triflux 9.8.3 → 10.0.0-alpha.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "triflux",
-  "version": "9.8.3",
+  "version": "10.0.0-alpha.1",
   "description": "CLI-first multi-model orchestrator for Claude Code — route tasks to Codex, Gemini, and Claude",
   "type": "module",
   "bin": {
@@ -13,63 +13,24 @@
     "tfx-doctor-tui": "bin/tfx-doctor-tui.mjs",
     "tfx-setup-tui": "bin/tfx-setup-tui.mjs"
   },
+  "engines": { "node": ">=18.0.0" },
+  "dependencies": {
+    "@triflux/core": "^10.0.0-alpha.1",
+    "@triflux/remote": "^10.0.0-alpha.1"
+  },
   "files": [
     "bin",
-    "tui",
-    "hub",
     "skills",
-    "!skills/tfx-workspace",
-    "!**/failure-reports",
-    "scripts",
-    "hooks",
-    "hud",
-    ".claude-plugin",
     "README.md",
-    "README.ko.md",
     "LICENSE"
   ],
-  "scripts": {
-    "setup": "node scripts/setup.mjs",
-    "preinstall": "node scripts/preinstall.mjs",
-    "postinstall": "node scripts/setup.mjs",
-    "lint": "biome check .",
-    "lint:fix": "biome check --fix .",
-    "health": "npm test && npm run lint",
-    "test": "node --test --test-force-exit --test-concurrency=1 \"tests/**/*.test.mjs\" \"scripts/__tests__/**/*.test.mjs\"",
-    "test:unit": "node --test --test-force-exit --test-concurrency=1 tests/unit/**/*.test.mjs",
-    "test:integration": "node --test --test-force-exit --test-concurrency=1 tests/integration/**/*.test.mjs",
-    "test:route-smoke": "node --test scripts/test-tfx-route-no-claude-native.mjs"
-  },
-  "engines": {
-    "node": ">=18.0.0"
-  },
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/tellang/triflux.git"
-  },
-  "homepage": "https://github.com/tellang/triflux#readme",
+  "keywords": ["claude-code", "plugin", "codex", "gemini", "cli-routing", "orchestration", "multi-model", "triflux", "tfx"],
   "author": "tellang",
   "license": "MIT",
-  "dependencies": {
-    "@modelcontextprotocol/sdk": "^1.27.1",
-    "better-sqlite3": "^12.6.2",
-    "pino": "^10.3.1",
-    "pino-pretty": "^13.1.3",
-    "systray2": "^2.1.4",
-    "zod": "^4.0.0"
-  },
-  "devDependencies": {
-    "@biomejs/biome": "^2.0.0"
-  },
-  "keywords": [
-    "claude-code",
-    "plugin",
-    "codex",
-    "gemini",
-    "cli-routing",
-    "orchestration",
-    "multi-model",
-    "triflux",
-    "tfx"
-  ]
+  "homepage": "https://github.com/tellang/triflux#readme",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/tellang/triflux.git",
+    "directory": "packages/triflux"
+  }
 }

package/skills/tfx-workspace/async-tests/run-tests.sh

@@ -0,0 +1,203 @@
+#!/usr/bin/env bash
+# tfx-route.sh v2.5 async job system — 통합 테스트
+set -uo pipefail
+
+ROUTE="scripts/tfx-route.sh"
+PASS=0
+FAIL=0
+TOTAL=0
+
+assert_eq() {
+  local name="$1" expected="$2" actual="$3"
+  TOTAL=$((TOTAL + 1))
+  if [[ "$actual" == *"$expected"* ]]; then
+    echo "  ✓ $name"
+    PASS=$((PASS + 1))
+  else
+    echo "  ✗ $name — expected: '$expected', got: '$actual'"
+    FAIL=$((FAIL + 1))
+  fi
+}
+
+assert_neq() {
+  local name="$1" unexpected="$2" actual="$3"
+  TOTAL=$((TOTAL + 1))
+  if [[ "$actual" != *"$unexpected"* ]]; then
+    echo "  ✓ $name"
+    PASS=$((PASS + 1))
+  else
+    echo "  ✗ $name — should NOT contain: '$unexpected', got: '$actual'"
+    FAIL=$((FAIL + 1))
+  fi
+}
+
+assert_exit() {
+  local name="$1" expected="$2" actual="$3"
+  TOTAL=$((TOTAL + 1))
+  if [[ "$actual" -eq "$expected" ]]; then
+    echo "  ✓ $name"
+    PASS=$((PASS + 1))
+  else
+    echo "  ✗ $name — expected exit=$expected, got exit=$actual"
+    FAIL=$((FAIL + 1))
+  fi
+}
+
+echo "═══ tfx-route.sh v2.5 Async Job System Tests ═══"
+echo ""
+
+# ── Test 1: --async 기본 동작 ──
+echo "Test 1: --async 기본 시작 + job_id 반환"
+JOB_ID=$(bash "$ROUTE" --async executor "echo hello" none 30 2>/dev/null)
+EC=$?
+assert_exit "exit code 0" 0 "$EC"
+TOTAL=$((TOTAL + 1))
+if [[ -n "$JOB_ID" ]]; then echo "  ✓ job_id not empty ($JOB_ID)"; PASS=$((PASS + 1)); else echo "  ✗ job_id is empty"; FAIL=$((FAIL + 1)); fi
+assert_neq "job_id not error" "error" "$JOB_ID"
+echo ""
+
+# ── Test 2: --job-status running → done 전이 ──
+echo "Test 2: --job-status 상태 전이 (running → done)"
+LONG_JOB=$(bash "$ROUTE" --async executor "sleep 3 && echo done" none 60 2>/dev/null)
+STATUS_EARLY=$(bash "$ROUTE" --job-status "$LONG_JOB" 2>/dev/null)
+assert_eq "initial status: running" "running" "$STATUS_EARLY"
+
+# Codex 시작 ~10초 + sleep 3초 + 후처리 → 최대 25초 대기
+for i in $(seq 1 5); do
+  sleep 5
+  STATUS_LATE=$(bash "$ROUTE" --job-status "$LONG_JOB" 2>/dev/null)
+  [[ "$STATUS_LATE" == "done" ]] && break
+done
+assert_eq "final status: done" "done" "$STATUS_LATE"
+echo ""
+
+# ── Test 3: --job-status 존재하지 않는 job ──
+echo "Test 3: --job-status 존재하지 않는 job"
+RESULT=$(bash "$ROUTE" --job-status "nonexistent-12345" 2>/dev/null)
+EC=$?
+assert_eq "returns error" "error" "$RESULT"
+assert_exit "exit code 1" 1 "$EC"
+echo ""
+
+# ── Test 4: --job-result 완료된 job ──
+echo "Test 4: --job-result 완료된 job 결과 읽기"
+# Test 1의 JOB_ID 재사용 — Codex 완료 대기
+for i in $(seq 1 6); do
+  S=$(bash "$ROUTE" --job-status "$JOB_ID" 2>/dev/null)
+  [[ "$S" == "done" ]] && break
+  sleep 5
+done
+RESULT=$(bash "$ROUTE" --job-result "$JOB_ID" 2>/dev/null)
+EC=$?
+assert_exit "exit code 0" 0 "$EC"
+TOTAL=$((TOTAL + 1))
+if [[ -n "$RESULT" ]]; then echo "  ✓ result not empty (${#RESULT} bytes)"; PASS=$((PASS + 1)); else echo "  ✗ result is empty"; FAIL=$((FAIL + 1)); fi
+assert_neq "result not error" "error:" "$RESULT"
+echo ""
+
+# ── Test 5: --job-result 아직 실행 중인 job ──
+echo "Test 5: --job-result 실행 중인 job → 에러"
+RUNNING_JOB=$(bash "$ROUTE" --async executor "sleep 30" none 60 2>/dev/null)
+RESULT=$(bash "$ROUTE" --job-result "$RUNNING_JOB" 2>/dev/null)
+EC=$?
+assert_eq "returns error" "error: job still running" "$RESULT"
+assert_exit "exit code 1" 1 "$EC"
+# cleanup
+JOB_DIR="${TMPDIR:-/tmp}/tfx-jobs/$RUNNING_JOB"
+[[ -f "$JOB_DIR/pid" ]] && kill "$(cat "$JOB_DIR/pid")" 2>/dev/null
+echo ""
+
+# ── Test 6: --job-wait 완료 감지 ──
+echo "Test 6: --job-wait 완료 감지"
+WAIT_JOB=$(bash "$ROUTE" --async executor "echo wait-test-ok" none 30 2>/dev/null)
+sleep 15  # codex 실행 대기
+WAIT_RESULT=$(bash "$ROUTE" --job-wait "$WAIT_JOB" 60 2>/dev/null)
+assert_eq "wait returns done" "done" "$WAIT_RESULT"
+echo ""
+
+# ── Test 7: --job-wait still_running (max_wait < 실행시간) ──
+echo "Test 7: --job-wait still_running (짧은 max_wait)"
+SLOW_JOB=$(bash "$ROUTE" --async executor "sleep 60" none 120 2>/dev/null)
+sleep 1
+WAIT_RESULT=$(bash "$ROUTE" --job-wait "$SLOW_JOB" 5 2>/dev/null)
+assert_eq "wait returns still_running" "still_running" "$WAIT_RESULT"
+# cleanup
+JOB_DIR="${TMPDIR:-/tmp}/tfx-jobs/$SLOW_JOB"
+[[ -f "$JOB_DIR/pid" ]] && kill "$(cat "$JOB_DIR/pid")" 2>/dev/null
+echo ""
+
+# ── Test 8: exit code 전파 ──
+echo "Test 8: 실패한 job의 exit code 전파"
+FAIL_JOB=$(bash "$ROUTE" --async executor "exit 42" none 30 2>/dev/null)
+# Codex 완료 대기
+for i in $(seq 1 8); do
+  S=$(bash "$ROUTE" --job-status "$FAIL_JOB" 2>/dev/null)
+  [[ "$S" != *"running"* ]] && break
+  sleep 5
+done
+STATUS=$(bash "$ROUTE" --job-status "$FAIL_JOB" 2>/dev/null)
+# Codex가 exit 42를 감싸서 성공/실패 둘 다 가능 — "running이 아님"만 확인
+TOTAL=$((TOTAL + 1))
+if [[ "$STATUS" == "done" || "$STATUS" == *"failed"* || "$STATUS" == "timeout" ]]; then
+  echo "  ✓ status is terminal: $STATUS"; PASS=$((PASS + 1))
+else
+  echo "  ✗ status not terminal: $STATUS"; FAIL=$((FAIL + 1))
+fi
+# Codex는 exit 42를 감싸서 다른 코드로 반환할 수 있음 — 완료 자체만 확인
+TOTAL=$((TOTAL + 1))
+if [[ "$STATUS" != *"running"* ]]; then echo "  ✓ job completed (not stuck running)"; PASS=$((PASS + 1)); else echo "  ✗ job still running"; FAIL=$((FAIL + 1)); fi
+echo ""
+
+# ── Test 9: job 디렉토리 구조 검증 ──
+echo "Test 9: job 디렉토리 구조"
+STRUCT_JOB=$(bash "$ROUTE" --async executor "echo structure-test" none 30 2>/dev/null)
+JOB_DIR="${TMPDIR:-/tmp}/tfx-jobs/$STRUCT_JOB"
+assert_eq "pid file exists" "true" "$([ -f "$JOB_DIR/pid" ] && echo true || echo false)"
+assert_eq "agent_type file exists" "true" "$([ -f "$JOB_DIR/agent_type" ] && echo true || echo false)"
+assert_eq "start_time file exists" "true" "$([ -f "$JOB_DIR/start_time" ] && echo true || echo false)"
+AGENT=$(cat "$JOB_DIR/agent_type" 2>/dev/null)
+assert_eq "agent_type == executor" "executor" "$AGENT"
+echo ""
+
+# ── Test 10: native.mjs 프롬프트 검증 ──
+echo "Test 10: native.mjs buildSlimWrapperPrompt async 키워드"
+PROMPT_CHECK=$(node -e "
+import('./hub/team/native.mjs').then(m => {
+  const p = m.buildSlimWrapperPrompt('codex', {
+    subtask: 'test task',
+    role: 'scientist',
+    teamName: 'test-team',
+    taskId: 'task-1',
+    agentName: 'codex-worker-1',
+  });
+  const checks = {
+    has_async: p.includes('--async'),
+    has_job_wait: p.includes('--job-wait'),
+    has_job_result: p.includes('--job-result'),
+    has_route_timeout: p.includes('auto 1800'),
+    no_old_bashTimeout: !p.includes('timeout: 1860000'),
+    has_launch_timeout: p.includes('timeout: 15000'),
+    has_wait_timeout: p.includes('timeout: 570000'),
+    has_result_timeout: p.includes('timeout: 30000'),
+  };
+  for (const [k, v] of Object.entries(checks)) {
+    console.log(k + '=' + v);
+  }
+});
+" 2>/dev/null)
+for line in $PROMPT_CHECK; do
+  key="${line%%=*}"
+  val="${line##*=}"
+  assert_eq "$key" "true" "$val"
+done
+echo ""
+
+# ── 결과 요약 ──
+echo "═══════════════════════════════════════════════════"
+echo "  Results: $PASS/$TOTAL passed, $FAIL failed"
+echo "═══════════════════════════════════════════════════"
+
+if [[ "$FAIL" -gt 0 ]]; then
+  exit 1
+fi
+exit 0

package/skills/tfx-workspace/evals/evals.json

@@ -0,0 +1,79 @@
+{
+  "skill_name": "tfx-skills-suite",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "You are a Claude Code agent. Read the tfx-auto skill definition, then explain how you would handle this user request: '/implement JWT 인증 미들웨어 추가해줘'. List the EXACT bash commands you would run. Do NOT actually execute them.",
+      "expected_output": "Should route to executor agent via tfx-route.sh with 'implement' MCP profile. Command: bash ~/.claude/scripts/tfx-route.sh executor 'JWT 인증 미들웨어 추가해줘' implement",
+      "files": [],
+      "expectations": [
+        "Routes to 'executor' agent (not architect, not analyst)",
+        "Uses 'implement' MCP profile",
+        "Generates correct tfx-route.sh command syntax",
+        "Does NOT trigger triage (single command shortcut)",
+        "Does NOT delegate to tfx-multi"
+      ]
+    },
+    {
+      "id": 2,
+      "prompt": "You are a Claude Code agent. Read the tfx-auto skill definition, then explain how you would handle: '/tfx-auto 프론트엔드 리팩터링하고 보안 리뷰도 해줘'. List all routing decisions, triage steps, and delegation.",
+      "expected_output": "Should enter auto triage mode, classify via Codex, decompose into 2+ subtasks, then delegate to tfx-multi Phase 3",
+      "files": [],
+      "expectations": [
+        "Identifies this as auto mode (not command shortcut)",
+        "Triggers Codex classification step",
+        "Decomposes into at least 2 subtasks",
+        "Notes delegation to tfx-multi for subtasks >= 2",
+        "Does NOT try to execute all subtasks directly"
+      ]
+    },
+    {
+      "id": 3,
+      "prompt": "You are a Claude Code agent. Read the tfx-multi skill definition, then explain step-by-step how you would handle: '/tfx-multi 인증 리팩터링 + UI 개선 + 보안 리뷰'. List all TeamCreate, TaskCreate, Agent calls with exact parameters.",
+      "expected_output": "Should create team, 3 TaskCreates, 3 Agent spawns with slim wrapper structure following Phase 0-5",
+      "files": [],
+      "expectations": [
+        "Creates exactly one TeamCreate with tfx- prefix naming",
+        "Creates 3 TaskCreate calls (one per subtask)",
+        "Spawns 3 Agent wrappers with mode: bypassPermissions",
+        "Uses tfx-route.sh inside Agent wrapper (not direct codex/gemini)",
+        "Includes Phase 5 cleanup (TeamDelete)"
+      ]
+    },
+    {
+      "id": 4,
+      "prompt": "You are a Claude Code agent. Read the tfx-doctor skill definition, then explain how you would handle: 'HUD가 안 보이고 codex도 안 되는데 어떻게 해?'. List exact commands and reasoning.",
+      "expected_output": "Should suggest running triflux doctor first, then triflux doctor --fix if issues found",
+      "files": [],
+      "expectations": [
+        "Runs 'triflux doctor' as first diagnostic step",
+        "Suggests '--fix' mode for auto-repair",
+        "Mentions HUD and CLI path checks in explanation",
+        "Does NOT jump straight to --reset (that's for cache only)"
+      ]
+    },
+    {
+      "id": 5,
+      "prompt": "You are a Claude Code agent. Read the tfx-hub skill definition, then explain how you would handle: '/tfx-hub start'. List exact commands.",
+      "expected_output": "Should run 'node hub/server.mjs' in background",
+      "files": [],
+      "expectations": [
+        "Runs 'node hub/server.mjs' with run_in_background=true",
+        "Mentions port 27888 and /mcp endpoint",
+        "Does NOT try to run any triage or routing"
+      ]
+    },
+    {
+      "id": 6,
+      "prompt": "You are a Claude Code agent. Read the tfx-codex skill definition, then explain the Gemini-to-Codex remapping. For '/tfx-codex API 문서를 작성하고 디자인 가이드도 만들어줘', list the routing showing how designer/writer get remapped.",
+      "expected_output": "designer remapped to Codex(high), writer to Codex Spark(spark_fast), TFX_CLI_MODE=codex env var",
+      "files": [],
+      "expectations": [
+        "designer remapped to Codex with effort: high",
+        "writer remapped to Codex Spark with effort: spark_fast",
+        "Sets TFX_CLI_MODE=codex environment variable",
+        "Changes MCP profile: designer->implement, writer->analyze"
+      ]
+    }
+  ]
+}

package/skills/tfx-workspace/iteration-1/benchmark.json

@@ -0,0 +1,162 @@
+{
+  "metadata": {
+    "skill_name": "tfx-skills-suite",
+    "skill_path": "C:/Users/SSAFY/Desktop/Projects/cli/triflux/skills",
+    "executor_model": "claude-sonnet-4-6",
+    "analyzer_model": "claude-opus-4-6",
+    "timestamp": "2026-03-19T10:00:00Z",
+    "evals_run": [1, 2, 3, 4, 5, 6],
+    "runs_per_configuration": 1
+  },
+  "runs": [
+    {
+      "eval_id": 1, "eval_name": "routing-implement-shortcut", "configuration": "with_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 5, "failed": 0, "total": 5, "time_seconds": 43.6, "tokens": 16303, "tool_calls": 4, "errors": 0},
+      "expectations": [
+        {"text": "Routes to executor agent", "passed": true, "evidence": "Correctly mapped from implement shortcut table"},
+        {"text": "Uses implement MCP profile", "passed": true, "evidence": "Mapped from shortcut table"},
+        {"text": "Generates correct tfx-route.sh command", "passed": true, "evidence": "bash ~/.claude/scripts/tfx-route.sh executor '...' implement"},
+        {"text": "Does NOT trigger triage", "passed": true, "evidence": "Command shortcut skips triage"},
+        {"text": "Does NOT delegate to tfx-multi", "passed": true, "evidence": "No subtask decomposition occurred"}
+      ]
+    },
+    {
+      "eval_id": 1, "eval_name": "routing-implement-shortcut", "configuration": "without_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 5, "failed": 0, "total": 5, "time_seconds": 48.1, "tokens": 16436, "tool_calls": 4, "errors": 0},
+      "expectations": [
+        {"text": "Routes to executor agent", "passed": true, "evidence": "Correctly mapped"},
+        {"text": "Uses implement MCP profile", "passed": true, "evidence": "Assigned by shortcut table"},
+        {"text": "Generates correct tfx-route.sh command", "passed": true, "evidence": "Correct syntax generated"},
+        {"text": "Does NOT trigger triage", "passed": true, "evidence": "Shortcut mode skips triage"},
+        {"text": "Does NOT delegate to tfx-multi", "passed": true, "evidence": "No delegation"}
+      ]
+    },
+    {
+      "eval_id": 2, "eval_name": "routing-multi-task-triage", "configuration": "with_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 5, "failed": 0, "total": 5, "time_seconds": 58.2, "tokens": 17584, "tool_calls": 3, "errors": 0},
+      "expectations": [
+        {"text": "Identifies as auto mode", "passed": true, "evidence": "No shortcut match, auto mode selected"},
+        {"text": "Triggers Codex classification", "passed": true, "evidence": "Codex --full-auto classification triggered"},
+        {"text": "Decomposes into 2+ subtasks", "passed": true, "evidence": "2 subtasks: executor + security-reviewer"},
+        {"text": "Notes tfx-multi delegation", "passed": true, "evidence": "subtasks.length >= 2 triggers tfx-multi Phase 3"},
+        {"text": "Does NOT execute directly", "passed": true, "evidence": "Delegates to tfx-multi"}
+      ]
+    },
+    {
+      "eval_id": 2, "eval_name": "routing-multi-task-triage", "configuration": "without_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 5, "failed": 0, "total": 5, "time_seconds": 77.2, "tokens": 18626, "tool_calls": 4, "errors": 0},
+      "expectations": [
+        {"text": "Identifies as auto mode", "passed": true, "evidence": "Auto mode selected"},
+        {"text": "Triggers Codex classification", "passed": true, "evidence": "Codex --full-auto triggered"},
+        {"text": "Decomposes into 2+ subtasks", "passed": true, "evidence": "2 subtasks decomposed"},
+        {"text": "Notes tfx-multi delegation", "passed": true, "evidence": "Hands off to tfx-multi Phase 3"},
+        {"text": "Does NOT execute directly", "passed": true, "evidence": "Delegates correctly"}
+      ]
+    },
+    {
+      "eval_id": 3, "eval_name": "multi-team-creation", "configuration": "with_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 5, "failed": 0, "total": 5, "time_seconds": 115.3, "tokens": 27197, "tool_calls": 3, "errors": 0},
+      "expectations": [
+        {"text": "Creates TeamCreate with tfx- prefix", "passed": true, "evidence": "TeamCreate({ team_name: 'tfx-<base36>' })"},
+        {"text": "Creates 3 TaskCreate calls", "passed": true, "evidence": "3x TaskCreate with metadata"},
+        {"text": "Spawns 3 Agent wrappers with bypassPermissions", "passed": true, "evidence": "3x Agent({ mode: bypassPermissions })"},
+        {"text": "Uses tfx-route.sh inside wrappers", "passed": true, "evidence": "Direct codex/gemini calls prohibited"},
+        {"text": "Includes Phase 5 TeamDelete", "passed": true, "evidence": "TeamDelete always runs, max 30s wait"}
+      ]
+    },
+    {
+      "eval_id": 3, "eval_name": "multi-team-creation", "configuration": "without_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 5, "failed": 0, "total": 5, "time_seconds": 100.6, "tokens": 26140, "tool_calls": 3, "errors": 0},
+      "expectations": [
+        {"text": "Creates TeamCreate with tfx- prefix", "passed": true, "evidence": "TeamCreate with tfx-<id>"},
+        {"text": "Creates 3 TaskCreate calls", "passed": true, "evidence": "Three TaskCreate calls"},
+        {"text": "Spawns 3 Agent wrappers with bypassPermissions", "passed": true, "evidence": "mode: bypassPermissions in all 3"},
+        {"text": "Uses tfx-route.sh inside wrappers", "passed": true, "evidence": "Never direct codex/gemini calls"},
+        {"text": "Includes Phase 5 TeamDelete", "passed": true, "evidence": "TeamDelete unconditionally"}
+      ]
+    },
+    {
+      "eval_id": 4, "eval_name": "doctor-diagnosis", "configuration": "with_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 4, "failed": 0, "total": 4, "time_seconds": 53.8, "tokens": 14499, "tool_calls": 4, "errors": 0},
+      "expectations": [
+        {"text": "Runs triflux doctor first", "passed": true, "evidence": "Bash(\"triflux doctor\")"},
+        {"text": "Suggests --fix mode", "passed": true, "evidence": "Suggests after diagnosis report"},
+        {"text": "Mentions HUD and CLI checks", "passed": true, "evidence": "HUD and CLI paths checked"},
+        {"text": "Does NOT jump to --reset", "passed": true, "evidence": "--reset reserved for explicit request"}
+      ]
+    },
+    {
+      "eval_id": 4, "eval_name": "doctor-diagnosis", "configuration": "without_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 4, "failed": 0, "total": 4, "time_seconds": 48.3, "tokens": 14482, "tool_calls": 3, "errors": 0},
+      "expectations": [
+        {"text": "Runs triflux doctor first", "passed": true, "evidence": "Bash(\"triflux doctor\")"},
+        {"text": "Suggests --fix mode", "passed": true, "evidence": "Offers --fix after diagnosis"},
+        {"text": "Mentions HUD and CLI checks", "passed": true, "evidence": "All 8 diagnostics listed"},
+        {"text": "Does NOT jump to --reset", "passed": true, "evidence": "--reset reserved for explicit request"}
+      ]
+    },
+    {
+      "eval_id": 5, "eval_name": "hub-start-sequence", "configuration": "with_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 3, "failed": 0, "total": 3, "time_seconds": 47.2, "tokens": 14821, "tool_calls": 4, "errors": 0},
+      "expectations": [
+        {"text": "Runs node hub/server.mjs in background", "passed": true, "evidence": "Bash(\"node hub/server.mjs\", run_in_background=true)"},
+        {"text": "Mentions port 27888 and /mcp", "passed": true, "evidence": "Port 27888, http://127.0.0.1:27888/mcp"},
+        {"text": "No triage or routing attempted", "passed": true, "evidence": "Command match, not fallthrough"}
+      ]
+    },
+    {
+      "eval_id": 5, "eval_name": "hub-start-sequence", "configuration": "without_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 3, "failed": 0, "total": 3, "time_seconds": 51.8, "tokens": 14904, "tool_calls": 4, "errors": 0},
+      "expectations": [
+        {"text": "Runs node hub/server.mjs in background", "passed": true, "evidence": "Bash(\"node hub/server.mjs\", run_in_background=true)"},
+        {"text": "Mentions port 27888 and /mcp", "passed": true, "evidence": "Port 27888, endpoint /mcp"},
+        {"text": "No triage or routing attempted", "passed": true, "evidence": "Command match, not fallthrough"}
+      ]
+    },
+    {
+      "eval_id": 6, "eval_name": "codex-gemini-remap", "configuration": "with_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 4, "failed": 0, "total": 4, "time_seconds": 69.7, "tokens": 14889, "tool_calls": 5, "errors": 0},
+      "expectations": [
+        {"text": "designer remapped to Codex (effort: high)", "passed": true, "evidence": "designer → Codex (effort: high)"},
+        {"text": "writer remapped to Codex Spark (spark_fast)", "passed": true, "evidence": "writer → Codex Spark (effort: spark_fast)"},
+        {"text": "TFX_CLI_MODE=codex set", "passed": true, "evidence": "Set for every Phase 3 call"},
+        {"text": "MCP profiles changed", "passed": true, "evidence": "designer→implement, writer→analyze"}
+      ]
+    },
+    {
+      "eval_id": 6, "eval_name": "codex-gemini-remap", "configuration": "without_skill", "run_number": 1,
+      "result": {"pass_rate": 1.0, "passed": 4, "failed": 0, "total": 4, "time_seconds": 85.2, "tokens": 19802, "tool_calls": 7, "errors": 0},
+      "expectations": [
+        {"text": "designer remapped to Codex (effort: high)", "passed": true, "evidence": "designer → Codex (effort: high)"},
+        {"text": "writer remapped to Codex Spark (spark_fast)", "passed": true, "evidence": "writer → Codex Spark (effort: spark_fast)"},
+        {"text": "TFX_CLI_MODE=codex set", "passed": true, "evidence": "TFX_CLI_MODE set to codex"},
+        {"text": "MCP profiles changed", "passed": true, "evidence": "writer→analyze, designer→implement"}
+      ]
+    }
+  ],
+  "run_summary": {
+    "with_skill": {
+      "pass_rate": {"mean": 1.0, "stddev": 0.0, "min": 1.0, "max": 1.0},
+      "time_seconds": {"mean": 64.6, "stddev": 26.4, "min": 43.6, "max": 115.3},
+      "tokens": {"mean": 17549, "stddev": 4857, "min": 14499, "max": 27197}
+    },
+    "without_skill": {
+      "pass_rate": {"mean": 1.0, "stddev": 0.0, "min": 1.0, "max": 1.0},
+      "time_seconds": {"mean": 68.5, "stddev": 20.4, "min": 48.1, "max": 100.6},
+      "tokens": {"mean": 18398, "stddev": 4227, "min": 14482, "max": 26140}
+    },
+    "delta": {
+      "pass_rate": "+0.00",
+      "time_seconds": "-3.9",
+      "tokens": "-849"
+    }
+  },
+  "notes": [
+    "All 26 assertions pass at 100% for both configurations — the skills are functionally correct",
+    "The fixes applied (dead reference removal, Phase numbering consistency, hub description) don't change routing logic, so pass rates are identical",
+    "NEW version is marginally faster (-3.9s avg) and uses fewer tokens (-849 avg), likely due to cleaner references reducing model confusion",
+    "tfx-multi is the most complex skill (115s / 27K tokens with_skill) — consider extracting reference docs to reduce context load",
+    "tfx-codex OLD references 'Phase(1~6)' which doesn't exist in tfx-auto — the NEW version correctly references the actual workflow names",
+    "All assertions pass regardless of configuration — these test the core routing logic which is unchanged. Consider adding assertions that specifically test the fixed issues (dead refs, phase naming) for differentiation"
+  ]
+}

package/skills/tfx-workspace/iteration-1/codex-gemini-remap/eval_metadata.json

@@ -0,0 +1,11 @@
+{
+  "eval_id": 6,
+  "eval_name": "codex-gemini-remap",
+  "prompt": "/tfx-codex API 문서를 작성하고 디자인 가이드도 만들어줘",
+  "assertions": [
+    "designer remapped to Codex with effort: high",
+    "writer remapped to Codex Spark with effort: spark_fast",
+    "Sets TFX_CLI_MODE=codex environment variable",
+    "Changes MCP profile: designer->implement, writer->analyze"
+  ]
+}

package/skills/tfx-workspace/iteration-1/codex-gemini-remap/old_skill/grading.json

@@ -0,0 +1,9 @@
+{
+  "expectations": [
+    {"text": "designer remapped to Codex with effort: high", "passed": true, "evidence": "Agent output: designer → Codex (effort: high)"},
+    {"text": "writer remapped to Codex Spark with effort: spark_fast", "passed": true, "evidence": "Agent output: writer → Codex Spark (effort: spark_fast)"},
+    {"text": "Sets TFX_CLI_MODE=codex environment variable", "passed": true, "evidence": "Agent output: 'TFX_CLI_MODE: Set to codex'"},
+    {"text": "Changes MCP profile: designer->implement, writer->analyze", "passed": true, "evidence": "Agent output: writer→analyze, designer→implement"}
+  ],
+  "summary": {"passed": 4, "failed": 0, "total": 4, "pass_rate": 1.0}
+}