Merchantlee99

Explicit GPT-5.6 native-first router for auditing, designing, installing, or validating Codex skill combinations, global skill setup, routing fixtures, and harness behavior. Use when the user explicitly invokes $codex-skill-router or asks to change or inspect Codex skills, routing, AGENTS guidance, or global harness configuration. Do not use for ordinary coding, review, debugging, research, or UI work merely because the task is complex.

Use when work introduces or changes shared nouns, states, IDs, ownership, authority, or customer-facing vocabulary.

Use when changing harness gates, routing rules, skills, or automation behavior and benchmark/eval evidence is needed to avoid slowing normal coding performance. Do not use for ordinary app code changes.

Use when a request is early, ambiguous, or lacks a codebase-backed shared language; interview the user to expose assumptions before planning.

Use when a codebase, docs, ADRs, tests, prior reviews, or team traces exist; align new work with existing shared language before implementation.

Use first for normal or high-risk natural-language work to choose task mode, tier, grill path, spec layers, team-rule scan, and required gates before implementation.

Use before claiming normal+ completion when accepted REQ statements must be mapped to executed tests, guardrails, smoke checks, runtime/UI evidence, or named manual review.

Use when behavior changes need L1/L2/L3 intent specification, EARS requirements, feature archetype prompts, latency contracts, or rollback/idempotency decisions.

Use after implementation to apply gstack-inspired quality gates such as review, validation, QA or browse, security checks, and ship readiness without turning them into always-on orchestration.

Use when a request is new, ambiguous, likely to sprawl, or strategically important and you need to turn it into a scoped build-ready plan with prompt, PRD, plan, assumptions, and a readiness check before implementation.

Use when a bug is unclear, recurring, or expensive to guess at and you need a disciplined loop to reproduce the issue, isolate the root cause, apply the smallest fix, and verify the result before moving on.

Use when implementation is approved and you need to run a disciplined build loop with a single writer, scoped execution, validation slices, document updates, and controlled handoff into review and QA gates.