@thierrynakoa/fire-flow 10.0.0 → 12.2.0

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 +9 -9
  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 +102 -45
  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 +2 -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
package/DOMINION-FLOW-OVERVIEW.md CHANGED
@@ -1,421 +1,581 @@
1
- # Dominion Flow v10.0 -- Complete System Overview
2
-
3
- Bird's eye view of the entire Dominion Flow system.
4
-
5
- ---
6
-
7
- ```
8
- +==============================================================================+
9
- | DOMINION FLOW v10.0 -- COMPLETE SYSTEM MAP |
10
- +==============================================================================+
11
-
12
-
13
- ===============================================================================
14
- 1. THE LIFECYCLE -- How a project flows from idea to done
15
- ===============================================================================
16
-
17
- +-------------+ +--------------+ +--------------+ +--------------+
18
- | /fire-1-new|--->| /fire-2-plan|--->|/fire-3-exec |--->|/fire-4-verify|
19
- | New Project| | Plan Phase | |Execute Phase | | Verify Phase |
20
- +------+------+ +------+-------+ +------+-------+ +------+-------+
21
- | | | |
22
- Questions Research & Breath-based Goal-backward
23
- Research Planning Execution Verification
24
- Roadmap + Checking + Commits + 70-point
25
- | | | |
26
- v v v v
27
- PROJECT.md BLUEPRINT.md RECORD.md VERIFICATION.md
28
- VISION.md |
29
- CONSCIENCE.md |
30
- | +----+----+
31
- | | PASS? |
32
- | +----+----+
33
- | yes/ \no
34
- | / \
35
- +------+--------------------------------------------------+ +----------+
36
- | NEXT PHASE / MILESTONE | | Gap Plans|
37
- | (loop back to /fire-2-plan) | | fix & re-|
38
- +-----------------------------------------------------+ | verify |
39
- +----------+
40
-
41
- AUTONOMOUS PATH (v9.0):
42
- +------------------------------------------------------------------+
43
- | /fire-autonomous |
44
- | |
45
- | After /fire-1-new completes, runs the ENTIRE pipeline: |
46
- | 2-plan --> 3-execute --> 4-verify (per phase, all phases) |
47
- | Auto-routes merge gate and review gate verdicts. |
48
- | No human checkpoints required. |
49
- +------------------------------------------------------------------+
50
-
51
- SESSION BOUNDARIES:
52
- +--------------+ +--------------+
53
- |/fire-5-hand | === session break ===> |/fire-6-resum|
54
- | off | POWER-HANDOFF-*.md | e |
55
- | Save context | (WARRIOR 7-step) | Load context |
56
- +--------------+ +--------------+
57
-
58
-
59
- ===============================================================================
60
- 2. ALL AGENTS -- Who does what
61
- ===============================================================================
62
-
63
- AGENT FILE DESCRIPTION SPAWNED BY
64
- ---------- ----------- ----------
65
- fire-executor.md Executes plans with honesty /fire-3-execute
66
- protocols, atomic commits, /fire-execute-plan
67
- creates RECORD.md handoffs /fire-autonomous
68
-
69
- fire-planner.md Creates phase plans with skills /fire-2-plan
70
- library integration and /fire-autonomous
71
- WARRIOR validation
72
-
73
- fire-researcher.md Researches phase context using /fire-research
74
- skills library, pattern matching, /fire-1-new
75
- and external search /fire-2-plan
76
-
77
- fire-verifier.md Must-haves verification + /fire-4-verify
78
- WARRIOR 70-point validation /fire-3-execute
79
-
80
- fire-reviewer.md Independent code review -- /fire-7-review
81
- architecture, patterns, perf, /fire-3-execute
82
- maintainability, security (parallel with verifier)
83
-
84
-
85
- AGENT CAPABILITIES:
86
- +-------------------------+----------+-------+------+------+------+---------+----------+
87
- | Agent | Read | Write | Edit | Bash | Grep | Web | Context7 |
88
- +-------------------------+----------+-------+------+------+------+---------+----------+
89
- | fire-executor | Y | Y | Y | Y | Y | | |
90
- | fire-planner | Y | Y | | Y | Y | Fetch | Y |
91
- | fire-researcher | Y | Y | | Y | Y | Both | Y |
92
- | fire-verifier | Y | | | Y | Y | | |
93
- | fire-reviewer | Y | | | Y | Y | | |
94
- +-------------------------+----------+-------+------+------+------+---------+----------+
95
-
96
-
97
- ===============================================================================
98
- 3. BREATH EXECUTION -- How /fire-3-execute parallelizes work
99
- ===============================================================================
100
-
101
- BLUEPRINT.md files have frontmatter: breath: 1, breath: 2, breath: 3 ...
102
-
103
- +---------------------------------------------------------+
104
- | BREATH 1 (parallel) |
105
- | |
106
- | +-------------+ +-------------+ +-------------+ |
107
- | | Plan 01-01 | | Plan 01-02 | | Plan 01-03 | |
108
- | | Foundation | | Schema | | Config | |
109
- | | | | | | | |
110
- | | executor <--| | executor <--| | executor <--| |
111
- | +------+------+ +------+------+ +------+------+ |
112
- | | | | |
113
- | v v v |
114
- | commit commit commit |
115
- +--------------------------+------------------------------+
116
- | all complete
117
- v
118
- +---------------------------------------------------------+
119
- | BREATH 2 (depends on breath 1) |
120
- | |
121
- | +-------------+ +-------------+ |
122
- | | Plan 01-04 | | Plan 01-05 | |
123
- | | API Routes | | Auth Flow | |
124
- | | | | | |
125
- | | executor <--| | executor <--| |
126
- | +------+------+ +------+------+ |
127
- | | | |
128
- | v v |
129
- | commit commit |
130
- +--------------------------+------------------------------+
131
- | all complete
132
- v
133
- +---------------------------------------------------------+
134
- | BREATH 3 |
135
- | +-------------+ |
136
- | | Plan 01-06 | Then: fire-verifier runs |
137
- | | UI + Tests | 70-point validation on everything |
138
- | +-------------+ + fire-reviewer in parallel (v8.0) |
139
- +---------------------------------------------------------+
140
-
141
- MODE SELECTION (auto per breath):
142
- +------------------------------------------------------+
143
- | 1 plan in breath --> Sequential (single executor) |
144
- | 2+ plans, no file overlap --> Parallel (Task tool) |
145
- | 2+ plans, file overlap --> Sequential (safe) |
146
- | 3+ plans, no overlap --> Team/Swarm mode |
147
- +------------------------------------------------------+
148
-
149
-
150
- ===============================================================================
151
- 4. NEW PROJECT FLOW -- /fire-1-new deep dive
152
- ===============================================================================
153
-
154
- User: "/fire-1-new My LMS Platform"
155
- |
156
- v
157
- +----------------------+
158
- | Adaptive Questioning | "What's the core value?"
159
- | (5-15 questions) | "Who are the users?"
160
- | | "What's v1 scope?"
161
- +----------+-----------+
162
- v
163
- +----------------------+
164
- | Write PROJECT.md | Core value, constraints, users
165
- | Write REQUIREMENTS | REQ-IDs: AUTH-01, CONT-01, etc.
166
- +----------+-----------+
167
- v
168
- +-------------------------------------------------------------+
169
- | 4 PARALLEL RESEARCHERS (fire-project-researcher x4) |
170
- | |
171
- | +----------+ +----------+ +----------+ +----------+ |
172
- | | STACK | | FEATURES | | ARCHITECT| | PITFALLS | |
173
- | | research | | research | | research | | research | |
174
- | +----+-----+ +----+-----+ +----+-----+ +----+-----+ |
175
- | | | | | |
176
- | v v v v |
177
- | STACK.md FEATURES.md ARCHITECT.md PITFALLS.md |
178
- +-----------------------+-------------------------------------+
179
- v
180
- +----------------------------------+
181
- | fire-research-synthesizer |
182
- | Merges 4 files -> RECORD.md |
183
- +------------------+---------------+
184
- v
185
- +----------------------------------+
186
- | fire-roadmapper |
187
- | |
188
- | Requirements -> Phase grouping |
189
- | Dependencies -> Ordering |
190
- | Goal-backward -> Success crit. |
191
- | Coverage validation (100%) |
192
- | |
193
- | Output: VISION.md + CONSCIENCE |
194
- +----------------------------------+
195
-
196
-
197
- ===============================================================================
198
- 5. VERIFICATION SYSTEM -- Dual-layer validation
199
- ===============================================================================
200
-
201
- +---------------------------------------------------------+
202
- | LAYER 1: MUST-HAVES (Goal-Backward) |
203
- | |
204
- | "What must be TRUE for this phase's goal?" |
205
- | |
206
- | Truths: Observable behaviors users can verify |
207
- | Artifacts: Files that must exist with specific exports|
208
- | Key Links: Components properly wired together |
209
- | |
210
- | Y User can log in with email/password |
211
- | Y JWT token persists across browser sessions |
212
- | X Password reset email sends (FAIL -> gap plan) |
213
- +---------------------------------------------------------+
214
- +
215
- +---------------------------------------------------------+
216
- | LAYER 2: WARRIOR 70-POINT CHECKLIST |
217
- | |
218
- | Code Quality ........... /10 Performance ...... /10 |
219
- | Testing ................ /10 Documentation .... /10 |
220
- | Security ............... /10 Infrastructure ... /10 |
221
- | E2E (Playwright) ...... /10 |
222
- | ---- |
223
- | /70 |
224
- | |
225
- | 63-70 = APPROVED 49-55 = CONDITIONAL |
226
- | 56-62 = APPROVED* <42 = REJECTED |
227
- +---------------------------------------------------------+
228
-
229
-
230
- ===============================================================================
231
- 6. FILE-BASED STATE MACHINE -- .planning/ directory
232
- ===============================================================================
233
-
234
- your-project/
235
- +-- .planning/
236
- +-- CONSCIENCE.md <-- Living project memory (updated constantly)
237
- +-- VISION.md <-- Phase overview + success criteria
238
- +-- REQUIREMENTS.md <-- REQ-IDs with traceability
239
- +-- PROJECT.md <-- Core value, users, constraints
240
- |
241
- +-- research/ <-- Created by /fire-1-new
242
- | +-- STACK.md
243
- | +-- FEATURES.md
244
- | +-- ARCHITECTURE.md
245
- | +-- PITFALLS.md
246
- | +-- RECORD.md
247
- |
248
- +-- codebase/ <-- Created by /fire-map-codebase
249
- | +-- STACK.md
250
- | +-- ARCHITECTURE.md
251
- | +-- STRUCTURE.md
252
- | +-- CONVENTIONS.md
253
- | +-- TESTING.md
254
- | +-- INTEGRATIONS.md
255
- | +-- CONCERNS.md
256
- |
257
- +-- phases/
258
- | +-- 01-foundation/
259
- | | +-- 01-01-BLUEPRINT.md <-- Breath 1
260
- | | +-- 01-02-BLUEPRINT.md <-- Breath 1
261
- | | +-- 01-03-BLUEPRINT.md <-- Breath 2
262
- | | +-- 01-01-RECORD.md <-- After execution
263
- | | +-- 01-VERIFICATION.md <-- After /fire-4-verify
264
- | | +-- 01-REVIEW.md <-- After /fire-7-review (v8.0)
265
- | | +-- 01-MEMORY.md <-- From /fire-1a-discuss
266
- | |
267
- | +-- 02-authentication/
268
- | | +-- ...
269
- | +-- 03-content/
270
- | +-- ...
271
- |
272
- +-- debug/ <-- Created by /fire-debug
273
- | +-- login-fails.md
274
- | +-- resolved/
275
- | +-- api-timeout.md
276
- |
277
- +-- loops/ <-- Created by /fire-loop
278
- | +-- fire-loop-{ID}.md
279
- | +-- sabbath-{ID}-iter{N}.md
280
- |
281
- +-- .shared-state.json <-- SWARM inter-agent coordination (v9.0)
282
- +-- POWER-HANDOFF-2026-02-14.md <-- Session continuity
283
-
284
-
285
- ===============================================================================
286
- 7. HOOKS & SESSION MANAGEMENT
287
- ===============================================================================
288
-
289
- +---------------------------------------------------------+
290
- | SESSION START |
291
- | +-- fire-check-update.js (check for plugin updates) |
292
- | +-- compact-reinject.js (restore context on /compact|
293
- | re-injects WARRIOR state) |
294
- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~+
295
- | STOP |
296
- | +-- stop-verify.js (warn if tasks incomplete) |
297
- +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~+
298
- | STATUSLINE (always visible) |
299
- | +-- statusline.js opus | current task | dir |
300
- | ^ /fire-update | 45% ctx |
301
- +---------------------------------------------------------+
302
-
303
-
304
- ===============================================================================
305
- 8. SKILLS LIBRARY -- 190+ reusable patterns
306
- ===============================================================================
307
-
308
- +------------------+ +------------------+ +------------------+
309
- | advanced-features| | api-patterns | | automation |
310
- | (11 skills) | | (12 skills) | | (7 skills) |
311
- +------------------+ +------------------+ +------------------+
312
- | database-solutions| | deploy-security | | doc-processing |
313
- | (12 skills) | | (17 skills) | | (5 skills) |
314
- +------------------+ +------------------+ +------------------+
315
- | ecommerce | | form-solutions | | integrations |
316
- | (15 skills) | | (8 skills) | | (20+ skills) |
317
- | stripe,paypal,GTA| | | | stripe,zoom,yt |
318
- +------------------+ +------------------+ +------------------+
319
- | lms-patterns | | methodology | | patterns-standard|
320
- | (30+ skills) | | (10 skills) | | (15 skills) |
321
- +------------------+ +------------------+ +------------------+
322
-
323
- /fire-search "stripe webhook" --> finds matching skills
324
- /fire-add-new-skill --> add from current session
325
- /fire-skills-history --> git log of skill changes
326
- /fire-skills-rollback --> revert to previous version
327
-
328
-
329
- ===============================================================================
330
- 9. ALL 39 COMMANDS -- Organized by tier
331
- ===============================================================================
332
-
333
- TIER 1: CORE WORKFLOW TIER 2: AUTONOMOUS TIER 3: DEBUG/DISCOVERY
334
- ---------------------- ------------------- -----------------------
335
- /fire-1-new /fire-autonomous /fire-debug
336
- /fire-1a-discuss /fire-loop /fire-discover
337
- /fire-2-plan /fire-loop-resume /fire-map-codebase
338
- /fire-3-execute /fire-loop-stop /fire-0-orient
339
- /fire-4-verify /fire-research
340
- /fire-5-handoff /fire-brainstorm
341
- /fire-6-resume
342
-
343
- TIER 4: VERIFICATION TIER 5: SKILLS MGMT TIER 6: ANALYTICS/PM
344
- ---------------------- ------------------- --------------------
345
- /fire-7-review /fire-search /fire-dashboard
346
- /fire-verify-uat /fire-add-new-skill /fire-analytics
347
- /fire-test /fire-skills-sync /fire-todos
348
- /fire-security-scan /fire-skills-history /fire-reflect
349
- /fire-vuln-scan /fire-skills-rollback /fire-assumptions
350
- /fire-double-check /fire-skills-diff /fire-transition
351
-
352
- TIER 7: MILESTONE/ADVANCED
353
- --------------------------
354
- /fire-new-milestone
355
- /fire-complete-milestone
356
- /fire-execute-plan
357
- /fire-update
358
-
359
-
360
- ===============================================================================
361
- 10. THE BIG PICTURE -- Everything connected
362
- ===============================================================================
363
-
364
- +------------------------------------------------------+
365
- | YOU (the developer) |
366
- | Ideas, decisions, approvals |
367
- +----------------------+-------------------------------+
368
- |
369
- +-----------v-----------+
370
- | 39 SLASH COMMANDS |
371
- | (Orchestrators) |
372
- +-----------+-----------+
373
- | spawn
374
- +-----------------+------------------+
375
- | | |
376
- +---------v--------+ +-----v-------+ +---------v-------+
377
- | RESEARCHERS | | BUILDERS | | VALIDATORS |
378
- | | | | | |
379
- | fire-researcher | | fire- | | fire-verifier |
380
- | (phase/project | | executor | | fire-reviewer |
381
- | research) | | fire- | | |
382
- | | | planner | | |
383
- +--------+---------+ +------+------+ +--------+--------+
384
- | | |
385
- | +-------------v--------------+ |
386
- +--->| .planning/ STATE |<--+
387
- | (file-based memory) |
388
- +-------------+--------------+
389
- |
390
- +-------------v--------------+
391
- | 190+ SKILLS LIBRARY |
392
- | (proven patterns) |
393
- +-------------+--------------+
394
- |
395
- +-------------v--------------+
396
- | WARRIOR HANDOFFS |
397
- | (session continuity) |
398
- +----------------------------+
399
- ```
400
-
401
- ---
402
-
403
- ## Version History
404
-
405
- | Version | Date | Headline Features |
406
- |---------|------|-------------------|
407
- | v9.1 | 2026-02-24 | Research-backed intelligence: ReflexTree debugging, MAKER reasoning sharing, MemP failure memory, ATLAS agent selection, CriticGPT review profiles |
408
- | v1.0 | 2026-01 | Initial 6-command workflow (new, plan, execute, verify, handoff, resume) |
409
- | v2.0 | 2026-01 | Skills library integration, breath-based parallel execution |
410
- | v3.0 | 2026-02 | Circuit breaker, error classification, Sabbath Rest, context engineering |
411
- | v3.3 | 2026-02 | Decision-time guidance, .powerignore, recitation pattern |
412
- | v4.0 | 2026-02 | 75 skills, cleansing cycle, evolutionary synthesis |
413
- | v5.0 | 2026-02 | Confidence gates, self-judge, debug replay, SDFT self-distillation, Path Verification Gate |
414
- | v6.0 | 2026-02 | Episodic auto-injection (CoALA), utility scoring (ReMe), GCC checkpoints, turn-level rewards (AgentPRM), behavioral directives |
415
- | v7.0 | 2026-02 | Difficulty-aware routing, predicate-form rules with HAC, AUQ confidence propagation, failure taxonomy (AgentDebug), dual-replay (AgentRR) |
416
- | v8.0 | 2026-02 | Parallel review gate (verifier + reviewer), combined verdict matrix, post-loop review gate, version performance tracking, failure memory collection |
417
- | v9.0 | 2026-02 | /fire-autonomous full autopilot, 39 commands, inter-agent shared state, task-level resume, graceful Qdrant degradation, semantic progress metrics |
418
-
419
- ---
420
-
421
- *Generated 2026-02-24 -- Dominion Flow v10.0*
1
+ # Dominion Flow v12.2 -- Complete System Overview
2
+
3
+ Bird's eye view of the entire Dominion Flow system.
4
+
5
+ **Three Pillars:** Honesty Gate (accept mistakes, never blame) · Live Breadcrumbs (each instance smarter than the last) · Zero-Friction Tooling (ideas in, working app out)
6
+
7
+ **v12.0 Research-Backed Enhancements:**
8
+ - Tiered Verification (fast gate before slow gate — shift-left)
9
+ - Stuck-State Classification (6 types, not just "stuck")
10
+ - Kill Conditions (Google X pattern — pre-defined trip conditions)
11
+ - Scope Manifests (AWS TBAC — bounded file/tool access per task)
12
+ - Implied Scenario Detection (composition reveals what specification omits)
13
+ - Requirements Decomposition (CMU SEI utility tree — Level 4 before execution)
14
+ - Articulation Protocol (rubber duck step — catches 30-40% of stuck cases)
15
+ - Sensitivity Analysis (rank failures by downstream impact, not frequency)
16
+
17
+ ---
18
+
19
+ ```
20
+ +==============================================================================+
21
+ | DOMINION FLOW v12.2 -- COMPLETE SYSTEM MAP |
22
+ +==============================================================================+
23
+
24
+
25
+ ===============================================================================
26
+ 1. THE LIFECYCLE -- How a project flows from idea to done (v12.0)
27
+ ===============================================================================
28
+
29
+ +-------------+ +--------------+ +--------------+ +--------------+
30
+ | /fire-1a-new |--->| /fire-2-plan |--->| /fire-3-exec |--->|/fire-4-verify|
31
+ | New Project| | Plan Phase | | Execute Phase| | Verify Phase |
32
+ | + Vision | | [H] Honesty | | [H] Honesty | | [H] Honesty |
33
+ +------+------+ +------+-------+ +------+-------+ +------+-------+
34
+ | ^ | |
35
+ Visual Input? | Breath-based Goal-backward
36
+ Mode Gate | Execution Verification
37
+ Vision Architect | + Commits + 70-point
38
+ Zero-Friction CLI | + Playwright + Playwright
39
+ Roadmap | | |
40
+ | | v v
41
+ v | RECORD.md VERIFICATION.md
42
+ PROJECT.md | | |
43
+ VISION.md (LOCKED) | | +----+----+
44
+ CONSCIENCE.md | | | PASS? |
45
+ TOOLING-LOG.md | | +----+----+
46
+ breadcrumbs/ | | yes/ \no
47
+ | | | / \
48
+ +------+------------------+--------------------+----------+ +----------------+
49
+ | NEXT PHASE / MILESTONE | | RECOVERY LOOP |
50
+ | (loop back to /fire-2-plan) | | (v11.2) |
51
+ +--------------------------------------------------------+ | |
52
+ | 1. Researcher |
53
+ LIVE BREADCRUMBS (v11.2) -- updated by ALL agents: | searches: |
54
+ +------------------------------------------------------+ | Skills DB |
55
+ | breadcrumbs/LESSONS.md -- what worked | | Context7 |
56
+ | breadcrumbs/FAILURES.md -- what didn't + why | | Web (last) |
57
+ | breadcrumbs/PATTERNS.md -- recurring patterns | | |
58
+ | breadcrumbs/DEPENDENCIES.md -- env, packages, gotchas | | 2. Returns 2-3 |
59
+ +------------------------------------------------------+ | alternatives|
60
+ | ranked by |
61
+ DEAD ENDS (v11.3 — merged into FAILURES.md): | confidence |
62
+ +------------------------------------------------------+ | |
63
+ | breadcrumbs/FAILURES.md [DEAD-END] tagged entries | | 3. Planner |
64
+ | | | picks best |
65
+ | Agent hits wall (3+ attempts) --> SHELVE & move on | | alternative |
66
+ | Fresh Claude on /fire-6-resume --> reads shelf, | | NEW blueprint|
67
+ | attempts highest-priority problem with clean context | +-------+--------+
68
+ +------------------------------------------------------+ |
69
+ v
70
+ back to /fire-2-plan
71
+ (with new approach)
72
+
73
+ AUTONOMOUS PATH (v9.0):
74
+ +------------------------------------------------------------------+
75
+ | /fire-autonomous |
76
+ | |
77
+ | After /fire-1a-new completes, runs the ENTIRE pipeline: |
78
+ | 2-plan --> 3-execute --> 4-verify (per phase, all phases) |
79
+ | Auto-routes merge gate and review gate verdicts. |
80
+ | Dead ends shelved mid-run, solved on next session. |
81
+ +------------------------------------------------------------------+
82
+
83
+ PHOENIX REBUILD (v12.2):
84
+ +------------------------------------------------------------------+
85
+ | /fire-phoenix --source <path> |
86
+ | |
87
+ | Takes a messy "vibe coded" project and rebuilds it clean: |
88
+ | AUTOPSY --> INTENT --> CLARIFY --> VISION --> REBUILD --> COMPARE|
89
+ | Source is READ-ONLY. Rebuild goes to new target folder. |
90
+ | Extracts INTENT (what code was trying to do), asks user about |
91
+ | ambiguities, then rebuilds using full Dominion Flow pipeline. |
92
+ | Phoenix Score: PX-1 to PX-5 (feature parity, edge cases, etc.) |
93
+ +------------------------------------------------------------------+
94
+
95
+ SESSION BOUNDARIES:
96
+ +--------------+ +--------------+
97
+ |/fire-5-hand | === session break ===> |/fire-6-resum |
98
+ | off | POWER-HANDOFF-*.md | e |
99
+ | Save context | (WARRIOR 7-step) | Load context |
100
+ | + breadcrumbs| | + breadcrumbs|
101
+ +--------------+ +--------------+
102
+
103
+ [H] = Honesty Gate -- mandatory 3-question checkpoint at every agent
104
+
105
+
106
+ ===============================================================================
107
+ 2. ALL AGENTS -- Who does what
108
+ ===============================================================================
109
+
110
+ AGENT FILE DESCRIPTION SPAWNED BY
111
+ ---------- ----------- ----------
112
+ fire-executor.md Executes plans with honesty /fire-3-execute
113
+ protocols, atomic commits, /fire-execute-plan
114
+ creates RECORD.md handoffs /fire-autonomous
115
+
116
+ fire-planner.md Creates phase plans with skills /fire-2-plan
117
+ library integration and /fire-autonomous
118
+ WARRIOR validation
119
+
120
+ fire-researcher.md Researches phase context using /fire-research
121
+ skills library, pattern matching, /fire-1a-new
122
+ and external search. In RECOVERY /fire-2-plan
123
+ MODE (v11.2): 3-tier cascade /fire-planner (on failure)
124
+ (Skills→Context7→Web) returns /fire-4-verify (gap research)
125
+ 2-3 ranked alternatives.
126
+
127
+ fire-verifier.md Must-haves verification + /fire-4-verify
128
+ WARRIOR 70-point validation /fire-3-execute
129
+
130
+ fire-reviewer.md Independent code review -- /fire-7-review
131
+ architecture, patterns, perf, /fire-3-execute
132
+ maintainability, security (parallel with verifier)
133
+
134
+ fire-vision-architect.md Generates 2-3 competing /fire-1a-new
135
+ architecture vision branches. /fire-new-milestone
136
+ Anti-Frankenstein gate prevents
137
+ incompatible stack combos.
138
+
139
+ fire-phoenix-analyst.md Reverse-engineers developer intent /fire-phoenix
140
+ from messy codebases. Extracts what
141
+ code was TRYING to do. Produces
142
+ INTENT.md + INTENT-GRAPH.md.
143
+
144
+
145
+ AGENT CAPABILITIES:
146
+ +-------------------------+----------+-------+------+------+------+---------+----------+
147
+ | Agent | Read | Write | Edit | Bash | Grep | Web | Context7 |
148
+ +-------------------------+----------+-------+------+------+------+---------+----------+
149
+ | fire-executor | Y | Y | Y | Y | Y | | |
150
+ | fire-planner | Y | Y | | Y | Y | Fetch | Y |
151
+ | fire-researcher | Y | Y | | Y | Y | Both | Y |
152
+ | fire-verifier | Y | | | Y | Y | | |
153
+ | fire-reviewer | Y | | | Y | Y | | |
154
+ | fire-vision-architect | Y | Y | | | Y | | | ← Forward + Backward modes
155
+ | fire-phoenix-analyst | Y | Y | | Y | Y | | | ← Intent extraction
156
+ +-------------------------+----------+-------+------+------+------+---------+----------+
157
+
158
+
159
+ ===============================================================================
160
+ 3. BREATH EXECUTION -- How /fire-3-execute parallelizes work
161
+ ===============================================================================
162
+
163
+ BLUEPRINT.md files have frontmatter: breath: 1, breath: 2, breath: 3 ...
164
+
165
+ +---------------------------------------------------------+
166
+ | BREATH 1 (parallel) |
167
+ | |
168
+ | +-------------+ +-------------+ +-------------+ |
169
+ | | Plan 01-01 | | Plan 01-02 | | Plan 01-03 | |
170
+ | | Foundation | | Schema | | Config | |
171
+ | | | | | | | |
172
+ | | executor <--| | executor <--| | executor <--| |
173
+ | +------+------+ +------+------+ +------+------+ |
174
+ | | | | |
175
+ | v v v |
176
+ | commit commit commit |
177
+ +--------------------------+------------------------------+
178
+ | all complete
179
+ v
180
+ +---------------------------------------------------------+
181
+ | BREATH 2 (depends on breath 1) |
182
+ | |
183
+ | +-------------+ +-------------+ |
184
+ | | Plan 01-04 | | Plan 01-05 | |
185
+ | | API Routes | | Auth Flow | |
186
+ | | | | | |
187
+ | | executor <--| | executor <--| |
188
+ | +------+------+ +------+------+ |
189
+ | | | |
190
+ | v v |
191
+ | commit commit |
192
+ +--------------------------+------------------------------+
193
+ | all complete
194
+ v
195
+ +---------------------------------------------------------+
196
+ | BREATH 3 |
197
+ | +-------------+ |
198
+ | | Plan 01-06 | Then: fire-verifier runs |
199
+ | | UI + Tests | 70-point validation on everything |
200
+ | +-------------+ + fire-reviewer in parallel (v8.0) |
201
+ +---------------------------------------------------------+
202
+
203
+ MODE SELECTION (auto per breath):
204
+ +------------------------------------------------------+
205
+ | 1 plan in breath --> Sequential (single executor) |
206
+ | 2+ plans, no file overlap --> Parallel (Task tool) |
207
+ | 2+ plans, file overlap --> Sequential (safe) |
208
+ | 3+ plans, no overlap --> Team/Swarm mode |
209
+ +------------------------------------------------------+
210
+
211
+
212
+ ===============================================================================
213
+ 4. NEW PROJECT FLOW -- 3-command chain
214
+ ===============================================================================
215
+
216
+ /fire-1a-new --> /fire-1b-research --> /fire-1c-setup
217
+ (scaffold) (research+vision) (tooling+finalize)
218
+
219
+ Each command is <250 lines so agents follow every step.
220
+ Each command gates on the previous (checks files exist).
221
+
222
+ ┌─────────────────────────────────────────────────────┐
223
+ │ /fire-1a-new (Steps 1-3) │
224
+ │ │
225
+ │ User: "/fire-1a-new My LMS Platform" │
226
+ │ | │
227
+ │ v │
228
+ │ +----------------------+ │
229
+ │ | Adaptive Questioning | "What's the core value?" │
230
+ │ | (5-15 questions) | "Who are the users?" │
231
+ │ +----------+-----------+ │
232
+ │ | │
233
+ │ v │
234
+ │ +-----------------------------------------+ │
235
+ │ | MODE GATE: "Have you already started | │
236
+ │ | building, or starting from scratch?" | │
237
+ │ +--------+------------------+-------------+ │
238
+ │ | | │
239
+ │ FORWARD MODE BACKWARD MODE │
240
+ │ (has tech) (vibe coders) │
241
+ │ | | │
242
+ │ v v │
243
+ │ +----------------------+ │
244
+ │ | Write PROJECT.md | Core value, constraints │
245
+ │ | Write REQUIREMENTS | REQ-IDs │
246
+ │ | Create .planning/ | breadcrumbs/ (on-demand) │
247
+ │ +----------+-----------+ │
248
+ │ | │
249
+ │ OUTPUT: 8 files (.planning/ scaffold) │
250
+ │ NEXT: "Run /fire-1b-research" │
251
+ └─────────────────────────────────────────────────────┘
252
+ |
253
+ v
254
+ ┌─────────────────────────────────────────────────────┐
255
+ │ /fire-1b-research (Steps 3b-3d) │
256
+ │ │
257
+ │ +-----------------------------------------------+ │
258
+ │ | 4 PARALLEL RESEARCHERS (+ GitHub search) | │
259
+ │ | STACK | FEATURES | ARCHITECT | PITFALLS | │
260
+ │ | --> SYNTHESIS.md (merged + GitHub refs) | │
261
+ │ +----------------------+------------------------+ │
262
+ │ v │
263
+ │ +--------------------------------------------------│
264
+ │ | fire-vision-architect │
265
+ │ | Anti-Frankenstein (forward) / Capability │
266
+ │ | Extraction (backward) --> 2-3 branches │
267
+ │ | User picks one --> VISION.md (LOCKED) │
268
+ │ | Rejected --> ALTERNATIVES.md │
269
+ │ +----------------------+---------------------------│
270
+ │ v │
271
+ │ +--------------------------------------------------│
272
+ │ | fire-roadmapper │
273
+ │ | Reads LOCKED VISION.md (no stack changes) │
274
+ │ | Requirements --> phases --> ROADMAP.md │
275
+ │ +--------------------------------------------------│
276
+ │ │
277
+ │ OUTPUT: SYNTHESIS.md, VISION.md, ALTERNATIVES.md, │
278
+ │ ROADMAP.md │
279
+ │ NEXT: "Run /fire-1c-setup" │
280
+ └─────────────────────────────────────────────────────┘
281
+ |
282
+ v
283
+ ┌─────────────────────────────────────────────────────┐
284
+ │ /fire-1c-setup (Steps 4-6 + FINAL) │
285
+ │ │
286
+ │ WARRIOR handoff --> ~/.claude/warrior-handoffs/ │
287
+ │ Zero-friction tooling --> install CLIs from VISION │
288
+ │ SKILLS-INDEX.md --> empty tracking │
289
+ │ Update CONSCIENCE.md --> "Ready to plan" │
290
+ │ │
291
+ │ ┌─── MANDATORY FILE GATE ─────────────────────┐ │
292
+ │ │ Verify ALL 16 files exist │ │
293
+ │ │ If ANY missing --> abort, tell user which │ │
294
+ │ │ command to re-run │ │
295
+ │ └─────────────────────────────────────────────┘ │
296
+ │ │
297
+ │ OUTPUT: TOOLING-LOG.md, SKILLS-INDEX.md, handoff │
298
+ │ NEXT: "Run /fire-2-plan 1" │
299
+ └─────────────────────────────────────────────────────┘
300
+
301
+
302
+ ===============================================================================
303
+ 5. VERIFICATION SYSTEM -- Triple-layer validation (v12.0)
304
+ ===============================================================================
305
+
306
+ +---------------------------------------------------------+
307
+ | TIER 1: FAST GATE (v12.0 — shift-left, seconds) |
308
+ | |
309
+ | Build compiles? Types check? Lint passes? |
310
+ | Files exist? Imports resolve? |
311
+ | |
312
+ | IF ANY FAIL --> STOP. Don't run Tier 2 or 3. |
313
+ | Catches 60%+ of failures in <30 seconds. |
314
+ +---------------------------------------------------------+
315
+ +
316
+ +---------------------------------------------------------+
317
+ | TIER 2: MUST-HAVES (Goal-Backward) |
318
+ | |
319
+ | "What must be TRUE for this phase's goal?" |
320
+ | |
321
+ | Truths: Observable behaviors users can verify |
322
+ | Artifacts: Files that must exist with specific exports|
323
+ | Key Links: Components properly wired together |
324
+ | |
325
+ | Y User can log in with email/password |
326
+ | Y JWT token persists across browser sessions |
327
+ | X Password reset email sends (FAIL -> gap plan) |
328
+ +---------------------------------------------------------+
329
+ +
330
+ +---------------------------------------------------------+
331
+ | TIER 3: WARRIOR 70-POINT CHECKLIST (scope-adaptive) |
332
+ | |
333
+ | Code Quality ........... /10 Performance ...... /10 |
334
+ | Testing ................ /10 Documentation .... /10 |
335
+ | Security ............... /10 Infrastructure ... /10 |
336
+ | E2E (Playwright) ...... /10 |
337
+ | ---- |
338
+ | /70 (max, adjusted per scope) |
339
+ | |
340
+ | Scoring: percentage of ACTIVE sections only (v11.3) |
341
+ | 90%+ = APPROVED 70-79% = CONDITIONAL |
342
+ | 80-89% = APPROVED* <60% = REJECTED |
343
+ +---------------------------------------------------------+
344
+ +
345
+ +---------------------------------------------------------+
346
+ | POST-VERIFICATION (v12.0) |
347
+ | |
348
+ | Implied Scenario Detection: |
349
+ | Positive (correct but unplanned) --> add to spec |
350
+ | Negative (incorrect/unintended) --> CRITICAL GAP |
351
+ | |
352
+ | Failure Sensitivity Analysis: |
353
+ | Rank gaps by downstream impact (LOCAL < CASCADING) |
354
+ | Fix CASCADING failures first |
355
+ +---------------------------------------------------------+
356
+
357
+
358
+ ===============================================================================
359
+ 6. FILE-BASED STATE MACHINE -- .planning/ directory
360
+ ===============================================================================
361
+
362
+ your-project/
363
+ +-- .planning/
364
+ +-- CONSCIENCE.md <-- Living project memory (updated constantly)
365
+ +-- VISION.md <-- Phase overview + success criteria (LOCKED)
366
+ +-- REQUIREMENTS.md <-- REQ-IDs with traceability
367
+ +-- PROJECT.md <-- Core value, users, constraints
368
+ +-- TOOLING-LOG.md <-- CLI tools installed + versions (v11.2)
369
+ |
370
+ +-- breadcrumbs/ <-- Live memory across agents (on-demand, v11.3)
371
+ | +-- LESSONS.md <-- What worked (created on first write)
372
+ | +-- FAILURES.md <-- What didn't + why + [DEAD-END] entries (created on first write)
373
+ | +-- PATTERNS.md <-- Recurring patterns (created on first write)
374
+ | +-- DEPENDENCIES.md <-- Env, packages, gotchas (created on first write)
375
+ |
376
+ +-- research/ <-- Created by /fire-1a-new
377
+ | +-- STACK.md
378
+ | +-- FEATURES.md
379
+ | +-- ARCHITECTURE.md
380
+ | +-- PITFALLS.md
381
+ | +-- RECORD.md
382
+ | +-- ALTERNATIVES.md <-- Rejected vision branches (v11.2)
383
+ |
384
+ +-- codebase/ <-- Created by /fire-map-codebase
385
+ | +-- STACK.md
386
+ | +-- ARCHITECTURE.md
387
+ | +-- STRUCTURE.md
388
+ | +-- CONVENTIONS.md
389
+ | +-- TESTING.md
390
+ | +-- INTEGRATIONS.md
391
+ | +-- CONCERNS.md
392
+ |
393
+ +-- phases/
394
+ | +-- 01-foundation/
395
+ | | +-- 01-01-BLUEPRINT.md <-- Breath 1
396
+ | | +-- 01-02-BLUEPRINT.md <-- Breath 1
397
+ | | +-- 01-03-BLUEPRINT.md <-- Breath 2
398
+ | | +-- 01-01-RECORD.md <-- After execution
399
+ | | +-- 01-VERIFICATION.md <-- After /fire-4-verify
400
+ | | +-- 01-REVIEW.md <-- After /fire-7-review (v8.0)
401
+ | | +-- 01-MEMORY.md <-- From /fire-1d-discuss
402
+ | |
403
+ | +-- 02-authentication/
404
+ | | +-- ...
405
+ | +-- 03-content/
406
+ | +-- ...
407
+ |
408
+ +-- debug/ <-- Created by /fire-debug
409
+ | +-- login-fails.md
410
+ | +-- resolved/
411
+ | +-- api-timeout.md
412
+ |
413
+ +-- loops/ <-- Created by /fire-loop
414
+ | +-- fire-loop-{ID}.md
415
+ | +-- sabbath-{ID}-iter{N}.md
416
+ |
417
+ +-- .shared-state.json <-- SWARM inter-agent coordination (v9.0)
418
+ +-- POWER-HANDOFF-2026-02-14.md <-- Session continuity
419
+
420
+
421
+ ===============================================================================
422
+ 7. HOOKS & SESSION MANAGEMENT
423
+ ===============================================================================
424
+
425
+ +---------------------------------------------------------+
426
+ | SESSION START |
427
+ | +-- fire-check-update.js (check for plugin updates) |
428
+ | +-- compact-reinject.js (restore context on /compact|
429
+ | re-injects WARRIOR state) |
430
+ +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~+
431
+ | STOP |
432
+ | +-- stop-verify.js (warn if tasks incomplete) |
433
+ +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~+
434
+ | STATUSLINE (always visible) |
435
+ | +-- statusline.js opus | current task | dir |
436
+ | ^ /fire-update | 45% ctx |
437
+ +---------------------------------------------------------+
438
+
439
+
440
+ ===============================================================================
441
+ 8. SKILLS LIBRARY -- 478+ reusable patterns
442
+ ===============================================================================
443
+
444
+ +------------------+ +------------------+ +------------------+
445
+ | advanced-features| | api-patterns | | automation |
446
+ | (11 skills) | | (12 skills) | | (7 skills) |
447
+ +------------------+ +------------------+ +------------------+
448
+ | database-solutions| | deploy-security | | doc-processing |
449
+ | (12 skills) | | (17 skills) | | (5 skills) |
450
+ +------------------+ +------------------+ +------------------+
451
+ | ecommerce | | form-solutions | | integrations |
452
+ | (15 skills) | | (8 skills) | | (20+ skills) |
453
+ | stripe,paypal,GTA| | | | stripe,zoom,yt |
454
+ +------------------+ +------------------+ +------------------+
455
+ | lms-patterns | | methodology | | patterns-standard|
456
+ | (30+ skills) | | (16 skills) | | (15 skills) |
457
+ +------------------+ +------------------+ +------------------+
458
+
459
+ v12.0 RESEARCH-BACKED METHODOLOGY SKILLS (6 new):
460
+ +-------------------------+ +-------------------------+ +-------------------------+
461
+ | RELIABILITY_PREDICTION | | QUALITY_GATES_AND_ | | CIRCUIT_BREAKER_ |
462
+ | Implied scenarios, | | VERIFICATION | | INTELLIGENCE |
463
+ | sensitivity analysis, | | Tiered gates, risk- | | 6-type stuck class, |
464
+ | probability completeness| | based testing, error | | kill conditions, |
465
+ | | | budgets, DoR/DoD | | articulation protocol |
466
+ +-------------------------+ +-------------------------+ +-------------------------+
467
+ | CONTEXT_ROTATION | | AUTONOMOUS_ | | REQUIREMENTS_ |
468
+ | Fresh-eyes science, | | ORCHESTRATION | | DECOMPOSITION |
469
+ | fixation prevention, | | Planner/Worker/Judge, | | Utility tree (L1→L4), |
470
+ | navigator pattern | | scope manifests, DORA | | ATAM tradeoffs, WDM |
471
+ +-------------------------+ +-------------------------+ +-------------------------+
472
+
473
+ /fire-search "stripe webhook" --> finds matching skills
474
+ /fire-add-new-skill --> add from current session
475
+ /fire-skills-history --> git log of skill changes
476
+ /fire-skills-rollback --> revert to previous version
477
+
478
+
479
+ ===============================================================================
480
+ 9. ALL 46 COMMANDS -- Organized by tier
481
+ ===============================================================================
482
+
483
+ TIER 1: CORE WORKFLOW TIER 2: AUTONOMOUS TIER 3: DEBUG/DISCOVERY
484
+ ---------------------- ------------------- -----------------------
485
+ /fire-1a-new /fire-autonomous /fire-debug
486
+ /fire-1b-research /fire-loop /fire-discover
487
+ /fire-1c-setup /fire-loop-resume /fire-map-codebase
488
+ /fire-1d-discuss /fire-loop-stop /fire-0-orient
489
+ /fire-2-plan /fire-phoenix /fire-research
490
+ /fire-3-execute /fire-brainstorm
491
+ /fire-4-verify
492
+ /fire-5-handoff
493
+ /fire-6-resume
494
+
495
+ TIER 4: VERIFICATION TIER 5: SKILLS MGMT TIER 6: ANALYTICS/PM
496
+ ---------------------- ------------------- --------------------
497
+ /fire-7-review /fire-search /fire-dashboard
498
+ /fire-verify-uat /fire-add-new-skill /fire-analytics
499
+ /fire-test /fire-skills-sync /fire-todos
500
+ /fire-security-scan /fire-skills-history /fire-reflect
501
+ /fire-vuln-scan /fire-skills-rollback /fire-assumptions
502
+ /fire-double-check /fire-skills-diff /fire-transition
503
+
504
+ TIER 7: MILESTONE/ADVANCED
505
+ --------------------------
506
+ /fire-new-milestone
507
+ /fire-complete-milestone
508
+ /fire-execute-plan
509
+ /fire-update
510
+
511
+
512
+ ===============================================================================
513
+ 10. THE BIG PICTURE -- Everything connected
514
+ ===============================================================================
515
+
516
+ +------------------------------------------------------+
517
+ | YOU (the developer) |
518
+ | Ideas, screenshots, wireframes, decisions, approvals |
519
+ +----------------------+-------------------------------+
520
+ |
521
+ +-----------v-----------+
522
+ | 46 SLASH COMMANDS |
523
+ | (Orchestrators) |
524
+ +-----------+-----------+
525
+ | spawn
526
+ +----------------------+----------------------+
527
+ | | |
528
+ +------v---------+ +-------v-------+ +-----------v------+
529
+ | RESEARCHERS | | BUILDERS | | VALIDATORS |
530
+ | | | | | |
531
+ | fire-researcher| | fire-executor | | fire-verifier |
532
+ | fire-vision- | | fire-planner | | fire-reviewer |
533
+ | architect | | | | |
534
+ +------+---------+ +-------+-------+ +--------+---------+
535
+ | | |
536
+ | [H] HONESTY GATE at every agent [H] |
537
+ | | |
538
+ | +---------------v--------------+ |
539
+ +---->| .planning/ STATE |<-----+
540
+ | + breadcrumbs/ (on-demand) |
541
+ | + TOOLING-LOG.md |
542
+ +---------------+--------------+
543
+ |
544
+ +---------------v--------------+
545
+ | 478+ SKILLS LIBRARY |
546
+ | (proven patterns) |
547
+ +---------------+--------------+
548
+ |
549
+ +---------------v--------------+
550
+ | WARRIOR HANDOFFS |
551
+ | + breadcrumbs preserved |
552
+ | + dead ends documented |
553
+ | (session continuity) |
554
+ +------------------------------+
555
+ ```
556
+
557
+ ---
558
+
559
+ ## Version History
560
+
561
+ | Version | Date | Headline Features |
562
+ |---------|------|-------------------|
563
+ | v12.2 | 2026-03-06 | Phoenix Rebuild: `/fire-phoenix` autonomous rebuild from messy-to-clean. fire-phoenix-analyst agent (intent extraction), PHOENIX_REBUILD_METHODOLOGY skill (anti-pattern map, intent graph, edge case protocol), GOF_DESIGN_PATTERNS_FOR_AI_AGENTS skill, phoenix-comparison template, PX-1 to PX-5 verification checks |
564
+ | v12.1 | 2026-03-06 | v12.0 audit fixes: Tier naming alignment, DORA metrics in autonomous, Requirements Decomposition in discuss, researcher skill awareness, circuit breaker weight alignment |
565
+ | v12.0 | 2026-03-06 | Research-backed upgrade: 6 new methodology skills (Reliability Prediction, Quality Gates, Circuit Breaker Intelligence, Context Rotation, Autonomous Orchestration, Requirements Decomposition), tiered verification, stuck-state classification, kill conditions, scope manifests, implied scenario detection |
566
+ | v11.2 | 2026-03-06 | Branching Vision System + Honesty Gate + Zero-Friction CLI + Dead Ends Shelf: fire-vision-architect (Forward + Backward modes), Anti-Frankenstein gate, Visual Input fast-track (screenshots/wireframes/sketches), BACKWARD_PLANNING_INTERVIEW (10 beginner questions), ZERO_FRICTION_CLI_SETUP (auto-install all tools from VISION.md), DevTools guide for beginners, Honesty Gate universal enforcement (slim 10-line gates referencing canonical protocol), Live Breadcrumb Protocol (LESSONS/FAILURES/PATTERNS/DEPENDENCIES), Dead Ends Shelf (DEAD-ENDS.md — shelve unsolved problems, fresh instance retries on resume), Recovery Research Loop (Skills→Context7→Web), Verifier isolation (fresh instance), Playwright MCP non-negotiable |
567
+ | v9.1 | 2026-02-24 | Research-backed intelligence: ReflexTree debugging, MAKER reasoning sharing, MemP failure memory, ATLAS agent selection, CriticGPT review profiles |
568
+ | v1.0 | 2026-01 | Initial 6-command workflow (new, plan, execute, verify, handoff, resume) |
569
+ | v2.0 | 2026-01 | Skills library integration, breath-based parallel execution |
570
+ | v3.0 | 2026-02 | Circuit breaker, error classification, Sabbath Rest, context engineering |
571
+ | v3.3 | 2026-02 | Decision-time guidance, .powerignore, recitation pattern |
572
+ | v4.0 | 2026-02 | 75 skills, cleansing cycle, evolutionary synthesis |
573
+ | v5.0 | 2026-02 | Confidence gates, self-judge, debug replay, SDFT self-distillation, Path Verification Gate |
574
+ | v6.0 | 2026-02 | Episodic auto-injection (CoALA), utility scoring (ReMe), GCC checkpoints, turn-level rewards (AgentPRM), behavioral directives |
575
+ | v7.0 | 2026-02 | Difficulty-aware routing, predicate-form rules with HAC, AUQ confidence propagation, failure taxonomy (AgentDebug), dual-replay (AgentRR) |
576
+ | v8.0 | 2026-02 | Parallel review gate (verifier + reviewer), combined verdict matrix, post-loop review gate, version performance tracking, failure memory collection |
577
+ | v9.0 | 2026-02 | /fire-autonomous full autopilot, 39 commands, inter-agent shared state, task-level resume, graceful Qdrant degradation, semantic progress metrics |
578
+
579
+ ---
580
+
581
+ *Generated 2026-03-06 -- Dominion Flow v12.2*