prizmkit 1.1.193 → 1.1.195

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 (79) hide show
  1. package/bin/create-prizmkit.js +43 -12
  2. package/bundled/VERSION.json +3 -3
  3. package/bundled/dev-pipeline/.env.example +5 -0
  4. package/bundled/dev-pipeline/README.md +2 -1
  5. package/bundled/dev-pipeline/prizmkit_runtime/checkpoint_state.py +111 -30
  6. package/bundled/dev-pipeline/prizmkit_runtime/cli.py +44 -3
  7. package/bundled/dev-pipeline/prizmkit_runtime/commands.py +29 -9
  8. package/bundled/dev-pipeline/prizmkit_runtime/config.py +121 -44
  9. package/bundled/dev-pipeline/prizmkit_runtime/daemon.py +190 -37
  10. package/bundled/dev-pipeline/prizmkit_runtime/interoperability.py +1 -0
  11. package/bundled/dev-pipeline/prizmkit_runtime/iterate.py +2480 -0
  12. package/bundled/dev-pipeline/prizmkit_runtime/paths.py +3 -0
  13. package/bundled/dev-pipeline/prizmkit_runtime/runner_bookkeeping.py +32 -8
  14. package/bundled/dev-pipeline/prizmkit_runtime/runners.py +29 -12
  15. package/bundled/dev-pipeline/prizmkit_runtime/runtime_commit.py +13 -5
  16. package/bundled/dev-pipeline/prizmkit_runtime/status.py +166 -0
  17. package/bundled/dev-pipeline/scripts/feature_list_contract.py +964 -0
  18. package/bundled/dev-pipeline/scripts/generate-bootstrap-prompt.py +18 -40
  19. package/bundled/dev-pipeline/scripts/generate-bugfix-prompt.py +24 -19
  20. package/bundled/dev-pipeline/scripts/prompt_framework.py +24 -8
  21. package/bundled/dev-pipeline/templates/bootstrap-tier3.md +1 -63
  22. package/bundled/dev-pipeline/templates/bug-fix-list-schema.json +8 -6
  23. package/bundled/dev-pipeline/templates/bugfix-bootstrap-prompt.md +0 -10
  24. package/bundled/dev-pipeline/templates/feature-list-schema.json +8 -6
  25. package/bundled/dev-pipeline/templates/iterate/evaluate-prompt.md +97 -0
  26. package/bundled/dev-pipeline/templates/iterate/evaluation-schema.json +538 -0
  27. package/bundled/dev-pipeline/templates/iterate/headless-plan-prompt.md +66 -0
  28. package/bundled/dev-pipeline/templates/sections/phase-specify-plan-full.md +2 -2
  29. package/bundled/dev-pipeline/templates/sections/runtime-commit-handoff.md +13 -4
  30. package/bundled/rules/USAGE.md +15 -48
  31. package/bundled/rules/_rules-metadata.json +7 -14
  32. package/bundled/rules/general/coding-baseline.md +23 -0
  33. package/bundled/rules/prizm/prizm-progressive-loading.md +2 -2
  34. package/bundled/skills/_metadata.json +12 -42
  35. package/bundled/skills/app-planner/SKILL.md +2 -2
  36. package/bundled/skills/app-planner/references/generated-plan-review.md +2 -2
  37. package/bundled/skills/app-planner/references/project-state-detection.md +1 -1
  38. package/bundled/skills/app-planner/references/rules-configuration.md +158 -88
  39. package/bundled/skills/app-planner/scripts/validate-rules-configuration.py +543 -12
  40. package/bundled/skills/bug-planner/references/verification.md +4 -5
  41. package/bundled/skills/bugfix-pipeline-launcher/SKILL.md +20 -14
  42. package/bundled/skills/bugfix-pipeline-launcher/references/configuration.md +49 -9
  43. package/bundled/skills/feature-pipeline-launcher/SKILL.md +20 -14
  44. package/bundled/skills/feature-pipeline-launcher/references/configuration.md +49 -9
  45. package/bundled/skills/feature-planner/SKILL.md +3 -3
  46. package/bundled/skills/feature-planner/references/browser-interaction.md +9 -29
  47. package/bundled/skills/iterate-pipeline-launcher/SKILL.md +273 -0
  48. package/bundled/skills/iterate-pipeline-launcher/references/configuration.md +105 -0
  49. package/bundled/skills/prizmkit-code-review/SKILL.md +10 -8
  50. package/bundled/skills/prizmkit-code-review/references/independent-code-review.md +4 -1
  51. package/bundled/skills/prizmkit-code-review/references/review-report-template.md +2 -1
  52. package/bundled/skills/prizmkit-code-review/scripts/render_review_report.py +12 -8
  53. package/bundled/skills/prizmkit-implement/SKILL.md +2 -2
  54. package/bundled/skills/prizmkit-init/SKILL.md +10 -10
  55. package/bundled/skills/prizmkit-init/references/brownfield-deep-init.md +81 -0
  56. package/bundled/skills/prizmkit-plan/SKILL.md +2 -1
  57. package/bundled/skills/prizmkit-plan/assets/plan-template.md +2 -0
  58. package/bundled/skills/prizmkit-prizm-docs/SKILL.md +8 -4
  59. package/bundled/skills/prizmkit-prizm-docs/assets/prizm-docs-format.md +8 -7
  60. package/bundled/skills/prizmkit-prizm-docs/references/op-init.md +33 -16
  61. package/bundled/skills/prizmkit-prizm-docs/references/op-validate.md +1 -1
  62. package/bundled/skills/prizmkit-retrospective/SKILL.md +29 -12
  63. package/bundled/skills/prizmkit-retrospective/references/retrospective-result-schema.json +126 -2
  64. package/bundled/skills/prizmkit-retrospective/references/rule-evolution-steps.md +86 -0
  65. package/bundled/skills/prizmkit-test/SKILL.md +2 -1
  66. package/bundled/skills/prizmkit-workflow/SKILL.md +8 -0
  67. package/bundled/skills/prizmkit-workflow/references/cold-start-rules.md +84 -0
  68. package/bundled/templates/project-memory-template.md +3 -3
  69. package/package.json +1 -1
  70. package/src/clean.js +2 -3
  71. package/src/config.js +52 -39
  72. package/src/index.js +29 -111
  73. package/src/prompts.js +20 -87
  74. package/src/runtime-passthrough.js +324 -0
  75. package/src/scaffold.js +41 -294
  76. package/src/upgrade.js +7 -39
  77. package/bundled/dev-pipeline/templates/sections/phase-browser-verification-auto.md +0 -127
  78. package/bundled/dev-pipeline/templates/sections/phase-browser-verification-opencli.md +0 -124
  79. package/src/external-skills.js +0 -103
@@ -0,0 +1,538 @@
1
+ {
2
+ "$schema": "http://json-schema.org/draft-07/schema#",
3
+ "title": "PrizmKit Iterate Evaluation Result",
4
+ "description": "Strict two-stage product value funnel output emitted by Phase A read-only evaluation.",
5
+ "type": "object",
6
+ "required": [
7
+ "schema_version",
8
+ "product_shapes",
9
+ "evidence_mode",
10
+ "walkthrough_notes",
11
+ "candidates_discovered",
12
+ "approved_candidates",
13
+ "requires_user_confirm",
14
+ "rejected_candidates",
15
+ "verdict",
16
+ "summary"
17
+ ],
18
+ "properties": {
19
+ "schema_version": {
20
+ "type": "string",
21
+ "const": "prizmkit-iterate-evaluation-v1"
22
+ },
23
+ "product_shapes": {
24
+ "type": "array",
25
+ "minItems": 1,
26
+ "maxItems": 2,
27
+ "uniqueItems": true,
28
+ "items": {
29
+ "type": "string",
30
+ "enum": [
31
+ "web_saas",
32
+ "cli_devtool",
33
+ "mobile",
34
+ "api_sdk",
35
+ "internal_ops"
36
+ ]
37
+ }
38
+ },
39
+ "evidence_mode": {
40
+ "type": "string",
41
+ "enum": [
42
+ "live_walkthrough",
43
+ "source_only"
44
+ ]
45
+ },
46
+ "walkthrough_notes": {
47
+ "type": "object",
48
+ "required": [
49
+ "target_attempted",
50
+ "server_cleanup_confirmed",
51
+ "reason"
52
+ ],
53
+ "properties": {
54
+ "target_attempted": {
55
+ "type": "boolean"
56
+ },
57
+ "server_cleanup_confirmed": {
58
+ "type": "boolean"
59
+ },
60
+ "reason": {
61
+ "type": "string",
62
+ "minLength": 1
63
+ }
64
+ },
65
+ "additionalProperties": false
66
+ },
67
+ "candidates_discovered": {
68
+ "type": "array",
69
+ "items": {
70
+ "type": "object",
71
+ "required": [
72
+ "id",
73
+ "title",
74
+ "lens",
75
+ "evidence_tier",
76
+ "evidence",
77
+ "problem",
78
+ "desired_outcome",
79
+ "blast_radius",
80
+ "blast_radius_flags",
81
+ "gate_results",
82
+ "disposition_reason"
83
+ ],
84
+ "properties": {
85
+ "id": {
86
+ "type": "string",
87
+ "minLength": 1
88
+ },
89
+ "title": {
90
+ "type": "string",
91
+ "minLength": 1
92
+ },
93
+ "lens": {
94
+ "type": "string",
95
+ "enum": [
96
+ "stall",
97
+ "hollow_success",
98
+ "trust_and_control",
99
+ "power_and_limits",
100
+ "failure",
101
+ "second_use",
102
+ "adjacent_wish",
103
+ "seeing_others",
104
+ "time_and_ritual",
105
+ "stretch_idea"
106
+ ]
107
+ },
108
+ "evidence_tier": {
109
+ "type": "string",
110
+ "enum": [
111
+ "fact",
112
+ "inference",
113
+ "taste"
114
+ ]
115
+ },
116
+ "evidence": {
117
+ "type": "array",
118
+ "minItems": 1,
119
+ "items": {
120
+ "type": "string",
121
+ "minLength": 1
122
+ }
123
+ },
124
+ "problem": {
125
+ "type": "string",
126
+ "minLength": 1
127
+ },
128
+ "desired_outcome": {
129
+ "type": "string",
130
+ "minLength": 1
131
+ },
132
+ "blast_radius": {
133
+ "type": "string",
134
+ "enum": [
135
+ "low",
136
+ "medium",
137
+ "high"
138
+ ]
139
+ },
140
+ "blast_radius_flags": {
141
+ "type": "array",
142
+ "uniqueItems": true,
143
+ "items": {
144
+ "type": "string",
145
+ "enum": [
146
+ "schema_migration",
147
+ "heavy_dependency",
148
+ "paid_external_api",
149
+ "breaking_contract",
150
+ "major_ia_redesign",
151
+ "over_3_features"
152
+ ]
153
+ }
154
+ },
155
+ "gate_results": {
156
+ "type": "object",
157
+ "required": [
158
+ "gate1_scope_dedupe",
159
+ "gate2_fact_admission",
160
+ "gate3_blast_radius",
161
+ "gate4_selected"
162
+ ],
163
+ "properties": {
164
+ "gate1_scope_dedupe": {
165
+ "type": "string",
166
+ "enum": [
167
+ "pass",
168
+ "fail"
169
+ ]
170
+ },
171
+ "gate2_fact_admission": {
172
+ "type": "string",
173
+ "enum": [
174
+ "pass",
175
+ "fail"
176
+ ]
177
+ },
178
+ "gate3_blast_radius": {
179
+ "type": "string",
180
+ "enum": [
181
+ "auto_safe",
182
+ "requires_user_confirm"
183
+ ]
184
+ },
185
+ "gate4_selected": {
186
+ "type": "string",
187
+ "enum": [
188
+ "approved",
189
+ "deferred_for_user",
190
+ "rejected"
191
+ ]
192
+ }
193
+ },
194
+ "additionalProperties": false
195
+ },
196
+ "disposition_reason": {
197
+ "type": "string",
198
+ "minLength": 1
199
+ }
200
+ },
201
+ "additionalProperties": false
202
+ }
203
+ },
204
+ "approved_candidates": {
205
+ "type": "array",
206
+ "maxItems": 3,
207
+ "items": {
208
+ "type": "object",
209
+ "required": [
210
+ "id",
211
+ "title",
212
+ "lens",
213
+ "evidence_tier",
214
+ "evidence",
215
+ "problem",
216
+ "desired_outcome",
217
+ "blast_radius",
218
+ "blast_radius_flags",
219
+ "target_paths",
220
+ "acceptance_hints",
221
+ "ui_affected"
222
+ ],
223
+ "properties": {
224
+ "id": {
225
+ "type": "string",
226
+ "minLength": 1
227
+ },
228
+ "title": {
229
+ "type": "string",
230
+ "minLength": 1
231
+ },
232
+ "lens": {
233
+ "type": "string",
234
+ "enum": [
235
+ "stall",
236
+ "hollow_success",
237
+ "trust_and_control",
238
+ "power_and_limits",
239
+ "failure",
240
+ "second_use"
241
+ ]
242
+ },
243
+ "evidence_tier": {
244
+ "type": "string",
245
+ "const": "fact"
246
+ },
247
+ "evidence": {
248
+ "type": "array",
249
+ "minItems": 1,
250
+ "items": {
251
+ "type": "string",
252
+ "minLength": 1
253
+ }
254
+ },
255
+ "problem": {
256
+ "type": "string",
257
+ "minLength": 1
258
+ },
259
+ "desired_outcome": {
260
+ "type": "string",
261
+ "minLength": 1
262
+ },
263
+ "blast_radius": {
264
+ "type": "string",
265
+ "enum": [
266
+ "low",
267
+ "medium"
268
+ ]
269
+ },
270
+ "blast_radius_flags": {
271
+ "type": "array",
272
+ "maxItems": 0
273
+ },
274
+ "target_paths": {
275
+ "type": "array",
276
+ "items": {
277
+ "type": "string",
278
+ "minLength": 1
279
+ }
280
+ },
281
+ "acceptance_hints": {
282
+ "type": "array",
283
+ "minItems": 1,
284
+ "items": {
285
+ "type": "string",
286
+ "minLength": 1
287
+ }
288
+ },
289
+ "ui_affected": {
290
+ "type": "boolean"
291
+ }
292
+ },
293
+ "additionalProperties": false
294
+ }
295
+ },
296
+ "requires_user_confirm": {
297
+ "type": "array",
298
+ "items": {
299
+ "type": "object",
300
+ "required": [
301
+ "id",
302
+ "title",
303
+ "evidence_tier",
304
+ "lens",
305
+ "blast_radius_flags",
306
+ "problem",
307
+ "proposal",
308
+ "decision_needed",
309
+ "evidence"
310
+ ],
311
+ "properties": {
312
+ "id": {
313
+ "type": "string",
314
+ "minLength": 1
315
+ },
316
+ "title": {
317
+ "type": "string",
318
+ "minLength": 1
319
+ },
320
+ "evidence_tier": {
321
+ "type": "string",
322
+ "enum": [
323
+ "fact",
324
+ "inference",
325
+ "taste"
326
+ ]
327
+ },
328
+ "lens": {
329
+ "type": "string",
330
+ "enum": [
331
+ "stall",
332
+ "hollow_success",
333
+ "trust_and_control",
334
+ "power_and_limits",
335
+ "failure",
336
+ "second_use",
337
+ "adjacent_wish",
338
+ "seeing_others",
339
+ "time_and_ritual",
340
+ "stretch_idea"
341
+ ]
342
+ },
343
+ "blast_radius_flags": {
344
+ "type": "array",
345
+ "uniqueItems": true,
346
+ "items": {
347
+ "type": "string",
348
+ "enum": [
349
+ "schema_migration",
350
+ "heavy_dependency",
351
+ "paid_external_api",
352
+ "breaking_contract",
353
+ "major_ia_redesign",
354
+ "over_3_features"
355
+ ]
356
+ }
357
+ },
358
+ "problem": {
359
+ "type": "string",
360
+ "minLength": 1
361
+ },
362
+ "proposal": {
363
+ "type": "string",
364
+ "minLength": 1
365
+ },
366
+ "decision_needed": {
367
+ "type": "string",
368
+ "minLength": 1
369
+ },
370
+ "evidence": {
371
+ "type": "array",
372
+ "minItems": 1,
373
+ "items": {
374
+ "type": "string",
375
+ "minLength": 1
376
+ }
377
+ }
378
+ },
379
+ "additionalProperties": false
380
+ }
381
+ },
382
+ "rejected_candidates": {
383
+ "type": "array",
384
+ "items": {
385
+ "type": "object",
386
+ "required": [
387
+ "id",
388
+ "title",
389
+ "evidence_tier",
390
+ "lens",
391
+ "rejected_by_gate",
392
+ "reason"
393
+ ],
394
+ "properties": {
395
+ "id": {
396
+ "type": "string",
397
+ "minLength": 1
398
+ },
399
+ "title": {
400
+ "type": "string",
401
+ "minLength": 1
402
+ },
403
+ "evidence_tier": {
404
+ "type": "string",
405
+ "enum": [
406
+ "fact",
407
+ "inference",
408
+ "taste"
409
+ ]
410
+ },
411
+ "lens": {
412
+ "type": "string",
413
+ "enum": [
414
+ "stall",
415
+ "hollow_success",
416
+ "trust_and_control",
417
+ "power_and_limits",
418
+ "failure",
419
+ "second_use",
420
+ "adjacent_wish",
421
+ "seeing_others",
422
+ "time_and_ritual",
423
+ "stretch_idea"
424
+ ]
425
+ },
426
+ "rejected_by_gate": {
427
+ "type": "string",
428
+ "enum": [
429
+ "gate1",
430
+ "gate2",
431
+ "gate3",
432
+ "gate4"
433
+ ]
434
+ },
435
+ "reason": {
436
+ "type": "string",
437
+ "minLength": 1
438
+ }
439
+ },
440
+ "additionalProperties": false
441
+ }
442
+ },
443
+ "verdict": {
444
+ "type": "string",
445
+ "enum": [
446
+ "CONTINUE_WITH_CANDIDATES",
447
+ "PAUSE_FOR_USER_CONFIRM",
448
+ "STOP_GOAL_REACHED",
449
+ "STOP_NO_HIGH_VALUE"
450
+ ]
451
+ },
452
+ "summary": {
453
+ "type": "string",
454
+ "minLength": 1
455
+ }
456
+ },
457
+ "allOf": [
458
+ {
459
+ "if": {
460
+ "properties": {
461
+ "verdict": {
462
+ "const": "CONTINUE_WITH_CANDIDATES"
463
+ }
464
+ }
465
+ },
466
+ "then": {
467
+ "properties": {
468
+ "approved_candidates": {
469
+ "minItems": 1,
470
+ "maxItems": 3
471
+ }
472
+ }
473
+ }
474
+ },
475
+ {
476
+ "if": {
477
+ "properties": {
478
+ "verdict": {
479
+ "const": "PAUSE_FOR_USER_CONFIRM"
480
+ }
481
+ }
482
+ },
483
+ "then": {
484
+ "properties": {
485
+ "approved_candidates": {
486
+ "maxItems": 0
487
+ },
488
+ "requires_user_confirm": {
489
+ "minItems": 1
490
+ }
491
+ }
492
+ }
493
+ },
494
+ {
495
+ "if": {
496
+ "properties": {
497
+ "verdict": {
498
+ "enum": [
499
+ "STOP_GOAL_REACHED",
500
+ "STOP_NO_HIGH_VALUE"
501
+ ]
502
+ }
503
+ }
504
+ },
505
+ "then": {
506
+ "properties": {
507
+ "approved_candidates": {
508
+ "maxItems": 0
509
+ }
510
+ }
511
+ }
512
+ },
513
+ {
514
+ "if": {
515
+ "properties": {
516
+ "evidence_mode": {
517
+ "const": "live_walkthrough"
518
+ }
519
+ }
520
+ },
521
+ "then": {
522
+ "properties": {
523
+ "walkthrough_notes": {
524
+ "properties": {
525
+ "target_attempted": {
526
+ "const": true
527
+ },
528
+ "server_cleanup_confirmed": {
529
+ "const": true
530
+ }
531
+ }
532
+ }
533
+ }
534
+ }
535
+ }
536
+ ],
537
+ "additionalProperties": false
538
+ }
@@ -0,0 +1,66 @@
1
+ # Autonomous Headless Feature Planning — Phase B
2
+
3
+ You are converting Phase A's approved product-improvement candidates into a validated feature draft in a **fresh, non-interactive headless session**.
4
+
5
+ ## Hard Execution Boundaries
6
+
7
+ 1. **Writable Target Only**:
8
+ - Write ONLY `{{DRAFT_OUTPUT_PATH}}`.
9
+ - NEVER directly create or edit `.prizmkit/plans/feature-list.json` — the Python runtime validates your draft and performs the single atomic write itself.
10
+ - NEVER modify project source files, tests, configs, or documentation.
11
+ 2. **Non-Interactive Headless Execution**:
12
+ - Do NOT ask questions or wait for human confirmation.
13
+ - Do NOT invoke interactive planner or launcher skills.
14
+ 3. **Bounded History Rule**:
15
+ - Consume ONLY the bounded context provided at `{{CONTEXT_PATH}}` (root project fields, `task_count`, `next_id`, and up to 5 recent `{id, description}` entries). Do NOT read complete historical feature lists into context.
16
+
17
+ ## Planning Inputs
18
+
19
+ - **Project Root**: `{{PROJECT_ROOT}}`
20
+ - **Planning Mode**: `{{MODE}}`
21
+ - **Bounded Context JSON**: `{{CONTEXT_PATH}}`
22
+ - **Approved Candidates JSON**: `{{CANDIDATES_PATH}}`
23
+ - **Draft Output Path**: `{{DRAFT_OUTPUT_PATH}}`
24
+ - **Feature List Schema**: `{{SCHEMA_PATH}}`
25
+
26
+ {{REPAIR_FEEDBACK}}
27
+
28
+ ## Required Draft Payload Shape
29
+
30
+ Follow the exact shape for `{{MODE}}`:
31
+
32
+ - **When `{{MODE}}` is `append`** (existing `.prizmkit/plans/feature-list.json`):
33
+ - Output an additions-only JSON object containing ONLY the top-level `"features"` key: `{"features": [...]}`.
34
+ - Assign strictly sequential `F-NNN` IDs starting at `next_id` from `{{CONTEXT_PATH}}` (e.g., if `next_id` is `"F-004"`, assign `"F-004"`, `"F-005"`, ...).
35
+ - **When `{{MODE}}` is `generate`** (no `.prizmkit/plans/feature-list.json` exists yet):
36
+ - Output a complete `dev-pipeline-feature-list-v1` object containing `"$schema": "dev-pipeline-feature-list-v1"`, non-empty `"project_name"`, `"project_description"`, `"global_context"`, and `"features": [...]`.
37
+ - Assign strictly sequential IDs starting at `"F-001"` (`"F-001"`, `"F-002"`, ...) and ensure `"F-001"` has `"dependencies": []`.
38
+
39
+ ## Fresh-Session Task Contract
40
+
41
+ Each feature object in `"features"` will be executed later in an isolated fresh AI session with zero conversation history. Therefore every feature MUST satisfy all rules below:
42
+
43
+ 1. **Allowed Fields Only**:
44
+ - Required: `id`, `title`, `description`, `priority` (`"critical" | "high" | "medium" | "low"`), `dependencies` (acyclic list of valid `F-NNN` IDs), `acceptance_criteria` (array of >=1 testable Given/When/Then strings; 3+ recommended), `status` (`"pending"`).
45
+ - Optional: `estimated_complexity` (`"low" | "medium" | "high" | "critical"`), `user_context` (supplementary purpose-tagged code/config refs only), `browser_interaction`, `testing`, `model`.
46
+ - Do NOT invent unknown root, `global_context`, or feature keys.
47
+ 2. **Self-Contained Contract**:
48
+ - `description` + `acceptance_criteria` alone must specify objective, current state, desired state, concrete constraints/non-goals, verified integration points, relevant edge cases, and observable completion evidence.
49
+ - Minimum 15 words required per `description` (30+ for `low`, 50+ for `medium`, 80+ for `high`, 100+ for `critical`).
50
+ - Group by contract-bounded capability (1–3 features matching the approved candidates; never over-split one capability into micro-tickets).
51
+ - Use clear English feature titles suitable for artifact directory slugs.
52
+ 3. **Browser Verification Contract (`playwright-cli`)**:
53
+ - For any candidate with `ui_affected: true` or user-facing UI acceptance criteria on a frontend project, include:
54
+ ```json
55
+ "browser_interaction": {
56
+ "tool": "playwright-cli",
57
+ "verify_steps": [
58
+ "Verify <observable user-visible outcome>"
59
+ ]
60
+ }
61
+ ```
62
+ - `tool` MUST always be `"playwright-cli"`. `verify_steps` describe WHAT to verify, not hardcoded ports or element refs.
63
+
64
+ ## Output Requirement
65
+
66
+ Read `{{CONTEXT_PATH}}` and `{{CANDIDATES_PATH}}`, inspect only the specific target files cited by the approved candidates when needed to make contracts accurate, write the valid JSON draft to `{{DRAFT_OUTPUT_PATH}}`, and stop.
@@ -17,7 +17,7 @@ If `EXISTING_CODE` is non-empty: your spec/plan/tasks must reflect this existing
17
17
 
18
18
  **Step A — Build Context Snapshot** (skip if `context-snapshot.md` already exists):
19
19
 
20
- 1. Read `.prizmkit/prizm-docs/root.prizm` and the relevant module indexes and detail docs
20
+ 1. Read `.prizmkit/prizm-docs/root.prizm` and the relevant module indexes and detail docs. If the feature lands on `frontend`, `backend`, `database`, or `mobile` (mapping browser UI work to frontend, service or API work to backend, schema migration or ORM work to database, and iOS, Android, React Native, or Flutter work to mobile), perform an exact path Read of `.prizmkit/rules/<layer>-rules.md` (read both existing files if spanning two layers; never load all four files by default; do not depend on git tracking or glob). When the target file does not exist, do not block and do not silently skip—explicitly activate `framework-coding-baseline` (`coding-baseline` plus detected language/stack conventions).
21
21
  2. Detect source code directories from KEY_FILES and STRUCTURE sections in `root.prizm`; if root docs are unavailable, use the helper to list likely source files:
22
22
  ```bash
23
23
  {{RUNTIME_HELPER_CMD}} artifact source-files . --json
@@ -27,7 +27,7 @@ If `EXISTING_CODE` is non-empty: your spec/plan/tasks must reflect this existing
27
27
  4. Write `.prizmkit/specs/{{FEATURE_SLUG}}/context-snapshot.md`:
28
28
  - **Section 1 — Feature Brief**: feature description (copy from Task Contract above, 2-3 lines only)
29
29
  - **Section 2 — Verification Gates**: copy the gate checklist from the Task Contract above
30
- - **Section 3 — Key TRAPS & RULES**: extract TRAPS and RULES entries from the loaded Prizm docs that apply to files in this feature's scope. Do NOT copy complete documentation files — include only the specific TRAPS/RULES lines relevant to the files listed in Section 4.
30
+ - **Section 3 — Key TRAPS & RULES**: record `- Active Rule Source: project-layer-rules (<paths>) | framework-coding-baseline (<detected language/stack conventions>) | not-applicable`, extract only the relevant rule highlights from the active layer rules (or `coding-baseline` + language conventions), and extract TRAPS and RULES entries from the loaded Prizm docs that apply to files in this feature's scope. Do NOT copy complete documentation or rule files — include only the specific TRAPS/RULES lines relevant to the files listed in Section 4.
31
31
  - **Section 4 — File Manifest**: For each file relevant to this feature, list path, why needed (modify/reference/test), key interface signatures. Do NOT include full file content. Format:
32
32
  ### Files to Modify
33
33
  | File | Why Needed | Key Interfaces |
@@ -6,13 +6,22 @@ After Code Review, all configured verification, `TEST_PASS`, family reports/summ
6
6
 
7
7
  1. As the session orchestrator, validate every required stage artifact and result first. Atomic Skills do not perform this sequencing check.
8
8
  2. Re-inventory the complete final Git-visible workspace: staged, unstaged, added, deleted, renamed, copied, and non-ignored untracked content. Confirm Code Review and Test authority covers every behavior-affecting change, including correct work that predated this session or lives in framework, generated, instruction, lock, or host-support paths. If production behavior changed after those gates, re-enter them before commit preparation.
9
- 3. Invoke `/prizmkit-committer` with the same artifact root, exact readiness evidence, and request path:
9
+ 3. Mark the committer checkpoint step `in_progress` before invoking `/prizmkit-committer` (never after `runtime-commit-request.json` exists):
10
+
11
+ ```text
12
+ {{CHECKPOINT_PYTHON_CMD}} \
13
+ --checkpoint-path {{CHECKPOINT_PATH}} \
14
+ --step prizmkit-committer \
15
+ --status in_progress
16
+ ```
17
+
18
+ 4. Invoke `/prizmkit-committer` with the same artifact root, exact readiness evidence, and request path:
10
19
 
11
20
  ```text
12
21
  /prizmkit-committer operation=prepare-runtime-commit artifact_dir={{ARTIFACT_DIR}} evidence_paths=<exact validated artifact paths> request_path={{ARTIFACT_DIR}}/runtime-commit-request.json
13
22
  ```
14
23
 
15
- 4. The committer validates the complete final workspace without a caller-supplied path manifest or provenance classification. Ignored paths remain local and never block or require force-add. Merge conflicts, Secrets, sensitive local content, known incorrect or incoherent changes, unverifiable content, and stale readiness evidence still block. It generates one truthful Conventional Commit message and writes this request without staging or committing:
24
+ 5. The committer validates the complete final workspace without a caller-supplied path manifest or provenance classification. Ignored paths remain local and never block or require force-add. Merge conflicts, Secrets, sensitive local content, known incorrect or incoherent changes, unverifiable content, and stale readiness evidence still block. It generates one truthful Conventional Commit message and writes this request without staging or committing:
16
25
 
17
26
  ```json
18
27
  {
@@ -23,7 +32,7 @@ After Code Review, all configured verification, `TEST_PASS`, family reports/summ
23
32
  }
24
33
  ```
25
34
 
26
- 5. Require the stage-local result `COMMIT_REQUEST_READY` and the exact request file. After that success, do not call the checkpoint helper again for the committer stage and do not run another request validator. Stop normal work immediately.
27
- 6. Do not run `git add`, `git commit`, `git commit --amend`, merge, push, broad source searches, or create additional task files after the valid request exists.
35
+ 6. Require the stage-local result `COMMIT_REQUEST_READY` and the exact request file. After that success, do not call the checkpoint helper again for the committer stage and do not run another request validator. Stop normal work immediately.
36
+ 7. Do not run `git add`, `git commit`, `git commit --amend`, merge, push, broad source searches, or create additional task files after the valid request exists.
28
37
 
29
38
  The Runtime validates the pathless schema, base, complete pre-commit checkpoint, non-ignored workspace, sensitive path safeguards, merge state, and causal bookkeeping boundary. It atomically publishes its own commit-pending checkpoint state, stages the complete workspace while omitting only the exact active request/checkpoint whose final receipt cannot truthfully precede the commit, verifies a non-empty commit with the expected parent and message, records its Git receipt, and only then finalizes `COMMITTED` and performs configured integration. A malformed, stale, unsafe, incomplete, or contradictory handoff blocks without deleting user data.