From rtl-agent-team
Runs structured cross-review with Codex CLI as second reviewer, exchanging findings and fixes in consensus loops (max 5 rounds) with user escalation. Use at phase boundaries or for manual quality gates.
npx claudepluginhub babyworm/rtl-agent-team --plugin rtl-agent-teamThis skill is limited to using the following tools:
<Purpose>
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
<Use_When>
<Do_Not_Use_When>
codex --version)codex --version must succeedThe skill reads ~/.codex/config.toml for model and effort settings.
Users configure their preferred model and reasoning effort there — the skill never overrides these.
Display the current config to the user at the start of every invocation:
Codex Config: model={model}, reasoning_effort={effort}
If no phase number is provided, detect the current phase from:
docs/phase-N-*/ directoryTask(subagent_type="rtl-agent-team:codex-cross-reviewer",
prompt="Run cross-review for Phase {N}.
Phase intent: {brief description from phase docs}.
Target artifacts: {list of docs/code paths}.
Changed files: {from git diff}.")
Phase orchestrators (P1-P6) should invoke cross-review as their penultimate step (before declaring phase complete):
# In orchestrator agent prompt, before final step:
Step N-1: Cross-Review Gate
Task(subagent_type="rtl-agent-team:codex-cross-reviewer",
prompt="Cross-review Phase {N}. Artifacts: {paths}.")
# MANDATORY explicit verdict check:
Read(".rat/cross-review/phase-{N}/cross-review-report.md")
# Parse verdict field — must be CONSENSUS or USER_DECIDED
# If verdict != CONSENSUS and user did not approve → do NOT proceed to completion
Orchestrators that integrate cross-review:
p1-research-orchestrator — review spec analysis qualityp2-arch-orchestrator — review architecture decisions + ref modelp3-uarch-orchestrator — review uArch design + BFMp4-implement-orchestrator — review RTL implementationp4-rtl-sanity-orchestrator — review rapid implementationp5-verify-orchestrator — review verification completenessp6-review-orchestrator — review design note qualityRound 1: Claude → phase summary → Codex reviews → findings JSON
Round 2+: Claude → fixes + rebuttals + agreement ledger → Codex re-reviews → updated findings
Stability: 2+ consecutive rounds with verdict==APPROVE + no new critical/major + no still_disagree + no oscillation = CONSENSUS
Max 5 rounds → AskUserQuestion escalation to user
Cross-review artifacts are phase-scoped for traceability:
.rat/cross-review/review-schema.json — shared JSON schema.rat/cross-review/phase-{N}/phase-summary.md — phase context sent to Codex.rat/cross-review/phase-{N}/prompt-round-R.txt — exact prompt sent each round.rat/cross-review/phase-{N}/round-R.json — Codex's structured response each round.rat/cross-review/phase-{N}/resolution-state.json — running resolution tracker.rat/cross-review/phase-{N}/cross-review-report.md — final summary report.rat/cross-review/phase-{N}/escalation-summary.md — generated if user escalation neededCompletion marker: .rat/state/cross-review-phase-${N}-done (e.g., cross-review-phase-2-done)