@thierrynakoa/fire-flow 10.0.0 → 12.2.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (94) hide show
  1. package/.claude-plugin/plugin.json +8 -8
  2. package/ARCHITECTURE-DIAGRAM.md +7 -4
  3. package/COMMAND-REFERENCE.md +33 -13
  4. package/DOMINION-FLOW-OVERVIEW.md +581 -421
  5. package/QUICK-START.md +3 -3
  6. package/README.md +101 -44
  7. package/TROUBLESHOOTING.md +264 -264
  8. package/agents/fire-executor.md +200 -116
  9. package/agents/fire-fact-checker.md +276 -276
  10. package/agents/fire-phoenix-analyst.md +394 -0
  11. package/agents/fire-planner.md +145 -53
  12. package/agents/fire-project-researcher.md +155 -155
  13. package/agents/fire-research-synthesizer.md +166 -166
  14. package/agents/fire-researcher.md +144 -59
  15. package/agents/fire-roadmapper.md +215 -203
  16. package/agents/fire-verifier.md +247 -65
  17. package/agents/fire-vision-architect.md +381 -0
  18. package/commands/fire-0-orient.md +476 -476
  19. package/commands/fire-1a-new.md +216 -0
  20. package/commands/fire-1b-research.md +210 -0
  21. package/commands/fire-1c-setup.md +254 -0
  22. package/commands/{fire-1a-discuss.md → fire-1d-discuss.md} +35 -7
  23. package/commands/fire-3-execute.md +55 -2
  24. package/commands/fire-4-verify.md +61 -0
  25. package/commands/fire-5-handoff.md +2 -2
  26. package/commands/fire-6-resume.md +37 -2
  27. package/commands/fire-add-new-skill.md +2 -2
  28. package/commands/fire-autonomous.md +20 -3
  29. package/commands/fire-brainstorm.md +1 -1
  30. package/commands/fire-complete-milestone.md +2 -2
  31. package/commands/fire-cost.md +183 -0
  32. package/commands/fire-dashboard.md +2 -2
  33. package/commands/fire-debug.md +663 -663
  34. package/commands/fire-loop-resume.md +2 -2
  35. package/commands/fire-loop-stop.md +1 -1
  36. package/commands/fire-loop.md +1168 -1168
  37. package/commands/fire-map-codebase.md +3 -3
  38. package/commands/fire-new-milestone.md +356 -356
  39. package/commands/fire-phoenix.md +603 -0
  40. package/commands/fire-reflect.md +235 -235
  41. package/commands/fire-research.md +246 -246
  42. package/commands/fire-search.md +1 -1
  43. package/commands/fire-skills-diff.md +3 -3
  44. package/commands/fire-skills-history.md +3 -3
  45. package/commands/fire-skills-rollback.md +7 -7
  46. package/commands/fire-skills-sync.md +5 -5
  47. package/commands/fire-test.md +9 -9
  48. package/commands/fire-todos.md +1 -1
  49. package/commands/fire-update.md +5 -5
  50. package/hooks/hooks.json +16 -16
  51. package/hooks/run-hook.sh +8 -8
  52. package/hooks/run-session-end.sh +7 -7
  53. package/hooks/session-end.sh +90 -90
  54. package/hooks/session-start.sh +1 -1
  55. package/package.json +4 -2
  56. package/plugin.json +7 -7
  57. package/references/metrics-and-trends.md +1 -1
  58. package/skills-library/SKILLS-INDEX.md +588 -588
  59. package/skills-library/_general/methodology/AUTONOMOUS_ORCHESTRATION.md +182 -0
  60. package/skills-library/_general/methodology/BACKWARD_PLANNING_INTERVIEW.md +307 -0
  61. package/skills-library/_general/methodology/CIRCUIT_BREAKER_INTELLIGENCE.md +163 -0
  62. package/skills-library/_general/methodology/CONTEXT_ROTATION.md +151 -0
  63. package/skills-library/_general/methodology/DEAD_ENDS_SHELF.md +188 -0
  64. package/skills-library/_general/methodology/DESIGN_PHILOSOPHY_ENFORCEMENT.md +152 -0
  65. package/skills-library/_general/methodology/INTERNAL_CONSISTENCY_AUDIT.md +212 -0
  66. package/skills-library/_general/methodology/LIVE_BREADCRUMB_PROTOCOL.md +242 -0
  67. package/skills-library/_general/methodology/PHOENIX_REBUILD_METHODOLOGY.md +251 -0
  68. package/skills-library/_general/methodology/QUALITY_GATES_AND_VERIFICATION.md +157 -0
  69. package/skills-library/_general/methodology/RELIABILITY_PREDICTION.md +104 -0
  70. package/skills-library/_general/methodology/REQUIREMENTS_DECOMPOSITION.md +155 -0
  71. package/skills-library/_general/methodology/SELF_TESTING_FEEDBACK_LOOP.md +143 -0
  72. package/skills-library/_general/methodology/STACK_COMPATIBILITY_MATRIX.md +178 -0
  73. package/skills-library/_general/methodology/TIERED_CONTEXT_ARCHITECTURE.md +118 -0
  74. package/skills-library/_general/methodology/ZERO_FRICTION_CLI_SETUP.md +312 -0
  75. package/skills-library/_general/methodology/autonomous-multi-phase-build.md +133 -0
  76. package/skills-library/_general/methodology/claude-md-archival.md +280 -0
  77. package/skills-library/_general/methodology/debug-swarm-researcher-escape-hatch.md +240 -240
  78. package/skills-library/_general/methodology/git-worktrees-parallel.md +232 -0
  79. package/skills-library/_general/methodology/llm-judge-memory-crud.md +241 -0
  80. package/skills-library/_general/methodology/multi-project-autonomous-build.md +360 -0
  81. package/skills-library/_general/methodology/shell-autonomous-loop-fixplan.md +238 -238
  82. package/skills-library/_general/patterns-standards/GOF_DESIGN_PATTERNS_FOR_AI_AGENTS.md +358 -0
  83. package/skills-library/methodology/BREATH_BASED_PARALLEL_EXECUTION.md +1 -1
  84. package/skills-library/methodology/RESEARCH_BACKED_WORKFLOW_UPGRADE.md +1 -1
  85. package/skills-library/methodology/SABBATH_REST_PATTERN.md +1 -1
  86. package/templates/ASSUMPTIONS.md +1 -1
  87. package/templates/BLOCKERS.md +1 -1
  88. package/templates/DECISION_LOG.md +1 -1
  89. package/templates/phase-prompt.md +1 -1
  90. package/templates/phoenix-comparison.md +80 -0
  91. package/version.json +2 -2
  92. package/workflows/handoff-session.md +1 -1
  93. package/workflows/new-project.md +2 -2
  94. package/commands/fire-1-new.md +0 -281
@@ -0,0 +1,603 @@
1
+ ---
2
+ description: Autonomous Phoenix Rebuild — reverse-engineer intent from messy code, then rebuild clean from scratch
3
+ argument-hint: "--source <path> [--target <path>] [--migrate] [--dry-run] [--focus <subsystem>]"
4
+ ---
5
+
6
+ # /fire-phoenix
7
+
8
+ > Burn the Frankenstein. Rise production-ready. Reverse-engineer INTENT from messy code, ask clarifying questions, then rebuild clean in a new folder.
9
+
10
+ ---
11
+
12
+ ## Purpose
13
+
14
+ Take a messy "vibe coded" project and autonomously rebuild it into a clean, production-quality application. The source folder is **never modified** — the rebuild happens in a new target folder using the full Dominion Flow pipeline.
15
+
16
+ **What makes this different from refactoring:** Refactoring improves code incrementally. Phoenix burns the old code entirely and rebuilds from extracted INTENT. The result carries the knowledge but none of the accidental complexity.
17
+
18
+ > **Reference:** @skills-library/_general/methodology/PHOENIX_REBUILD_METHODOLOGY.md
19
+
20
+ **Core pipeline:**
21
+ ```
22
+ AUTOPSY → INTENT → CLARIFY → VISION → REBUILD → COMPARISON
23
+ ```
24
+
25
+ ---
26
+
27
+ ## Arguments
28
+
29
+ ```yaml
30
+ arguments:
31
+ --source:
32
+ type: path
33
+ required: true
34
+ description: "Path to the messy source project"
35
+ example: "/fire-phoenix --source C:/Projects/my-app"
36
+
37
+ --target:
38
+ type: path
39
+ required: false
40
+ default: "{source}-phoenix"
41
+ description: "Path for the clean rebuild output"
42
+ example: "/fire-phoenix --source ./app --target ./app-v2"
43
+
44
+ --migrate:
45
+ type: boolean
46
+ default: false
47
+ description: "Enable stack migration mode (propose alternative tech stacks)"
48
+
49
+ --dry-run:
50
+ type: boolean
51
+ default: false
52
+ description: "Run Phase 1-3 only (analyze + clarify). No rebuild."
53
+
54
+ --focus:
55
+ type: string
56
+ required: false
57
+ description: "Limit analysis to a specific subsystem"
58
+ example: "/fire-phoenix --source ./app --focus auth"
59
+ ```
60
+
61
+ ---
62
+
63
+ ## Process
64
+
65
+ ### Step 0: Path Verification Gate (MANDATORY)
66
+
67
+ ```
68
+ Validate ALL paths before any work:
69
+
70
+ 1. --source path EXISTS and is a directory
71
+ 2. --source contains code files (not empty)
72
+ 3. --target path does NOT exist (prevent overwrite)
73
+ 4. --source ≠ --target (prevent self-overwrite)
74
+ 5. --source is not inside --target or vice versa
75
+ 6. Working directory matches expected project context
76
+
77
+ IF any check fails:
78
+ Display error with specific violation
79
+ STOP — do not proceed
80
+
81
+ SAFETY RULE: Source folder is READ-ONLY for the entire pipeline.
82
+ - Autopsy documents write to {source}/.phoenix/ (metadata only)
83
+ - All code writes go to {target}/
84
+ - No file in {source}/ outside .phoenix/ is ever modified
85
+ ```
86
+
87
+ ### Step 1: Display Phoenix Banner
88
+
89
+ ```
90
+ +--------------------------------------------------------------+
91
+ | PHOENIX REBUILD |
92
+ +--------------------------------------------------------------+
93
+ | |
94
+ | Source: {source_path} |
95
+ | Target: {target_path} |
96
+ | Mode: {same-stack | migration} |
97
+ | Focus: {all | subsystem} |
98
+ | |
99
+ | Pipeline: |
100
+ | Phase 1: AUTOPSY — Map the mess |
101
+ | Phase 2: INTENT — Extract what it was trying to do |
102
+ | Phase 3: CLARIFY — Ask user about ambiguities |
103
+ | Phase 4: VISION — Design the clean architecture |
104
+ | Phase 5: REBUILD — Build it right |
105
+ | Phase 6: COMPARISON — Prove it's better |
106
+ | |
107
+ | Safety: Source is READ-ONLY. All writes go to target. |
108
+ | |
109
+ +--------------------------------------------------------------+
110
+ ```
111
+
112
+ IF `--dry-run`:
113
+ ```
114
+ DRY RUN — will execute Phases 1-3 only (Autopsy + Intent + Clarify).
115
+ No rebuild will occur. Remove --dry-run to execute full pipeline.
116
+ ```
117
+
118
+ ---
119
+
120
+ ### Phase 1: AUTOPSY — Map the Mess
121
+
122
+ > Understand the source codebase structure, stack, and problems.
123
+
124
+ ```
125
+ Create directory: {source}/.phoenix/autopsy/
126
+
127
+ Reuse /fire-map-codebase infrastructure:
128
+ Spawn 4 parallel mapper agents targeting {source}/:
129
+
130
+ Agent 1 (tech):
131
+ Focus: Technology stack, frameworks, libraries, versions
132
+ Output: {source}/.phoenix/autopsy/STACK.md
133
+
134
+ Agent 2 (arch):
135
+ Focus: Architecture patterns, data flow, entry points
136
+ Output: {source}/.phoenix/autopsy/ARCHITECTURE.md
137
+
138
+ Agent 3 (quality):
139
+ Focus: Code quality, anti-patterns, test coverage, error handling
140
+ Output: {source}/.phoenix/autopsy/CONCERNS.md
141
+
142
+ Agent 4 (concerns):
143
+ Focus: External integrations, APIs, services, databases
144
+ Output: {source}/.phoenix/autopsy/INTEGRATIONS.md
145
+
146
+ Additionally, the orchestrator produces:
147
+
148
+ {source}/.phoenix/autopsy/STRUCTURE.md:
149
+ - Full directory tree (2 levels deep)
150
+ - Entry point files identified
151
+ - Config files listed
152
+
153
+ {source}/.phoenix/autopsy/SOURCE-METRICS.md:
154
+ - Total files by extension
155
+ - LOC per file (sorted descending)
156
+ - Dependency list from package.json / requirements.txt / etc.
157
+ - Largest files flagged (>300 LOC)
158
+
159
+ IF git history available:
160
+ {source}/.phoenix/autopsy/GIT-HISTORY.md:
161
+ - Last 20 commits with messages
162
+ - Most-changed files (hotspots)
163
+ - Contributors
164
+ ```
165
+
166
+ **Completion gate:** All 7 autopsy documents exist and are non-empty.
167
+
168
+ ---
169
+
170
+ ### Phase 2: INTENT EXTRACTION — What Was It Trying to Do?
171
+
172
+ > **Reference:** @agents/fire-phoenix-analyst.md
173
+
174
+ ```
175
+ Spawn 2 fire-phoenix-analyst instances:
176
+
177
+ Instance 1 — Feature Analyst:
178
+ Input: All autopsy documents + source code access
179
+ Process: Steps 1-5 from fire-phoenix-analyst.md
180
+ Output: {source}/.phoenix/INTENT.md
181
+ - Project-level intent
182
+ - Technology stack table
183
+ - Feature inventory (per-feature: intent, uniqueness, quality,
184
+ classification, confidence, edge cases, dependencies)
185
+ - Data model intent
186
+ - Business rules catalog
187
+ - Accidental vs essential complexity
188
+ - Items needing clarification
189
+
190
+ Instance 2 — Architecture Analyst:
191
+ Input: All autopsy documents + source code access
192
+ Process: Step 6 from fire-phoenix-analyst.md
193
+ Output: {source}/.phoenix/INTENT-GRAPH.md
194
+ - Code → Intent → Clean mapping for all major features
195
+ - Anti-pattern replacement map
196
+ - Current vs target architecture
197
+ - Migration notes
198
+ ```
199
+
200
+ **Honesty Protocol:** Both instances apply the Three Questions before analysis. LOW confidence items are flagged, not fabricated.
201
+
202
+ **Completion gate:** Both INTENT.md and INTENT-GRAPH.md exist with non-empty feature inventories.
203
+
204
+ ---
205
+
206
+ ### Phase 3: CLARIFICATION — Resolve Ambiguities
207
+
208
+ ```
209
+ Read {source}/.phoenix/INTENT.md
210
+
211
+ Collect items needing clarification:
212
+ 1. Features with confidence: LOW
213
+ 2. Features with classification: UNKNOWN
214
+ 3. Edge cases with uncertain KEEP/KILL
215
+ 4. Items in the "Items Needing Clarification" section
216
+
217
+ Additionally, ask:
218
+ "Which features do you NOT want in the rebuild?"
219
+ "Are there any new features or changes you want added?"
220
+
221
+ Batch questions into rounds (max 3 rounds, 3-4 questions each):
222
+
223
+ Round 1: Critical ambiguities (HIGH uniqueness features with LOW confidence)
224
+ Round 2: Feature scope (what to keep, what to drop, what to add)
225
+ Round 3: Remaining clarifications (MEDIUM uniqueness features)
226
+
227
+ Use AskUserQuestion for each round.
228
+
229
+ After each round:
230
+ Update {source}/.phoenix/INTENT.md with answers
231
+ Mark clarified items with confidence: HIGH (CLARIFIED)
232
+
233
+ IF --focus specified:
234
+ Only ask about features in the focused subsystem
235
+ Mark out-of-focus features as "DEFERRED — out of scope for this rebuild"
236
+ ```
237
+
238
+ **Completion gate:** No HIGH-uniqueness features remain at confidence: LOW.
239
+
240
+ ---
241
+
242
+ ### Phase 4: VISION — Design the Clean Architecture
243
+
244
+ ```
245
+ IF --migrate:
246
+ Spawn fire-vision-architect (if available) with:
247
+ Input: INTENT.md, INTENT-GRAPH.md
248
+ Task: Propose 2-3 technology stack alternatives
249
+ Output: {target}/.planning/VISION.md with stack branches
250
+
251
+ Present branches to user via AskUserQuestion:
252
+ "Which technology stack for the rebuild?"
253
+ Options: [branch summaries with trade-offs]
254
+
255
+ ELSE (same-stack rebuild — default):
256
+ Auto-generate {target}/.planning/VISION.md:
257
+ - Same technology stack as source (from STACK.md)
258
+ - Clean architecture based on INTENT-GRAPH.md target architecture
259
+ - Phase breakdown derived from INTENT.md feature inventory
260
+
261
+ Phase breakdown strategy (from PHOENIX_REBUILD_METHODOLOGY):
262
+ Phase 1: FOUNDATION
263
+ - Project scaffold, config, types/interfaces, database schema
264
+ - Environment setup, CI/CD skeleton
265
+ Phase 2: CORE
266
+ - Features with uniqueness CRITICAL and HIGH
267
+ - Ordered by dependency (foundations first)
268
+ Phase 3: SUPPORT
269
+ - Features with uniqueness MEDIUM
270
+ - Ordered by dependency on CORE features
271
+ Phase 4: STANDARD
272
+ - Features with uniqueness LOW and BOILERPLATE
273
+ - Often auto-generated or minimal effort
274
+ Phase 5: INTEGRATION
275
+ - Wire everything together
276
+ - Cross-module flows, API contracts
277
+ Phase 6: HARDENING
278
+ - Error handling, logging, security, edge cases
279
+ - All "KEEP" edge cases from INTENT.md
280
+ Phase 7: TESTING
281
+ - Tests written from INTENT.md assertions
282
+ - Feature parity verification
283
+ Phase 8: DOCUMENTATION
284
+ - README, API docs, deployment guide
285
+
286
+ Write {target}/.planning/VISION.md with:
287
+ - Project metadata (name, description, stack)
288
+ - Architecture description
289
+ - Phase list with descriptions
290
+ - Success criteria per phase
291
+ - Phoenix verification checks (PX-1 through PX-5)
292
+ ```
293
+
294
+ **Initialize target project:**
295
+ ```
296
+ Create {target}/ directory
297
+ Create {target}/.planning/ structure:
298
+ .planning/
299
+ VISION.md (just created)
300
+ CONSCIENCE.md (initialized empty)
301
+ MEMORY.md (populated from INTENT.md context)
302
+ phases/ (empty — fire-2-plan creates phase dirs)
303
+ ```
304
+
305
+ **Completion gate:** VISION.md exists with phases. Target directory initialized.
306
+
307
+ ---
308
+
309
+ ### Phase 5: REBUILD — Build It Right
310
+
311
+ > Standard Dominion Flow pipeline, with INTENT.md as the requirements source.
312
+
313
+ ```
314
+ FOR each phase in VISION.md (Phase 1 through Phase 8):
315
+
316
+ Display:
317
+ "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
318
+ " PHOENIX REBUILD: Phase {N} — {phase_name}"
319
+ "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
320
+
321
+ Working directory: {target}/
322
+
323
+ // ── PLAN ──
324
+ Run /fire-2-plan {N}
325
+ Planner reads INTENT.md as requirements source (via MEMORY.md reference)
326
+ Planner reads INTENT-GRAPH.md for clean implementation guidance
327
+ BLUEPRINT frontmatter includes:
328
+ phoenix_source: "{source_path}"
329
+ phoenix_intent: "{source}/.phoenix/INTENT.md"
330
+ phoenix_checks: [PX-1, PX-2, PX-3, PX-4, PX-5]
331
+ scope_manifest:
332
+ read_allowed: ["{source}/"] # read-only reference
333
+ write_allowed: ["{target}/"]
334
+ forbidden: ["modify {source}/ files"]
335
+
336
+ // ── EXECUTE ──
337
+ Run /fire-3-execute {N} --auto-continue
338
+ Executor follows BLUEPRINT tasks
339
+ Source folder referenced as READ-ONLY for code patterns
340
+ All writes go to {target}/
341
+
342
+ // ── VERIFY ──
343
+ Run /fire-4-verify {N}
344
+ Standard verification PLUS Phoenix-specific checks:
345
+
346
+ PX-1: Feature Parity (weight: 30%)
347
+ FOR each feature in INTENT.md:
348
+ Check: is it implemented in {target}/ OR explicitly marked as dropped?
349
+ Score: implemented_count / total_features * 100
350
+
351
+ PX-2: Edge Case Coverage (weight: 25%)
352
+ FOR each edge case marked "KEEP" in INTENT.md:
353
+ Check: is it handled in {target}/ code?
354
+ Score: handled_count / keep_count * 100
355
+
356
+ PX-3: Dependency Compatibility (weight: 20%)
357
+ FOR each external integration in INTEGRATIONS.md:
358
+ Check: is the connection configured in {target}/?
359
+ Score: connected_count / total_integrations * 100
360
+
361
+ PX-4: Accidental Complexity Removal (weight: 15%)
362
+ FOR each anti-pattern in INTENT-GRAPH.md:
363
+ Check: is the anti-pattern ABSENT from {target}/?
364
+ Score: absent_count / total_antipatterns * 100
365
+
366
+ PX-5: Architecture Improvement (weight: 10%)
367
+ Compare: target file structure vs source
368
+ Check: smaller avg file size, proper separation, consistent naming
369
+ Score: qualitative assessment 0-100
370
+
371
+ Phoenix Score = (PX-1 * 0.30) + (PX-2 * 0.25) + (PX-3 * 0.20)
372
+ + (PX-4 * 0.15) + (PX-5 * 0.10)
373
+
374
+ // ── EVALUATE ──
375
+ IF verifier_verdict == APPROVED or CONDITIONAL:
376
+ Advance to next phase
377
+ git add -A && git commit -m "phoenix: Phase {N} - {phase_name} complete"
378
+
379
+ ELSE (REJECTED):
380
+ attempt += 1
381
+ IF attempt < 3:
382
+ Re-plan with --gaps flag, re-execute
383
+ ELSE:
384
+ Display blocker, STOP with escalation options
385
+ ```
386
+
387
+ **Safety during rebuild:**
388
+ ```
389
+ ENFORCED throughout Phase 5:
390
+ - Source folder is READ-ONLY (scope manifest forbidden list)
391
+ - Circuit breaker active (CIRCUIT_BREAKER_INTELLIGENCE thresholds)
392
+ - HAC enforcement active
393
+ - Path verification on every phase
394
+ - Kill conditions checked before retries
395
+ ```
396
+
397
+ **Completion gate:** All rebuild phases reach APPROVED or CONDITIONAL verdict.
398
+
399
+ ---
400
+
401
+ ### Phase 6: COMPARISON — Prove It's Better
402
+
403
+ > **Reference:** @templates/phoenix-comparison.md
404
+
405
+ ```
406
+ Gather metrics from both projects:
407
+
408
+ Source metrics:
409
+ - Total files, LOC, avg/max file size
410
+ - Dependency count (from package.json / requirements.txt)
411
+ - Test file count, coverage estimate
412
+ - Anti-pattern count (from INTENT-GRAPH.md)
413
+
414
+ Target metrics:
415
+ - Same measurements from {target}/
416
+ - Phoenix verification scores (PX-1 through PX-5)
417
+
418
+ Write {target}/.planning/PHOENIX-COMPARISON.md using template:
419
+ @templates/phoenix-comparison.md
420
+
421
+ Calculate final Phoenix Score:
422
+ 90%+ = APPROVED — Rebuild is production-ready
423
+ 75-89% = CONDITIONAL — Minor fixes needed
424
+ <75% = REJECTED — Significant gaps, review INTENT.md coverage
425
+ ```
426
+
427
+ **Display completion banner:**
428
+ ```
429
+ +--------------------------------------------------------------+
430
+ | PHOENIX REBUILD COMPLETE |
431
+ +--------------------------------------------------------------+
432
+ | |
433
+ | Source: {source_path} |
434
+ | Target: {target_path} |
435
+ | |
436
+ | Before → After: |
437
+ | Files: {N} → {N} ({change}) |
438
+ | Lines of Code: {N} → {N} ({change}) |
439
+ | Dependencies: {N} → {N} ({change}) |
440
+ | Test Files: {N} → {N} ({change}) |
441
+ | Max File Size: {N} → {N} ({change}) |
442
+ | |
443
+ | Phoenix Score: {score}% — {verdict} |
444
+ | PX-1 Feature Parity: {score}% |
445
+ | PX-2 Edge Case Coverage: {score}% |
446
+ | PX-3 Dependency Compat: {score}% |
447
+ | PX-4 Complexity Removal: {score}% |
448
+ | PX-5 Architecture: {score}% |
449
+ | |
450
+ | Reports: |
451
+ | {source}/.phoenix/INTENT.md |
452
+ | {source}/.phoenix/INTENT-GRAPH.md |
453
+ | {target}/.planning/PHOENIX-COMPARISON.md |
454
+ | |
455
+ +--------------------------------------------------------------+
456
+ | NEXT STEPS |
457
+ +--------------------------------------------------------------+
458
+ | |
459
+ | /fire-dashboard — View project status |
460
+ | /fire-4-verify {N} — Detailed phase verification |
461
+ | /fire-phoenix --dry-run — Re-analyze without rebuilding |
462
+ | |
463
+ +--------------------------------------------------------------+
464
+ ```
465
+
466
+ IF `--dry-run`:
467
+ ```
468
+ +--------------------------------------------------------------+
469
+ | PHOENIX DRY RUN COMPLETE |
470
+ +--------------------------------------------------------------+
471
+ | |
472
+ | Analysis produced: |
473
+ | {source}/.phoenix/autopsy/ (7 documents) |
474
+ | {source}/.phoenix/INTENT.md |
475
+ | {source}/.phoenix/INTENT-GRAPH.md |
476
+ | |
477
+ | Features found: {N} ({N unique, {N ambiguous}) |
478
+ | Edge cases cataloged: {N} ({N keep, {N kill}) |
479
+ | Anti-patterns detected: {N} |
480
+ | Clarifications resolved: {N} |
481
+ | |
482
+ | To proceed with rebuild: |
483
+ | /fire-phoenix --source {source} |
484
+ | |
485
+ +--------------------------------------------------------------+
486
+ ```
487
+
488
+ ---
489
+
490
+ ## Blocker Handling
491
+
492
+ ```
493
+ IF any phase fails after max attempts:
494
+
495
+ +--------------------------------------------------------------+
496
+ | PHOENIX REBUILD STOPPED — BLOCKER |
497
+ +--------------------------------------------------------------+
498
+ | |
499
+ | Completed phases: {list} |
500
+ | Blocked at: Rebuild Phase {N} — {name} |
501
+ | |
502
+ | Blocker: {description} |
503
+ | |
504
+ | What was tried: |
505
+ | Attempt 1: {verdict} ({score}/70) |
506
+ | Attempt 2: {verdict} ({score}/70) |
507
+ | Attempt 3: {verdict} ({score}/70) |
508
+ | |
509
+ | Options: |
510
+ | A) /fire-debug — Investigate the blocker |
511
+ | B) /fire-3-execute {N} — Manual execution |
512
+ | C) /fire-phoenix --source {source} — Restart |
513
+ | D) /fire-dashboard — Review current state |
514
+ | |
515
+ +--------------------------------------------------------------+
516
+ ```
517
+
518
+ ---
519
+
520
+ ## Safety Guarantees
521
+
522
+ ```
523
+ NEVER DISABLED during Phoenix Rebuild:
524
+
525
+ 1. Source READ-ONLY — No file in {source}/ (except .phoenix/) is ever modified
526
+ 2. Path Verification — Source ≠ target, no nesting, paths exist
527
+ 3. Scope Manifests — Every rebuild phase has explicit read/write boundaries
528
+ 4. Circuit Breaker — CIRCUIT_BREAKER_INTELLIGENCE thresholds active
529
+ 5. HAC Enforcement — Known-bad actions blocked before execution
530
+ 6. Verification — fire-verifier + Phoenix checks (PX-1 through PX-5)
531
+
532
+ WHAT .phoenix/ CONTAINS (only metadata written to source):
533
+ .phoenix/
534
+ autopsy/ — 7 analysis documents (stack, arch, concerns, etc.)
535
+ INTENT.md — Extracted feature intent
536
+ INTENT-GRAPH.md — Code → Intent → Clean mapping
537
+
538
+ ALL CODE writes go to {target}/ exclusively.
539
+ ```
540
+
541
+ ---
542
+
543
+ ## Examples
544
+
545
+ ```bash
546
+ # Basic same-stack rebuild
547
+ /fire-phoenix --source C:/Projects/my-messy-app
548
+
549
+ # Custom target path
550
+ /fire-phoenix --source ./old-app --target ./old-app-v2
551
+
552
+ # Analyze only (no rebuild)
553
+ /fire-phoenix --source ./app --dry-run
554
+
555
+ # Focus on auth subsystem
556
+ /fire-phoenix --source ./app --focus auth
557
+
558
+ # Stack migration (propose new tech)
559
+ /fire-phoenix --source ./express-app --migrate
560
+ ```
561
+
562
+ ---
563
+
564
+ ## Agent & Skill References
565
+
566
+ | Component | Role in Pipeline |
567
+ |-----------|-----------------|
568
+ | **fire-phoenix-analyst** (agent) | Phase 2 — Extracts INTENT.md and INTENT-GRAPH.md |
569
+ | **fire-codebase-mapper** (agent) | Phase 1 — Reused for autopsy mapping |
570
+ | **fire-planner** (agent) | Phase 5 — Plans each rebuild phase from INTENT.md |
571
+ | **fire-executor** (agent) | Phase 5 — Executes rebuild tasks |
572
+ | **fire-verifier** (agent) | Phase 5 — Verifies + Phoenix checks (PX-1 to PX-5) |
573
+ | **PHOENIX_REBUILD_METHODOLOGY** (skill) | Knowledge base — intent extraction, anti-patterns, edge cases |
574
+ | **GOF_DESIGN_PATTERNS_FOR_AI_AGENTS** (skill) | Architecture reference for clean rebuild |
575
+ | **CIRCUIT_BREAKER_INTELLIGENCE** (skill) | Stuck-state handling during rebuild |
576
+ | **phoenix-comparison** (template) | Phase 6 — Before/after metrics report |
577
+
578
+ ---
579
+
580
+ ## Success Criteria
581
+
582
+ ```
583
+ - [ ] Path verification gate validates source/target paths
584
+ - [ ] Source folder is never modified (except .phoenix/ metadata)
585
+ - [ ] Phase 1 produces 7 autopsy documents
586
+ - [ ] Phase 2 produces INTENT.md + INTENT-GRAPH.md
587
+ - [ ] Phase 2 applies Honesty Protocol (LOW confidence items flagged, not fabricated)
588
+ - [ ] Phase 3 resolves ambiguities via user questions (max 3 rounds)
589
+ - [ ] Phase 4 generates VISION.md with rebuild phases
590
+ - [ ] Phase 5 runs full Dominion Flow pipeline per rebuild phase
591
+ - [ ] Phase 5 includes Phoenix verification checks (PX-1 through PX-5)
592
+ - [ ] Phase 6 produces PHOENIX-COMPARISON.md with before/after metrics
593
+ - [ ] Phoenix Score calculated: 90%+ APPROVED, 75-89% CONDITIONAL, <75% REJECTED
594
+ - [ ] --dry-run stops after Phase 3 (analysis only)
595
+ - [ ] --migrate presents stack alternatives in Phase 4
596
+ - [ ] --focus limits analysis to specified subsystem
597
+ - [ ] Circuit breaker, HAC, scope manifests all active during rebuild
598
+ - [ ] Blocker escalation with clear options when max attempts exceeded
599
+ ```
600
+
601
+ ---
602
+
603
+ *Dominion Flow v12.2 — Phoenix Rebuild: burn the mess, rise production-ready.*