptions against official documentation or specifications. Search and read primary pages for current external recommendations; snippets are not evidence. Version-matched bundled documentation or valid prior evidence suffices. Record decision, version, source, and limitations. Mark unavailable evidence UNVERIFIED; block only essential dependent work. Prefer native mechanisms, justify added tools or abstractions with evidence, and reuse the existing rule owner.

Tool Routing

| Need | Preferred tool | Use it when | Fallback | |---|---|---|---| | Repository state and safe edit boundary | Git status, diff, branch or worktree inspection, and repository instructions | Always before profiling or editing | Stop if user changes cannot be isolated safely | | Baseline and final metric | Existing benchmark, load test, reproducible command, or production-like replay | The metric and workload reflect the reported problem | Create the smallest local benchmark that reproduces the behavior without inventing production scale | | Bottleneck evidence | Existing profiler, tracing, query diagnostics, allocation tools, or OS-level metrics | Locating CPU, memory, I/O, lock, query, network, or scheduler cost | Targeted instrumentation with cleanup plan | | Code path and blast radius | Language server or host-native code intelligence | Following hot symbols, callers, implementations, and affected contracts | Narrow search plus direct inspection of definitions and consumers | | Correctness and regressions | Repository-defined tests, build, lint, type, and smoke commands | Before and after every retained experiment | Choose the smallest portfolio action when current evidence cannot detect the likely material regression | | Runtime and dependency semantics | Official documentation, release notes, and specifications matching installed versions | A hypothesis depends on optimizer, runtime, database, framework, or library behavior | Primary-source web research; otherwise mark the hypothesis `UNVERIFIED` |

Do not optimize by aesthetic preference or benchmark a different workload from the reported problem. Never discard user changes, use destructive Git reset, or run uncontrolled load against production.

Evidence Rules

• Separate cold-start, warm steady-state, and saturated-load behavior when the reported problem can occur in more than one regime.
• Profile contribution and end-to-end impact separately: a hot function can improve while the user-visible metric does not.
• Treat profiler estimates, synthetic workloads, and production observations as different evidence classes and label them.
• Correctness, resource safety, and operational stability are hard constraints, not secondary metrics.

Checklist

1. Define the Problem and Protect the Workspace

• [ ] Resolve the user-visible problem, workload, environment, primary metric, overall