integration-test
Codex compatibility note:
- Invoke
$skill-name: load the registered.agents/skills/<name>/SKILL.mdand execute it with Codex tools; no separateSkilltool or Claude mode switch is needed. When a workflow step or another skill names a skill, read that file in full yourself (every line, with no line limit; in parts only when output is cut off): a skill whose implicit invocation is off is never loaded for you. Author.claude/**; mirrors are generated.- Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
- Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
- Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required
spawn_agentsubagent(s) for that task.- Preserve protocol order unless the user approves a deviation. Workflows use
$start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence.
Quick Summary
Review modes: For review/audit work, standalone defaults to
--review-only(--report-onlyalias);--fix-loopenables review → validate → authorized fix → fresh re-review, default cap 3.--fix-loop --loop-owner=callerreturns a read-only pass to the caller that owns fixes/re-review. Create triage, review, validation and re-review todo tasks first; apply the carriedreview-policycontract for LOW deferral and user-approved bounded extensions. Non-review modes and terminal findings validation keep their own dispatch.
Goal: Generate, review, diagnose and verify integration tests that protect the selected case contract through real boundaries and system-owned outcomes.
Summary:
- Select the invocation route before applying its procedure: no flag uses from-changes, from-prompt, positional review, diagnose or verify-traceability;
--mode=reviewsupports review-only or the shared fix-loop;--mode=verify [--fix-loop]owns runtime proof. - Resolve the case profile and package before judging coverage. Generate: owner cases → tests → full-scope traceability. Review: scope/profile → package → eight gates → validate/deduplicate → verdict/report → stop. Verify follows its reference's repeat/isolation and failure rules.
- Preserve meaningful assertions, production fidelity, native carriers/cardinality and operation authority; blocked or unknown evidence never proves coverage.
Workflow: Detect → find targets → gather context → execute the selected mode → report.