@anhth2/spec-driven-dev-plugin 0.8.0 → 0.9.1

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 (93) hide show
  1. package/ARCHITECTURE.md +6 -2
  2. package/commands/debug.md +152 -0
  3. package/commands/debug.tmpl +16 -0
  4. package/commands/define-product.md +57 -0
  5. package/commands/fix-bug.md +153 -0
  6. package/commands/fix-bug.tmpl +17 -0
  7. package/commands/generate-bdd.md +277 -13
  8. package/commands/generate-bdd.tmpl +220 -13
  9. package/commands/generate-code.md +154 -2
  10. package/commands/generate-code.tmpl +97 -2
  11. package/commands/generate-design-spec.md +57 -0
  12. package/commands/generate-prd.md +114 -20
  13. package/commands/generate-prd.tmpl +57 -20
  14. package/commands/generate-spec-manifest.md +57 -0
  15. package/commands/generate-tech-docs.md +79 -1
  16. package/commands/generate-tech-docs.tmpl +22 -1
  17. package/commands/generate-tests.md +57 -0
  18. package/commands/learn.md +554 -0
  19. package/commands/learn.tmpl +63 -0
  20. package/commands/propose-scenario.md +521 -0
  21. package/commands/propose-scenario.tmpl +109 -0
  22. package/commands/refine-prd.md +66 -1
  23. package/commands/refine-prd.tmpl +9 -1
  24. package/commands/report-bug.md +543 -0
  25. package/commands/report-bug.tmpl +131 -0
  26. package/commands/review-code.md +153 -0
  27. package/commands/review-code.tmpl +17 -0
  28. package/commands/review-context.md +65 -0
  29. package/commands/review-context.tmpl +8 -0
  30. package/commands/review-tech-docs.md +146 -4
  31. package/commands/review-tech-docs.tmpl +89 -4
  32. package/commands/run-tests.md +82 -0
  33. package/commands/run-tests.tmpl +25 -0
  34. package/commands/setup-ai-first.md +15 -5
  35. package/commands/setup-ai-first.tmpl +10 -5
  36. package/commands/smoke-test.md +57 -0
  37. package/commands/sync.md +405 -0
  38. package/commands/sync.tmpl +345 -0
  39. package/commands/update-framework.md +211 -0
  40. package/commands/update-framework.tmpl +151 -0
  41. package/commands/validate-traces.md +115 -2
  42. package/commands/validate-traces.tmpl +58 -2
  43. package/core/FRAMEWORK_VERSION +1 -1
  44. package/core/commands/debug.md +152 -0
  45. package/core/commands/define-product.md +57 -0
  46. package/core/commands/fix-bug.md +153 -0
  47. package/core/commands/generate-bdd.md +277 -13
  48. package/core/commands/generate-code.md +154 -2
  49. package/core/commands/generate-design-spec.md +57 -0
  50. package/core/commands/generate-prd.md +114 -20
  51. package/core/commands/generate-spec-manifest.md +57 -0
  52. package/core/commands/generate-tech-docs.md +79 -1
  53. package/core/commands/generate-tests.md +57 -0
  54. package/core/commands/learn.md +554 -0
  55. package/core/commands/propose-scenario.md +521 -0
  56. package/core/commands/refine-prd.md +66 -1
  57. package/core/commands/report-bug.md +543 -0
  58. package/core/commands/review-code.md +153 -0
  59. package/core/commands/review-context.md +65 -0
  60. package/core/commands/review-tech-docs.md +146 -4
  61. package/core/commands/run-tests.md +82 -0
  62. package/core/commands/setup-ai-first.md +15 -5
  63. package/core/commands/smoke-test.md +57 -0
  64. package/core/commands/sync.md +405 -0
  65. package/core/commands/update-framework.md +211 -0
  66. package/core/commands/validate-traces.md +115 -2
  67. package/core/skills/code/SKILL.md +62 -0
  68. package/core/skills/debug/SKILL.md +67 -0
  69. package/core/skills/design-spec/SKILL.md +57 -0
  70. package/core/skills/discovery/SKILL.md +57 -0
  71. package/core/skills/prd/SKILL.md +10 -0
  72. package/core/skills/setup-ai-first/SKILL.md +5 -0
  73. package/core/skills/spec/SKILL.md +10 -0
  74. package/core/skills/test/SKILL.md +119 -0
  75. package/core/steps/capture-lesson.md +79 -0
  76. package/core/steps/context-loader.md +52 -0
  77. package/core/steps/report-footer.md +5 -0
  78. package/core/templates/prd.template.md +35 -20
  79. package/core/templates/project-context.yaml +11 -0
  80. package/package.json +9 -2
  81. package/skills/code/SKILL.md +62 -0
  82. package/skills/debug/SKILL.md +67 -0
  83. package/skills/design-spec/SKILL.md +57 -0
  84. package/skills/discovery/SKILL.md +57 -0
  85. package/skills/prd/SKILL.md +10 -0
  86. package/skills/setup-ai-first/SKILL.md +5 -0
  87. package/skills/spec/SKILL.md +10 -0
  88. package/skills/test/SKILL.md +119 -0
  89. package/steps/capture-lesson.md +79 -0
  90. package/steps/context-loader.md +52 -0
  91. package/steps/report-footer.md +5 -0
  92. package/templates/prd.template.md +35 -20
  93. package/templates/project-context.yaml +11 -0
@@ -205,6 +205,37 @@ If `services` section is present:
205
205
  - Override `paths.domain_knowledge_dir` → `{spec_source}/specs/domain-knowledge`
206
206
  - Override `paths.business_dictionary` → `{spec_source}/specs/domain-knowledge/business-dictionary.md`
207
207
  - Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
208
+ - Override `paths.bug_reports_dir` → `{spec_source}/feedback/bug-reports`
209
+ - Override `paths.bdd_proposals_dir` → `{spec_source}/feedback/bdd-proposals`
210
+
211
+ > **Why under `spec_source`:** tester feedback (`/report-bug`, `/propose-scenario`) must land in the **shared spec repo** so PO/Dev see it when they `/sync`. In single-service mode (no `spec_source`), these default to `feedback/bug-reports` and `feedback/bdd-proposals` at repo root — still shared, same repo.
212
+
213
+ ---
214
+
215
+ ## Step 1.6 — [SERVICE CONVENTIONS] Load service-specific conventions (umbrella mode)
216
+
217
+ *Skip this step entirely if `active_service` is `"unresolved"` or context is single-service mode.*
218
+
219
+ When `active_service` has been resolved to a real path in Step 1.5 (e.g., `user-service/`):
220
+
221
+ **1. Locate service config** — try in priority order:
222
+ - `{active_service}/.agent/project-context.yaml`
223
+ - `{active_service}/project-context.yaml`
224
+
225
+ **2. If found, override with service-specific values:**
226
+
227
+ | Variable | Source |
228
+ |----------|--------|
229
+ | `conventions.test_command` | service's `conventions.test_command` |
230
+ | `conventions.build_command` | service's `conventions.build_command` |
231
+ | `paths.trace_dir` | `{active_service}/{service paths.trace_dir}` — default: `{active_service}/.trace` |
232
+ | `paths.specs_dir` | `{active_service}/{service paths.specs_dir}` (if set in service config, else keep Step 1.5 override) |
233
+
234
+ **3. Store** `service_root = {active_service}` as the working directory anchor for all downstream commands:
235
+ - Shell commands (`/run-tests`, `/generate-tests`) run **from within** `service_root`
236
+ - File write operations (test files, trace TSVs) use paths **relative to** `service_root`
237
+
238
+ **4. If service config not found** — keep umbrella defaults, still set `service_root = {active_service}` (path anchor is always needed even without a config override).
208
239
 
209
240
  ---
210
241
 
@@ -298,6 +329,25 @@ These two variables (`active_module`, `platform_type`) are the canonical source
298
329
 
299
330
  ---
300
331
 
332
+ ## Step 6.7 — [GUARDRAILS] Load Project Lessons (conditional)
333
+
334
+ *Accumulated mistakes the AI must not repeat in this project. These are added over time via `/learn`
335
+ or accepted during `/review-code`, `/fix-bug`, `/debug`.*
336
+
337
+ Resolve the lessons file path:
338
+ - Use `paths.lessons_file` if set (may be service-overridden in umbrella mode, Step 1.6)
339
+ - Else default `specs/domain-knowledge/lessons-learned.md`
340
+ - In umbrella/service mode (when `service_root` is set), if `paths.lessons_file` is unset, default to `{service_root}/.agent/project-lessons.md`
341
+
342
+ If the file exists, read it and store ALL lessons as **ACTIVE GUARDRAILS** for the session:
343
+ - Treat each lesson's **Rule** as a hard constraint — same priority as CLAUDE.md coding standards (Step 3).
344
+ - Before generating or modifying any artifact (PRD, BDD, tech-doc, code, test), check the output against every lesson whose `category` matches the current command AND whose `scope` matches the target (domain / file).
345
+ - If a generated output would violate a lesson → correct it **before** presenting, and note which lesson (`L-NNN`) was applied.
346
+
347
+ If the file does not exist → skip silently (no lessons captured yet).
348
+
349
+ ---
350
+
301
351
  ## Step 7 — [RECAP] Working Memory Recap (anti-lost-in-middle)
302
352
 
303
353
  After loading all context, synthesize and output a compact summary block.
@@ -313,7 +363,9 @@ Layers : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Ser
313
363
  Ticket : {ticket_prefix}-
314
364
  Dict : {loaded — N canonical terms, M banned terms | missing}
315
365
  Entities : {loaded — EntityA, EntityB, EntityC | missing}
366
+ Lessons : {loaded — N guardrails | none yet}
316
367
  Service : {active_service} ({active_service_module}) | single-service
368
+ Svc Root : {service_root} — conventions + trace_dir loaded from service config | —
317
369
  Status : {FULL | PARTIAL — missing: CLAUDE.md / business-dict / core-entities | MINIMAL}
318
370
  ```
319
371
 
@@ -462,6 +514,11 @@ Suggest the logical next command based on workflow phase:
462
514
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
463
515
  | /fix-bug | Create PR and link to ticket |
464
516
  | /debug | `/fix-bug {ticket-id}` if fix needed |
517
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
518
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
519
+ | /learn | Continue working — lesson applies on next command |
520
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
521
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
465
522
 
466
523
  Format the footer as:
467
524
  ```
@@ -575,6 +632,11 @@ Suggest the logical next command based on workflow phase:
575
632
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
576
633
  | /fix-bug | Create PR and link to ticket |
577
634
  | /debug | `/fix-bug {ticket-id}` if fix needed |
635
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
636
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
637
+ | /learn | Continue working — lesson applies on next command |
638
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
639
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
578
640
 
579
641
  Format the footer as:
580
642
  ```
@@ -120,6 +120,37 @@ If `services` section is present:
120
120
  - Override `paths.domain_knowledge_dir` → `{spec_source}/specs/domain-knowledge`
121
121
  - Override `paths.business_dictionary` → `{spec_source}/specs/domain-knowledge/business-dictionary.md`
122
122
  - Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
123
+ - Override `paths.bug_reports_dir` → `{spec_source}/feedback/bug-reports`
124
+ - Override `paths.bdd_proposals_dir` → `{spec_source}/feedback/bdd-proposals`
125
+
126
+ > **Why under `spec_source`:** tester feedback (`/report-bug`, `/propose-scenario`) must land in the **shared spec repo** so PO/Dev see it when they `/sync`. In single-service mode (no `spec_source`), these default to `feedback/bug-reports` and `feedback/bdd-proposals` at repo root — still shared, same repo.
127
+
128
+ ---
129
+
130
+ ## Step 1.6 — [SERVICE CONVENTIONS] Load service-specific conventions (umbrella mode)
131
+
132
+ *Skip this step entirely if `active_service` is `"unresolved"` or context is single-service mode.*
133
+
134
+ When `active_service` has been resolved to a real path in Step 1.5 (e.g., `user-service/`):
135
+
136
+ **1. Locate service config** — try in priority order:
137
+ - `{active_service}/.agent/project-context.yaml`
138
+ - `{active_service}/project-context.yaml`
139
+
140
+ **2. If found, override with service-specific values:**
141
+
142
+ | Variable | Source |
143
+ |----------|--------|
144
+ | `conventions.test_command` | service's `conventions.test_command` |
145
+ | `conventions.build_command` | service's `conventions.build_command` |
146
+ | `paths.trace_dir` | `{active_service}/{service paths.trace_dir}` — default: `{active_service}/.trace` |
147
+ | `paths.specs_dir` | `{active_service}/{service paths.specs_dir}` (if set in service config, else keep Step 1.5 override) |
148
+
149
+ **3. Store** `service_root = {active_service}` as the working directory anchor for all downstream commands:
150
+ - Shell commands (`/run-tests`, `/generate-tests`) run **from within** `service_root`
151
+ - File write operations (test files, trace TSVs) use paths **relative to** `service_root`
152
+
153
+ **4. If service config not found** — keep umbrella defaults, still set `service_root = {active_service}` (path anchor is always needed even without a config override).
123
154
 
124
155
  ---
125
156
 
@@ -213,6 +244,25 @@ These two variables (`active_module`, `platform_type`) are the canonical source
213
244
 
214
245
  ---
215
246
 
247
+ ## Step 6.7 — [GUARDRAILS] Load Project Lessons (conditional)
248
+
249
+ *Accumulated mistakes the AI must not repeat in this project. These are added over time via `/learn`
250
+ or accepted during `/review-code`, `/fix-bug`, `/debug`.*
251
+
252
+ Resolve the lessons file path:
253
+ - Use `paths.lessons_file` if set (may be service-overridden in umbrella mode, Step 1.6)
254
+ - Else default `specs/domain-knowledge/lessons-learned.md`
255
+ - In umbrella/service mode (when `service_root` is set), if `paths.lessons_file` is unset, default to `{service_root}/.agent/project-lessons.md`
256
+
257
+ If the file exists, read it and store ALL lessons as **ACTIVE GUARDRAILS** for the session:
258
+ - Treat each lesson's **Rule** as a hard constraint — same priority as CLAUDE.md coding standards (Step 3).
259
+ - Before generating or modifying any artifact (PRD, BDD, tech-doc, code, test), check the output against every lesson whose `category` matches the current command AND whose `scope` matches the target (domain / file).
260
+ - If a generated output would violate a lesson → correct it **before** presenting, and note which lesson (`L-NNN`) was applied.
261
+
262
+ If the file does not exist → skip silently (no lessons captured yet).
263
+
264
+ ---
265
+
216
266
  ## Step 7 — [RECAP] Working Memory Recap (anti-lost-in-middle)
217
267
 
218
268
  After loading all context, synthesize and output a compact summary block.
@@ -228,7 +278,9 @@ Layers : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Ser
228
278
  Ticket : {ticket_prefix}-
229
279
  Dict : {loaded — N canonical terms, M banned terms | missing}
230
280
  Entities : {loaded — EntityA, EntityB, EntityC | missing}
281
+ Lessons : {loaded — N guardrails | none yet}
231
282
  Service : {active_service} ({active_service_module}) | single-service
283
+ Svc Root : {service_root} — conventions + trace_dir loaded from service config | —
232
284
  Status : {FULL | PARTIAL — missing: CLAUDE.md / business-dict / core-entities | MINIMAL}
233
285
  ```
234
286
 
@@ -400,6 +452,11 @@ Suggest the logical next command based on workflow phase:
400
452
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
401
453
  | /fix-bug | Create PR and link to ticket |
402
454
  | /debug | `/fix-bug {ticket-id}` if fix needed |
455
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
456
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
457
+ | /learn | Continue working — lesson applies on next command |
458
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
459
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
403
460
 
404
461
  Format the footer as:
405
462
  ```
@@ -539,6 +596,11 @@ Suggest the logical next command based on workflow phase:
539
596
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
540
597
  | /fix-bug | Create PR and link to ticket |
541
598
  | /debug | `/fix-bug {ticket-id}` if fix needed |
599
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
600
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
601
+ | /learn | Continue working — lesson applies on next command |
602
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
603
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
542
604
 
543
605
  Format the footer as:
544
606
  ```
@@ -635,6 +697,11 @@ Suggest the logical next command based on workflow phase:
635
697
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
636
698
  | /fix-bug | Create PR and link to ticket |
637
699
  | /debug | `/fix-bug {ticket-id}` if fix needed |
700
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
701
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
702
+ | /learn | Continue working — lesson applies on next command |
703
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
704
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
638
705
 
639
706
  Format the footer as:
640
707
  ```
@@ -194,6 +194,37 @@ If `services` section is present:
194
194
  - Override `paths.domain_knowledge_dir` → `{spec_source}/specs/domain-knowledge`
195
195
  - Override `paths.business_dictionary` → `{spec_source}/specs/domain-knowledge/business-dictionary.md`
196
196
  - Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
197
+ - Override `paths.bug_reports_dir` → `{spec_source}/feedback/bug-reports`
198
+ - Override `paths.bdd_proposals_dir` → `{spec_source}/feedback/bdd-proposals`
199
+
200
+ > **Why under `spec_source`:** tester feedback (`/report-bug`, `/propose-scenario`) must land in the **shared spec repo** so PO/Dev see it when they `/sync`. In single-service mode (no `spec_source`), these default to `feedback/bug-reports` and `feedback/bdd-proposals` at repo root — still shared, same repo.
201
+
202
+ ---
203
+
204
+ ## Step 1.6 — [SERVICE CONVENTIONS] Load service-specific conventions (umbrella mode)
205
+
206
+ *Skip this step entirely if `active_service` is `"unresolved"` or context is single-service mode.*
207
+
208
+ When `active_service` has been resolved to a real path in Step 1.5 (e.g., `user-service/`):
209
+
210
+ **1. Locate service config** — try in priority order:
211
+ - `{active_service}/.agent/project-context.yaml`
212
+ - `{active_service}/project-context.yaml`
213
+
214
+ **2. If found, override with service-specific values:**
215
+
216
+ | Variable | Source |
217
+ |----------|--------|
218
+ | `conventions.test_command` | service's `conventions.test_command` |
219
+ | `conventions.build_command` | service's `conventions.build_command` |
220
+ | `paths.trace_dir` | `{active_service}/{service paths.trace_dir}` — default: `{active_service}/.trace` |
221
+ | `paths.specs_dir` | `{active_service}/{service paths.specs_dir}` (if set in service config, else keep Step 1.5 override) |
222
+
223
+ **3. Store** `service_root = {active_service}` as the working directory anchor for all downstream commands:
224
+ - Shell commands (`/run-tests`, `/generate-tests`) run **from within** `service_root`
225
+ - File write operations (test files, trace TSVs) use paths **relative to** `service_root`
226
+
227
+ **4. If service config not found** — keep umbrella defaults, still set `service_root = {active_service}` (path anchor is always needed even without a config override).
197
228
 
198
229
  ---
199
230
 
@@ -287,6 +318,25 @@ These two variables (`active_module`, `platform_type`) are the canonical source
287
318
 
288
319
  ---
289
320
 
321
+ ## Step 6.7 — [GUARDRAILS] Load Project Lessons (conditional)
322
+
323
+ *Accumulated mistakes the AI must not repeat in this project. These are added over time via `/learn`
324
+ or accepted during `/review-code`, `/fix-bug`, `/debug`.*
325
+
326
+ Resolve the lessons file path:
327
+ - Use `paths.lessons_file` if set (may be service-overridden in umbrella mode, Step 1.6)
328
+ - Else default `specs/domain-knowledge/lessons-learned.md`
329
+ - In umbrella/service mode (when `service_root` is set), if `paths.lessons_file` is unset, default to `{service_root}/.agent/project-lessons.md`
330
+
331
+ If the file exists, read it and store ALL lessons as **ACTIVE GUARDRAILS** for the session:
332
+ - Treat each lesson's **Rule** as a hard constraint — same priority as CLAUDE.md coding standards (Step 3).
333
+ - Before generating or modifying any artifact (PRD, BDD, tech-doc, code, test), check the output against every lesson whose `category` matches the current command AND whose `scope` matches the target (domain / file).
334
+ - If a generated output would violate a lesson → correct it **before** presenting, and note which lesson (`L-NNN`) was applied.
335
+
336
+ If the file does not exist → skip silently (no lessons captured yet).
337
+
338
+ ---
339
+
290
340
  ## Step 7 — [RECAP] Working Memory Recap (anti-lost-in-middle)
291
341
 
292
342
  After loading all context, synthesize and output a compact summary block.
@@ -302,7 +352,9 @@ Layers : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Ser
302
352
  Ticket : {ticket_prefix}-
303
353
  Dict : {loaded — N canonical terms, M banned terms | missing}
304
354
  Entities : {loaded — EntityA, EntityB, EntityC | missing}
355
+ Lessons : {loaded — N guardrails | none yet}
305
356
  Service : {active_service} ({active_service_module}) | single-service
357
+ Svc Root : {service_root} — conventions + trace_dir loaded from service config | —
306
358
  Status : {FULL | PARTIAL — missing: CLAUDE.md / business-dict / core-entities | MINIMAL}
307
359
  ```
308
360
 
@@ -429,6 +481,11 @@ Suggest the logical next command based on workflow phase:
429
481
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
430
482
  | /fix-bug | Create PR and link to ticket |
431
483
  | /debug | `/fix-bug {ticket-id}` if fix needed |
484
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
485
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
486
+ | /learn | Continue working — lesson applies on next command |
487
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
488
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
432
489
 
433
490
  Format the footer as:
434
491
  ```
@@ -99,6 +99,37 @@ If `services` section is present:
99
99
  - Override `paths.domain_knowledge_dir` → `{spec_source}/specs/domain-knowledge`
100
100
  - Override `paths.business_dictionary` → `{spec_source}/specs/domain-knowledge/business-dictionary.md`
101
101
  - Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
102
+ - Override `paths.bug_reports_dir` → `{spec_source}/feedback/bug-reports`
103
+ - Override `paths.bdd_proposals_dir` → `{spec_source}/feedback/bdd-proposals`
104
+
105
+ > **Why under `spec_source`:** tester feedback (`/report-bug`, `/propose-scenario`) must land in the **shared spec repo** so PO/Dev see it when they `/sync`. In single-service mode (no `spec_source`), these default to `feedback/bug-reports` and `feedback/bdd-proposals` at repo root — still shared, same repo.
106
+
107
+ ---
108
+
109
+ ## Step 1.6 — [SERVICE CONVENTIONS] Load service-specific conventions (umbrella mode)
110
+
111
+ *Skip this step entirely if `active_service` is `"unresolved"` or context is single-service mode.*
112
+
113
+ When `active_service` has been resolved to a real path in Step 1.5 (e.g., `user-service/`):
114
+
115
+ **1. Locate service config** — try in priority order:
116
+ - `{active_service}/.agent/project-context.yaml`
117
+ - `{active_service}/project-context.yaml`
118
+
119
+ **2. If found, override with service-specific values:**
120
+
121
+ | Variable | Source |
122
+ |----------|--------|
123
+ | `conventions.test_command` | service's `conventions.test_command` |
124
+ | `conventions.build_command` | service's `conventions.build_command` |
125
+ | `paths.trace_dir` | `{active_service}/{service paths.trace_dir}` — default: `{active_service}/.trace` |
126
+ | `paths.specs_dir` | `{active_service}/{service paths.specs_dir}` (if set in service config, else keep Step 1.5 override) |
127
+
128
+ **3. Store** `service_root = {active_service}` as the working directory anchor for all downstream commands:
129
+ - Shell commands (`/run-tests`, `/generate-tests`) run **from within** `service_root`
130
+ - File write operations (test files, trace TSVs) use paths **relative to** `service_root`
131
+
132
+ **4. If service config not found** — keep umbrella defaults, still set `service_root = {active_service}` (path anchor is always needed even without a config override).
102
133
 
103
134
  ---
104
135
 
@@ -192,6 +223,25 @@ These two variables (`active_module`, `platform_type`) are the canonical source
192
223
 
193
224
  ---
194
225
 
226
+ ## Step 6.7 — [GUARDRAILS] Load Project Lessons (conditional)
227
+
228
+ *Accumulated mistakes the AI must not repeat in this project. These are added over time via `/learn`
229
+ or accepted during `/review-code`, `/fix-bug`, `/debug`.*
230
+
231
+ Resolve the lessons file path:
232
+ - Use `paths.lessons_file` if set (may be service-overridden in umbrella mode, Step 1.6)
233
+ - Else default `specs/domain-knowledge/lessons-learned.md`
234
+ - In umbrella/service mode (when `service_root` is set), if `paths.lessons_file` is unset, default to `{service_root}/.agent/project-lessons.md`
235
+
236
+ If the file exists, read it and store ALL lessons as **ACTIVE GUARDRAILS** for the session:
237
+ - Treat each lesson's **Rule** as a hard constraint — same priority as CLAUDE.md coding standards (Step 3).
238
+ - Before generating or modifying any artifact (PRD, BDD, tech-doc, code, test), check the output against every lesson whose `category` matches the current command AND whose `scope` matches the target (domain / file).
239
+ - If a generated output would violate a lesson → correct it **before** presenting, and note which lesson (`L-NNN`) was applied.
240
+
241
+ If the file does not exist → skip silently (no lessons captured yet).
242
+
243
+ ---
244
+
195
245
  ## Step 7 — [RECAP] Working Memory Recap (anti-lost-in-middle)
196
246
 
197
247
  After loading all context, synthesize and output a compact summary block.
@@ -207,7 +257,9 @@ Layers : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Ser
207
257
  Ticket : {ticket_prefix}-
208
258
  Dict : {loaded — N canonical terms, M banned terms | missing}
209
259
  Entities : {loaded — EntityA, EntityB, EntityC | missing}
260
+ Lessons : {loaded — N guardrails | none yet}
210
261
  Service : {active_service} ({active_service_module}) | single-service
262
+ Svc Root : {service_root} — conventions + trace_dir loaded from service config | —
211
263
  Status : {FULL | PARTIAL — missing: CLAUDE.md / business-dict / core-entities | MINIMAL}
212
264
  ```
213
265
 
@@ -410,6 +462,11 @@ Suggest the logical next command based on workflow phase:
410
462
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
411
463
  | /fix-bug | Create PR and link to ticket |
412
464
  | /debug | `/fix-bug {ticket-id}` if fix needed |
465
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
466
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
467
+ | /learn | Continue working — lesson applies on next command |
468
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
469
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
413
470
 
414
471
  Format the footer as:
415
472
  ```
@@ -205,6 +205,11 @@ Suggest the logical next command based on workflow phase:
205
205
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
206
206
  | /fix-bug | Create PR and link to ticket |
207
207
  | /debug | `/fix-bug {ticket-id}` if fix needed |
208
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
209
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
210
+ | /learn | Continue working — lesson applies on next command |
211
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
212
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
208
213
 
209
214
  Format the footer as:
210
215
  ```
@@ -449,6 +454,11 @@ Suggest the logical next command based on workflow phase:
449
454
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
450
455
  | /fix-bug | Create PR and link to ticket |
451
456
  | /debug | `/fix-bug {ticket-id}` if fix needed |
457
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
458
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
459
+ | /learn | Continue working — lesson applies on next command |
460
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
461
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
452
462
 
453
463
  Format the footer as:
454
464
  ```
@@ -151,6 +151,11 @@ Suggest the logical next command based on workflow phase:
151
151
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
152
152
  | /fix-bug | Create PR and link to ticket |
153
153
  | /debug | `/fix-bug {ticket-id}` if fix needed |
154
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
155
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
156
+ | /learn | Continue working — lesson applies on next command |
157
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
158
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
154
159
 
155
160
  Format the footer as:
156
161
  ```
@@ -222,6 +222,11 @@ Suggest the logical next command based on workflow phase:
222
222
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
223
223
  | /fix-bug | Create PR and link to ticket |
224
224
  | /debug | `/fix-bug {ticket-id}` if fix needed |
225
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
226
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
227
+ | /learn | Continue working — lesson applies on next command |
228
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
229
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
225
230
 
226
231
  Format the footer as:
227
232
  ```
@@ -354,6 +359,11 @@ Suggest the logical next command based on workflow phase:
354
359
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
355
360
  | /fix-bug | Create PR and link to ticket |
356
361
  | /debug | `/fix-bug {ticket-id}` if fix needed |
362
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
363
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
364
+ | /learn | Continue working — lesson applies on next command |
365
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
366
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
357
367
 
358
368
  Format the footer as:
359
369
  ```
@@ -265,6 +265,11 @@ Suggest the logical next command based on workflow phase:
265
265
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
266
266
  | /fix-bug | Create PR and link to ticket |
267
267
  | /debug | `/fix-bug {ticket-id}` if fix needed |
268
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
269
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
270
+ | /learn | Continue working — lesson applies on next command |
271
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
272
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
268
273
 
269
274
  Format the footer as:
270
275
  ```
@@ -372,6 +377,37 @@ If `services` section is present:
372
377
  - Override `paths.domain_knowledge_dir` → `{spec_source}/specs/domain-knowledge`
373
378
  - Override `paths.business_dictionary` → `{spec_source}/specs/domain-knowledge/business-dictionary.md`
374
379
  - Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
380
+ - Override `paths.bug_reports_dir` → `{spec_source}/feedback/bug-reports`
381
+ - Override `paths.bdd_proposals_dir` → `{spec_source}/feedback/bdd-proposals`
382
+
383
+ > **Why under `spec_source`:** tester feedback (`/report-bug`, `/propose-scenario`) must land in the **shared spec repo** so PO/Dev see it when they `/sync`. In single-service mode (no `spec_source`), these default to `feedback/bug-reports` and `feedback/bdd-proposals` at repo root — still shared, same repo.
384
+
385
+ ---
386
+
387
+ ## Step 1.6 — [SERVICE CONVENTIONS] Load service-specific conventions (umbrella mode)
388
+
389
+ *Skip this step entirely if `active_service` is `"unresolved"` or context is single-service mode.*
390
+
391
+ When `active_service` has been resolved to a real path in Step 1.5 (e.g., `user-service/`):
392
+
393
+ **1. Locate service config** — try in priority order:
394
+ - `{active_service}/.agent/project-context.yaml`
395
+ - `{active_service}/project-context.yaml`
396
+
397
+ **2. If found, override with service-specific values:**
398
+
399
+ | Variable | Source |
400
+ |----------|--------|
401
+ | `conventions.test_command` | service's `conventions.test_command` |
402
+ | `conventions.build_command` | service's `conventions.build_command` |
403
+ | `paths.trace_dir` | `{active_service}/{service paths.trace_dir}` — default: `{active_service}/.trace` |
404
+ | `paths.specs_dir` | `{active_service}/{service paths.specs_dir}` (if set in service config, else keep Step 1.5 override) |
405
+
406
+ **3. Store** `service_root = {active_service}` as the working directory anchor for all downstream commands:
407
+ - Shell commands (`/run-tests`, `/generate-tests`) run **from within** `service_root`
408
+ - File write operations (test files, trace TSVs) use paths **relative to** `service_root`
409
+
410
+ **4. If service config not found** — keep umbrella defaults, still set `service_root = {active_service}` (path anchor is always needed even without a config override).
375
411
 
376
412
  ---
377
413
 
@@ -465,6 +501,25 @@ These two variables (`active_module`, `platform_type`) are the canonical source
465
501
 
466
502
  ---
467
503
 
504
+ ## Step 6.7 — [GUARDRAILS] Load Project Lessons (conditional)
505
+
506
+ *Accumulated mistakes the AI must not repeat in this project. These are added over time via `/learn`
507
+ or accepted during `/review-code`, `/fix-bug`, `/debug`.*
508
+
509
+ Resolve the lessons file path:
510
+ - Use `paths.lessons_file` if set (may be service-overridden in umbrella mode, Step 1.6)
511
+ - Else default `specs/domain-knowledge/lessons-learned.md`
512
+ - In umbrella/service mode (when `service_root` is set), if `paths.lessons_file` is unset, default to `{service_root}/.agent/project-lessons.md`
513
+
514
+ If the file exists, read it and store ALL lessons as **ACTIVE GUARDRAILS** for the session:
515
+ - Treat each lesson's **Rule** as a hard constraint — same priority as CLAUDE.md coding standards (Step 3).
516
+ - Before generating or modifying any artifact (PRD, BDD, tech-doc, code, test), check the output against every lesson whose `category` matches the current command AND whose `scope` matches the target (domain / file).
517
+ - If a generated output would violate a lesson → correct it **before** presenting, and note which lesson (`L-NNN`) was applied.
518
+
519
+ If the file does not exist → skip silently (no lessons captured yet).
520
+
521
+ ---
522
+
468
523
  ## Step 7 — [RECAP] Working Memory Recap (anti-lost-in-middle)
469
524
 
470
525
  After loading all context, synthesize and output a compact summary block.
@@ -480,7 +535,9 @@ Layers : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Ser
480
535
  Ticket : {ticket_prefix}-
481
536
  Dict : {loaded — N canonical terms, M banned terms | missing}
482
537
  Entities : {loaded — EntityA, EntityB, EntityC | missing}
538
+ Lessons : {loaded — N guardrails | none yet}
483
539
  Service : {active_service} ({active_service_module}) | single-service
540
+ Svc Root : {service_root} — conventions + trace_dir loaded from service config | —
484
541
  Status : {FULL | PARTIAL — missing: CLAUDE.md / business-dict / core-entities | MINIMAL}
485
542
  ```
486
543
 
@@ -608,6 +665,11 @@ Suggest the logical next command based on workflow phase:
608
665
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
609
666
  | /fix-bug | Create PR and link to ticket |
610
667
  | /debug | `/fix-bug {ticket-id}` if fix needed |
668
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
669
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
670
+ | /learn | Continue working — lesson applies on next command |
671
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
672
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
611
673
 
612
674
  Format the footer as:
613
675
  ```
@@ -718,6 +780,37 @@ If `services` section is present:
718
780
  - Override `paths.domain_knowledge_dir` → `{spec_source}/specs/domain-knowledge`
719
781
  - Override `paths.business_dictionary` → `{spec_source}/specs/domain-knowledge/business-dictionary.md`
720
782
  - Override `paths.core_entities` → `{spec_source}/specs/domain-knowledge/core-entities.md`
783
+ - Override `paths.bug_reports_dir` → `{spec_source}/feedback/bug-reports`
784
+ - Override `paths.bdd_proposals_dir` → `{spec_source}/feedback/bdd-proposals`
785
+
786
+ > **Why under `spec_source`:** tester feedback (`/report-bug`, `/propose-scenario`) must land in the **shared spec repo** so PO/Dev see it when they `/sync`. In single-service mode (no `spec_source`), these default to `feedback/bug-reports` and `feedback/bdd-proposals` at repo root — still shared, same repo.
787
+
788
+ ---
789
+
790
+ ## Step 1.6 — [SERVICE CONVENTIONS] Load service-specific conventions (umbrella mode)
791
+
792
+ *Skip this step entirely if `active_service` is `"unresolved"` or context is single-service mode.*
793
+
794
+ When `active_service` has been resolved to a real path in Step 1.5 (e.g., `user-service/`):
795
+
796
+ **1. Locate service config** — try in priority order:
797
+ - `{active_service}/.agent/project-context.yaml`
798
+ - `{active_service}/project-context.yaml`
799
+
800
+ **2. If found, override with service-specific values:**
801
+
802
+ | Variable | Source |
803
+ |----------|--------|
804
+ | `conventions.test_command` | service's `conventions.test_command` |
805
+ | `conventions.build_command` | service's `conventions.build_command` |
806
+ | `paths.trace_dir` | `{active_service}/{service paths.trace_dir}` — default: `{active_service}/.trace` |
807
+ | `paths.specs_dir` | `{active_service}/{service paths.specs_dir}` (if set in service config, else keep Step 1.5 override) |
808
+
809
+ **3. Store** `service_root = {active_service}` as the working directory anchor for all downstream commands:
810
+ - Shell commands (`/run-tests`, `/generate-tests`) run **from within** `service_root`
811
+ - File write operations (test files, trace TSVs) use paths **relative to** `service_root`
812
+
813
+ **4. If service config not found** — keep umbrella defaults, still set `service_root = {active_service}` (path anchor is always needed even without a config override).
721
814
 
722
815
  ---
723
816
 
@@ -811,6 +904,25 @@ These two variables (`active_module`, `platform_type`) are the canonical source
811
904
 
812
905
  ---
813
906
 
907
+ ## Step 6.7 — [GUARDRAILS] Load Project Lessons (conditional)
908
+
909
+ *Accumulated mistakes the AI must not repeat in this project. These are added over time via `/learn`
910
+ or accepted during `/review-code`, `/fix-bug`, `/debug`.*
911
+
912
+ Resolve the lessons file path:
913
+ - Use `paths.lessons_file` if set (may be service-overridden in umbrella mode, Step 1.6)
914
+ - Else default `specs/domain-knowledge/lessons-learned.md`
915
+ - In umbrella/service mode (when `service_root` is set), if `paths.lessons_file` is unset, default to `{service_root}/.agent/project-lessons.md`
916
+
917
+ If the file exists, read it and store ALL lessons as **ACTIVE GUARDRAILS** for the session:
918
+ - Treat each lesson's **Rule** as a hard constraint — same priority as CLAUDE.md coding standards (Step 3).
919
+ - Before generating or modifying any artifact (PRD, BDD, tech-doc, code, test), check the output against every lesson whose `category` matches the current command AND whose `scope` matches the target (domain / file).
920
+ - If a generated output would violate a lesson → correct it **before** presenting, and note which lesson (`L-NNN`) was applied.
921
+
922
+ If the file does not exist → skip silently (no lessons captured yet).
923
+
924
+ ---
925
+
814
926
  ## Step 7 — [RECAP] Working Memory Recap (anti-lost-in-middle)
815
927
 
816
928
  After loading all context, synthesize and output a compact summary block.
@@ -826,7 +938,9 @@ Layers : {layer order from CLAUDE.md §2, e.g., Controller → Facade → Ser
826
938
  Ticket : {ticket_prefix}-
827
939
  Dict : {loaded — N canonical terms, M banned terms | missing}
828
940
  Entities : {loaded — EntityA, EntityB, EntityC | missing}
941
+ Lessons : {loaded — N guardrails | none yet}
829
942
  Service : {active_service} ({active_service_module}) | single-service
943
+ Svc Root : {service_root} — conventions + trace_dir loaded from service config | —
830
944
  Status : {FULL | PARTIAL — missing: CLAUDE.md / business-dict / core-entities | MINIMAL}
831
945
  ```
832
946
 
@@ -969,6 +1083,11 @@ Suggest the logical next command based on workflow phase:
969
1083
  | /validate-traces | DRIFT/UNTRACKED → `/generate-code {UC-ID}`; GAP → `/generate-tests {UC-ID}`; all OK → create PR |
970
1084
  | /fix-bug | Create PR and link to ticket |
971
1085
  | /debug | `/fix-bug {ticket-id}` if fix needed |
1086
+ | /report-bug | Send to dev (`/fix-bug {BUG-ID}`); if coverage gap → `/propose-scenario {UC-ID}` |
1087
+ | /propose-scenario | Notify PO/Dev to review the proposal in `feedback/bdd-proposals/` |
1088
+ | /learn | Continue working — lesson applies on next command |
1089
+ | /sync | `/validate-traces` for full coverage; act on any `📥 tester feedback` surfaced |
1090
+ | /update-framework | Review `git diff .agent/`, commit; `/sync` for project content |
972
1091
 
973
1092
  Format the footer as:
974
1093
  ```