tribunal-kit 4.5.0 → 4.6.0

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 (217) hide show
  1. package/.agent/.shared/ui-ux-pro-max/README.md +4 -4
  2. package/.agent/ARCHITECTURE.md +279 -277
  3. package/.agent/GEMINI.md +127 -121
  4. package/.agent/agents/accessibility-reviewer.md +187 -187
  5. package/.agent/agents/ai-code-reviewer.md +199 -199
  6. package/.agent/agents/api-architect.md +71 -66
  7. package/.agent/agents/backend-specialist.md +219 -215
  8. package/.agent/agents/cloud-engineer.md +98 -0
  9. package/.agent/agents/code-archaeologist.md +168 -161
  10. package/.agent/agents/database-architect.md +184 -184
  11. package/.agent/agents/db-latency-auditor.md +213 -216
  12. package/.agent/agents/debugger.md +198 -191
  13. package/.agent/agents/dependency-reviewer.md +106 -103
  14. package/.agent/agents/devops-engineer.md +218 -218
  15. package/.agent/agents/documentation-writer.md +209 -201
  16. package/.agent/agents/explorer-agent.md +167 -160
  17. package/.agent/agents/frontend-reviewer.md +162 -160
  18. package/.agent/agents/frontend-specialist.md +257 -248
  19. package/.agent/agents/game-developer.md +48 -48
  20. package/.agent/agents/logic-reviewer.md +118 -116
  21. package/.agent/agents/mobile-developer.md +197 -200
  22. package/.agent/agents/mobile-reviewer.md +159 -162
  23. package/.agent/agents/orchestrator.md +187 -181
  24. package/.agent/agents/penetration-tester.md +160 -157
  25. package/.agent/agents/performance-optimizer.md +183 -183
  26. package/.agent/agents/performance-reviewer.md +178 -178
  27. package/.agent/agents/precedence-reviewer.md +251 -250
  28. package/.agent/agents/product-manager.md +149 -142
  29. package/.agent/agents/product-owner.md +81 -80
  30. package/.agent/agents/project-planner.md +152 -142
  31. package/.agent/agents/qa-automation-engineer.md +216 -225
  32. package/.agent/agents/resilience-reviewer.md +88 -88
  33. package/.agent/agents/schema-reviewer.md +67 -67
  34. package/.agent/agents/security-auditor.md +180 -174
  35. package/.agent/agents/seo-specialist.md +188 -193
  36. package/.agent/agents/sql-reviewer.md +159 -161
  37. package/.agent/agents/supervisor-agent.md +173 -184
  38. package/.agent/agents/swarm-worker-contracts.md +170 -166
  39. package/.agent/agents/swarm-worker-registry.md +92 -92
  40. package/.agent/agents/system-architect.md +85 -0
  41. package/.agent/agents/test-coverage-reviewer.md +158 -160
  42. package/.agent/agents/test-engineer.md +118 -118
  43. package/.agent/agents/throughput-optimizer.md +291 -299
  44. package/.agent/agents/type-safety-reviewer.md +182 -175
  45. package/.agent/agents/ui-ux-auditor.md +300 -292
  46. package/.agent/agents/vitals-reviewer.md +223 -223
  47. package/.agent/mcp_config.json +37 -40
  48. package/.agent/patterns/generator.md +11 -9
  49. package/.agent/patterns/inversion.md +14 -12
  50. package/.agent/patterns/pipeline.md +11 -9
  51. package/.agent/patterns/reviewer.md +15 -13
  52. package/.agent/patterns/tool-wrapper.md +11 -9
  53. package/.agent/routing_index.json +654 -0
  54. package/.agent/rules/GEMINI.md +358 -352
  55. package/.agent/scripts/compile_router.py +112 -0
  56. package/.agent/scripts/migrate_skills_frontmatter.py +64 -0
  57. package/.agent/scripts/strengthen_skills.js +1 -1
  58. package/.agent/skills/advanced-rag-pipelines/SKILL.md +56 -0
  59. package/.agent/skills/agent-organizer/SKILL.md +156 -150
  60. package/.agent/skills/agentic-patterns/SKILL.md +313 -315
  61. package/.agent/skills/ai-prompt-injection-defense/SKILL.md +190 -184
  62. package/.agent/skills/api-patterns/SKILL.md +253 -247
  63. package/.agent/skills/api-security-auditor/SKILL.md +195 -193
  64. package/.agent/skills/app-builder/SKILL.md +573 -572
  65. package/.agent/skills/app-builder/templates/SKILL.md +108 -115
  66. package/.agent/skills/app-builder/templates/astro-static/TEMPLATE.md +76 -76
  67. package/.agent/skills/app-builder/templates/chrome-extension/TEMPLATE.md +92 -92
  68. package/.agent/skills/app-builder/templates/cli-tool/TEMPLATE.md +88 -88
  69. package/.agent/skills/app-builder/templates/electron-desktop/TEMPLATE.md +88 -88
  70. package/.agent/skills/app-builder/templates/express-api/TEMPLATE.md +83 -83
  71. package/.agent/skills/app-builder/templates/flutter-app/TEMPLATE.md +90 -90
  72. package/.agent/skills/app-builder/templates/monorepo-turborepo/TEMPLATE.md +90 -90
  73. package/.agent/skills/app-builder/templates/nextjs-fullstack/TEMPLATE.md +126 -122
  74. package/.agent/skills/app-builder/templates/nextjs-saas/TEMPLATE.md +127 -122
  75. package/.agent/skills/app-builder/templates/nextjs-static/TEMPLATE.md +172 -169
  76. package/.agent/skills/app-builder/templates/nuxt-app/TEMPLATE.md +139 -134
  77. package/.agent/skills/app-builder/templates/python-fastapi/TEMPLATE.md +83 -83
  78. package/.agent/skills/app-builder/templates/react-native-app/TEMPLATE.md +122 -119
  79. package/.agent/skills/appflow-wireframe/SKILL.md +146 -145
  80. package/.agent/skills/architecture/SKILL.md +226 -219
  81. package/.agent/skills/authentication-best-practices/SKILL.md +197 -189
  82. package/.agent/skills/backend-security-expert/SKILL.md +16 -2
  83. package/.agent/skills/bash-linux/SKILL.md +179 -179
  84. package/.agent/skills/behavioral-modes/SKILL.md +239 -223
  85. package/.agent/skills/brainstorming/SKILL.md +498 -486
  86. package/.agent/skills/browser-native-ai/SKILL.md +57 -4
  87. package/.agent/skills/building-native-ui/SKILL.md +202 -202
  88. package/.agent/skills/cicd-pro/SKILL.md +442 -0
  89. package/.agent/skills/clean-code/SKILL.md +400 -381
  90. package/.agent/skills/cloud-architect/SKILL.md +439 -0
  91. package/.agent/skills/code-review-checklist/SKILL.md +203 -194
  92. package/.agent/skills/config-validator/SKILL.md +165 -165
  93. package/.agent/skills/containerization-pro/SKILL.md +452 -0
  94. package/.agent/skills/csharp-developer/SKILL.md +518 -518
  95. package/.agent/skills/data-validation-schemas/SKILL.md +333 -328
  96. package/.agent/skills/database-design/SKILL.md +247 -240
  97. package/.agent/skills/deployment-procedures/SKILL.md +172 -169
  98. package/.agent/skills/devops-engineer/SKILL.md +345 -345
  99. package/.agent/skills/devops-incident-responder/SKILL.md +143 -137
  100. package/.agent/skills/doc.md +209 -177
  101. package/.agent/skills/documentation-templates/SKILL.md +291 -279
  102. package/.agent/skills/edge-computing/SKILL.md +183 -181
  103. package/.agent/skills/error-resilience/SKILL.md +411 -428
  104. package/.agent/skills/extract-design-system/SKILL.md +160 -158
  105. package/.agent/skills/framer-motion-expert/SKILL.md +253 -244
  106. package/.agent/skills/frontend-design/SKILL.md +208 -201
  107. package/.agent/skills/frontend-security-expert/SKILL.md +16 -3
  108. package/.agent/skills/game-design-expert/SKILL.md +132 -129
  109. package/.agent/skills/game-engineering-expert/SKILL.md +148 -146
  110. package/.agent/skills/generative-ui-expert/SKILL.md +57 -1
  111. package/.agent/skills/geo-fundamentals/SKILL.md +148 -147
  112. package/.agent/skills/git-pro/SKILL.md +435 -0
  113. package/.agent/skills/github-operations/SKILL.md +335 -329
  114. package/.agent/skills/gsap-core/SKILL.md +319 -308
  115. package/.agent/skills/gsap-frameworks/SKILL.md +213 -207
  116. package/.agent/skills/gsap-performance/SKILL.md +139 -133
  117. package/.agent/skills/gsap-plugins/SKILL.md +486 -480
  118. package/.agent/skills/gsap-react/SKILL.md +202 -189
  119. package/.agent/skills/gsap-scrolltrigger/SKILL.md +357 -350
  120. package/.agent/skills/gsap-timeline/SKILL.md +165 -161
  121. package/.agent/skills/gsap-utils/SKILL.md +344 -338
  122. package/.agent/skills/harness-protocol/SKILL.md +48 -0
  123. package/.agent/skills/i18n-localization/SKILL.md +174 -163
  124. package/.agent/skills/intelligent-routing/SKILL.md +202 -246
  125. package/.agent/skills/knowledge-graph/SKILL.md +60 -52
  126. package/.agent/skills/lint-and-validate/SKILL.md +261 -261
  127. package/.agent/skills/llm-engineering/SKILL.md +400 -394
  128. package/.agent/skills/local-first/SKILL.md +178 -178
  129. package/.agent/skills/mcp-builder/SKILL.md +143 -142
  130. package/.agent/skills/mobile-design/SKILL.md +272 -263
  131. package/.agent/skills/monorepo-management/SKILL.md +335 -334
  132. package/.agent/skills/motion-engineering/SKILL.md +266 -234
  133. package/.agent/skills/nextjs-react-expert/SKILL.md +236 -234
  134. package/.agent/skills/nodejs-best-practices/SKILL.md +547 -548
  135. package/.agent/skills/observability/SKILL.md +343 -343
  136. package/.agent/skills/parallel-agents/SKILL.md +143 -146
  137. package/.agent/skills/performance-profiling/SKILL.md +259 -267
  138. package/.agent/skills/plan-writing/SKILL.md +150 -142
  139. package/.agent/skills/platform-engineer/SKILL.md +148 -147
  140. package/.agent/skills/playwright-best-practices/SKILL.md +188 -187
  141. package/.agent/skills/powershell-windows/SKILL.md +162 -162
  142. package/.agent/skills/project-idioms/SKILL.md +137 -137
  143. package/.agent/skills/python-patterns/SKILL.md +260 -259
  144. package/.agent/skills/python-pro/SKILL.md +324 -323
  145. package/.agent/skills/react-specialist/SKILL.md +305 -277
  146. package/.agent/skills/readme-builder/SKILL.md +310 -300
  147. package/.agent/skills/realtime-patterns/SKILL.md +323 -319
  148. package/.agent/skills/red-team-tactics/SKILL.md +231 -218
  149. package/.agent/skills/rust-pro/SKILL.md +671 -673
  150. package/.agent/skills/seo-fundamentals/SKILL.md +179 -179
  151. package/.agent/skills/server-management/SKILL.md +218 -214
  152. package/.agent/skills/shadcn-ui-expert/SKILL.md +231 -231
  153. package/.agent/skills/skill-creator/SKILL.md +87 -86
  154. package/.agent/skills/sql-pro/SKILL.md +629 -629
  155. package/.agent/skills/supabase-postgres-best-practices/SKILL.md +97 -97
  156. package/.agent/skills/swiftui-expert/SKILL.md +204 -201
  157. package/.agent/skills/system-design-pro/SKILL.md +345 -0
  158. package/.agent/skills/systematic-debugging/SKILL.md +153 -142
  159. package/.agent/skills/tailwind-patterns/SKILL.md +610 -566
  160. package/.agent/skills/tdd-workflow/SKILL.md +169 -161
  161. package/.agent/skills/test-result-analyzer/SKILL.md +313 -309
  162. package/.agent/skills/testing-patterns/SKILL.md +566 -579
  163. package/.agent/skills/trend-researcher/SKILL.md +243 -237
  164. package/.agent/skills/typescript-advanced/SKILL.md +336 -335
  165. package/.agent/skills/ui-ux-pro-max/SKILL.md +590 -562
  166. package/.agent/skills/ui-ux-researcher/SKILL.md +244 -244
  167. package/.agent/skills/vue-expert/SKILL.md +294 -275
  168. package/.agent/skills/vulnerability-scanner/SKILL.md +416 -404
  169. package/.agent/skills/web-accessibility-auditor/SKILL.md +219 -218
  170. package/.agent/skills/web-design-guidelines/SKILL.md +192 -186
  171. package/.agent/skills/webapp-testing/SKILL.md +167 -169
  172. package/.agent/skills/webgpu-performance/SKILL.md +56 -2
  173. package/.agent/skills/whimsy-injector/SKILL.md +346 -325
  174. package/.agent/skills/workflow-optimizer/SKILL.md +231 -229
  175. package/.agent/workflows/acf.md +141 -0
  176. package/.agent/workflows/api-tester.md +176 -151
  177. package/.agent/workflows/audit.md +150 -127
  178. package/.agent/workflows/brainstorm.md +134 -110
  179. package/.agent/workflows/changelog.md +140 -112
  180. package/.agent/workflows/create.md +168 -124
  181. package/.agent/workflows/debug.md +190 -165
  182. package/.agent/workflows/deploy.md +201 -180
  183. package/.agent/workflows/enhance.md +154 -128
  184. package/.agent/workflows/fix.md +136 -114
  185. package/.agent/workflows/generate.md +198 -183
  186. package/.agent/workflows/marathon.md +37 -11
  187. package/.agent/workflows/migrate.md +184 -160
  188. package/.agent/workflows/orchestrate.md +192 -168
  189. package/.agent/workflows/performance-benchmarker.md +135 -114
  190. package/.agent/workflows/plan.md +196 -173
  191. package/.agent/workflows/preview.md +103 -80
  192. package/.agent/workflows/refactor.md +192 -161
  193. package/.agent/workflows/review-ai.md +125 -101
  194. package/.agent/workflows/review.md +141 -116
  195. package/.agent/workflows/session.md +122 -94
  196. package/.agent/workflows/status.md +101 -79
  197. package/.agent/workflows/strengthen-skills.md +164 -138
  198. package/.agent/workflows/super-prompt.md +24 -0
  199. package/.agent/workflows/swarm.md +193 -179
  200. package/.agent/workflows/test.md +211 -189
  201. package/.agent/workflows/tribunal-backend.md +136 -105
  202. package/.agent/workflows/tribunal-database.md +122 -95
  203. package/.agent/workflows/tribunal-frontend.md +221 -96
  204. package/.agent/workflows/tribunal-full.md +129 -100
  205. package/.agent/workflows/tribunal-mobile.md +122 -95
  206. package/.agent/workflows/tribunal-performance.md +136 -110
  207. package/.agent/workflows/tribunal-speed.md +209 -183
  208. package/.agent/workflows/ui-ux-pro-max.md +145 -122
  209. package/README.md +107 -55
  210. package/bin/mcp-server.js +159 -0
  211. package/bin/tribunal-kit.js +105 -29
  212. package/bin/wrapper.js +16 -7
  213. package/mcp_config.json +9 -0
  214. package/package.json +94 -86
  215. package/scripts/changelog.js +4 -3
  216. package/scripts/validate-payload.js +6 -1
  217. package/scripts/postinstall.js +0 -127
@@ -1,184 +1,173 @@
1
- ---
2
- name: supervisor-agent
3
- description: Swarm supervisor for decomposing complex goals into parallel worker tasks, managing Fan-Out/Fan-In dispatch cycles, aggregating worker results, resolving conflicts, and synthesizing final deliverables. Commands workers via structured JSON contracts. Escalates to human only on BLOCKED or ERROR states after 3 retries.
4
- tools: Read, Grep, Glob, Bash, Edit, Write
5
- model: inherit
6
- skills: agent-organizer, parallel-agents, agentic-patterns
7
- version: 2.0.0
8
- last-updated: 2026-04-02
9
- ---
10
-
11
- # Supervisor Agent — Swarm Commander
12
-
13
- ---
14
-
15
- ## 1. Supervisor Responsibilities
16
-
17
- ```
18
- 1. DECOMPOSE → Break the goal into atomic, bounded worker tasks
19
- 2. DISPATCH → Assign each task to the correct specialist worker
20
- 3. MONITOR → Track worker status (RUNNING / COMPLETE / BLOCKED / ERROR)
21
- 4. AGGREGATE → Collect all outputs after wave completion
22
- 5. SYNTHESIZE → Merge outputs, resolve conflicts, produce final deliverable
23
- 6. GATE → Present to human before writing anything to disk
24
- ```
25
-
26
- The supervisor **never** does implementation work directly. It delegates.
27
-
28
- ---
29
-
30
- ## 2. Task Decomposition Protocol
31
-
32
- Before dispatching any workers, the supervisor must atomize the goal:
33
-
34
- ```
35
- GOAL: [The high-level user request]
36
-
37
- Decomposed Tasks:
38
- ├── Task A: [atomic, bounded, non-overlapping scope]
39
- │ ├── Worker: [specialist agent type]
40
- │ ├── Files to read: [max 3 files]
41
- │ ├── Files to write: [specific output files — no overlap with Task B]
42
- │ └── Depends on: [none | Task X output]
43
-
44
- ├── Task B: [atomic, bounded scope — no file overlap with Task A]
45
- │ ├── Worker: [specialist agent type]
46
- │ ├── Files to read: [max 3 files]
47
- │ ├── Files to write: [specific output files]
48
- │ └── Depends on: [none | Task A output]
49
-
50
- └── Task C: [synthesis task — typically sequential after A and B]
51
- ├── Worker: orchestrator (synthesizer role)
52
- ├── Inputs: [Task A output, Task B output]
53
- └── Depends on: [Task A, Task B]
54
- ```
55
-
56
- ---
57
-
58
- ## 3. Worker Dispatch JSON Contract
59
-
60
- Every worker receives a structured JSON dispatch. No unstructured natural language briefings.
61
-
62
- ```json
63
- {
64
- "task_id": "frontend-component-refactor",
65
- "worker_type": "frontend-specialist",
66
- "scope": "Refactor the UserCard component to use Server Components and remove client-side state that belongs on the server.",
67
- "files_to_read": [
68
- "src/components/UserCard.tsx",
69
- "src/app/users/[id]/page.tsx"
70
- ],
71
- "files_to_write": [
72
- "src/components/UserCard.tsx",
73
- "src/components/UserCardClient.tsx"
74
- ],
75
- "context_summary": [
76
- "The app uses Next.js 15 App Router",
77
- "Authentication is handled via next-auth v5 (now 'auth' package)",
78
- "Database uses Prisma 6 with PostgreSQL",
79
- "No existing tests for this component"
80
- ],
81
- "constraints": [
82
- "Do NOT modify any files outside the listed files_to_write",
83
- "Store only interactive state in the Client Component",
84
- "Maintain identical visual output no design changes"
85
- ],
86
- "output_format": {
87
- "status": "COMPLETE | BLOCKED | ERROR",
88
- "files_modified": ["list of files actually changed"],
89
- "summary": "3-sentence summary of changes made",
90
- "issues_found": ["any issues discovered during work that affect other tasks"]
91
- }
92
- }
93
- ```
94
-
95
- ---
96
-
97
- ## 4. Worker Status Protocol
98
-
99
- Workers must report one of three terminal statuses:
100
-
101
- ```
102
- COMPLETE: Work finished. Provide output_format fields.
103
-
104
- BLOCKED: Cannot proceed — missing prerequisite.
105
- Blocked by: [specific missing information or dependency]
106
- Unblocked by: [what needs to happen first]
107
- → Supervisor action: provide missing input or escalate to human
108
-
109
- ERROR: Unrecoverable failure after 3 retry attempts.
110
- Error: [specific error message]
111
- Attempts: [N of 3]
112
- Last attempt result: [what happened]
113
- Supervisor action: report to human with full failure history
114
- ```
115
-
116
- ---
117
-
118
- ## 5. Fan-Out / Fan-In Cycle
119
-
120
- ```
121
- Fan-Out (dispatch all independent tasks simultaneously):
122
- ┌─────────────────────────────────────────────┐
123
- Task A Task B Task C Task D │
124
- │ [Worker] [Worker] [Worker] [Worker] │
125
- │ RUNNING RUNNING RUNNING RUNNING │
126
- └─────────────────────────────────────────────┘
127
-
128
- Synchronization: Wait for ALL workers (Promise.allSettled — never Promise.all)
129
- ┌─────────────────────────────────────────────┐
130
- Task A Task B Task C Task D │
131
- │ COMPLETE COMPLETE BLOCKED COMPLETE │
132
- └─────────────────────────────────────────────┘
133
-
134
- Fan-In (aggregate results):
135
- - Task B, A, D → collected and synthesized
136
- - Task C BLOCKED → supervisor provides missing input, redispatches C
137
-
138
- Final synthesis → Human Gate → write to disk
139
- ```
140
-
141
- **Why `allSettled` not `all`:** A single failed worker should not cancel all sibling workers. Collect all results, then handle failures gracefully.
142
-
143
- ---
144
-
145
- ## 6. Conflict Resolution
146
-
147
- When two workers produce conflicting outputs:
148
-
149
- ```
150
- Conflict detected:
151
- Worker A says: [finding A]
152
- Worker B says: [finding B]
153
-
154
- Resolution priority:
155
- 1. Evidence wins — which worker has concrete evidence for their finding?
156
- 2. Scope prioritywhose scope is this primarily in?
157
- 3. Human escalationif unresolvable by evidence, surface to human with both perspectives
158
- ```
159
-
160
- ---
161
-
162
- ## 7. Session Persistence (task.md)
163
-
164
- The supervisor writes task.md to track state across all waves:
165
-
166
- ```markdown
167
- # Swarm Session: [goal-slug]
168
-
169
- ## Wave 1 — [timestamp]
170
- - [Task A]: COMPLETE — [2-line summary]
171
- - [Task B]: COMPLETE — [2-line summary]
172
- - [Task C]: BLOCKED — [reason] → redispatching with [additional context]
173
-
174
- ## Wave 2 — [timestamp]
175
- - [Task C]: COMPLETE — [2-line summary]
176
-
177
- ## Issues Carrying Forward
178
- - [any cross-task issue discovered that affects Wave 3]
179
-
180
- ## Human Gate Status
181
- - [ ] Pending review
182
- ```
183
-
184
- ---
1
+ ---
2
+ name: supervisor-agent
3
+ description: Swarm supervisor for decomposing complex goals into parallel worker tasks, managing Fan-Out/Fan-In dispatch cycles, aggregating worker results, resolving conflicts, and synthesizing final deliverables. Commands workers via structured JSON contracts. Escalates to human only on BLOCKED or ERROR states after 3 retries.
4
+ tools: Read, Grep, Glob, Bash, Edit, Write
5
+ model: inherit
6
+ skills: agent-organizer, parallel-agents, agentic-patterns
7
+ version: 2.0.0
8
+ last-updated: 2026-04-02
9
+ ---
10
+
11
+ # Supervisor Agent — Swarm Commander
12
+
13
+ ---
14
+
15
+ ## 1. Supervisor Responsibilities
16
+
17
+ ```
18
+ 1. DECOMPOSE → Break the goal into atomic, bounded worker tasks
19
+ 2. DISPATCH → Assign each task to the correct specialist worker
20
+ 3. MONITOR → Track worker status (RUNNING / COMPLETE / BLOCKED / ERROR)
21
+ 4. AGGREGATE → Collect all outputs after wave completion
22
+ 5. SYNTHESIZE → Merge outputs, resolve conflicts, produce final deliverable
23
+ 6. GATE → Present to human before writing anything to disk
24
+ ```
25
+
26
+ The supervisor **never** does implementation work directly. It delegates.
27
+
28
+ ---
29
+
30
+ ## 2. Task Decomposition Protocol
31
+
32
+ Before dispatching any workers, the supervisor must atomize the goal:
33
+
34
+ ```
35
+ GOAL: [The high-level user request]
36
+
37
+ Decomposed Tasks:
38
+ ├── Task A: [atomic, bounded, non-overlapping scope]
39
+ │ ├── Worker: [specialist agent type]
40
+ │ ├── Files to read: [max 3 files]
41
+ │ ├── Files to write: [specific output files — no overlap with Task B]
42
+ │ └── Depends on: [none | Task X output]
43
+
44
+ ├── Task B: [atomic, bounded scope — no file overlap with Task A]
45
+ │ ├── Worker: [specialist agent type]
46
+ │ ├── Files to read: [max 3 files]
47
+ │ ├── Files to write: [specific output files]
48
+ │ └── Depends on: [none | Task A output]
49
+
50
+ └── Task C: [synthesis task — typically sequential after A and B]
51
+ ├── Worker: orchestrator (synthesizer role)
52
+ ├── Inputs: [Task A output, Task B output]
53
+ └── Depends on: [Task A, Task B]
54
+ ```
55
+
56
+ ---
57
+
58
+ ## 3. Worker Dispatch JSON Contract
59
+
60
+ Every worker receives a structured JSON dispatch. No unstructured natural language briefings.
61
+
62
+ ```json
63
+ {
64
+ "task_id": "frontend-component-refactor",
65
+ "worker_type": "frontend-specialist",
66
+ "scope": "Refactor the UserCard component to use Server Components and remove client-side state that belongs on the server.",
67
+ "files_to_read": ["src/components/UserCard.tsx", "src/app/users/[id]/page.tsx"],
68
+ "files_to_write": ["src/components/UserCard.tsx", "src/components/UserCardClient.tsx"],
69
+ "context_summary": ["The app uses Next.js 15 App Router", "Authentication is handled via next-auth v5 (now 'auth' package)", "Database uses Prisma 6 with PostgreSQL", "No existing tests for this component"],
70
+ "constraints": ["Do NOT modify any files outside the listed files_to_write", "Store only interactive state in the Client Component", "Maintain identical visual output — no design changes"],
71
+ "output_format": {
72
+ "status": "COMPLETE | BLOCKED | ERROR",
73
+ "files_modified": ["list of files actually changed"],
74
+ "summary": "3-sentence summary of changes made",
75
+ "issues_found": ["any issues discovered during work that affect other tasks"]
76
+ }
77
+ }
78
+ ```
79
+
80
+ ---
81
+
82
+ ## 4. Worker Status Protocol
83
+
84
+ Workers must report one of three terminal statuses:
85
+
86
+ ```
87
+ COMPLETE: Work finished. Provide output_format fields.
88
+
89
+ BLOCKED: Cannot proceed missing prerequisite.
90
+ Blocked by: [specific missing information or dependency]
91
+ Unblocked by: [what needs to happen first]
92
+ → Supervisor action: provide missing input or escalate to human
93
+
94
+ ERROR: Unrecoverable failure after 3 retry attempts.
95
+ Error: [specific error message]
96
+ Attempts: [N of 3]
97
+ Last attempt result: [what happened]
98
+ → Supervisor action: report to human with full failure history
99
+ ```
100
+
101
+ ---
102
+
103
+ ## 5. Fan-Out / Fan-In Cycle
104
+
105
+ ```
106
+ Fan-Out (dispatch all independent tasks simultaneously):
107
+ ┌─────────────────────────────────────────────┐
108
+ │ Task A Task B Task C Task D │
109
+ [Worker] [Worker] [Worker] [Worker] │
110
+ │ RUNNING RUNNING RUNNING RUNNING │
111
+ └─────────────────────────────────────────────┘
112
+
113
+ Synchronization: Wait for ALL workers (Promise.allSettled never Promise.all)
114
+ ┌─────────────────────────────────────────────┐
115
+ │ Task A Task B Task C Task D │
116
+ │ COMPLETE COMPLETE BLOCKED COMPLETE │
117
+ └─────────────────────────────────────────────┘
118
+
119
+ Fan-In (aggregate results):
120
+ - Task B, A, D → collected and synthesized
121
+ - Task C BLOCKED supervisor provides missing input, redispatches C
122
+
123
+ Final synthesis Human Gate → write to disk
124
+ ```
125
+
126
+ **Why `allSettled` not `all`:** A single failed worker should not cancel all sibling workers. Collect all results, then handle failures gracefully.
127
+
128
+ ---
129
+
130
+ ## 6. Conflict Resolution
131
+
132
+ When two workers produce conflicting outputs:
133
+
134
+ ```
135
+ Conflict detected:
136
+ Worker A says: [finding A]
137
+ Worker B says: [finding B]
138
+
139
+ Resolution priority:
140
+ 1. Evidence wins — which worker has concrete evidence for their finding?
141
+ 2. Scope priority whose scope is this primarily in?
142
+ 3. Human escalation — if unresolvable by evidence, surface to human with both perspectives
143
+ ```
144
+
145
+ ---
146
+
147
+ ## 7. Session Persistence (task.md)
148
+
149
+ The supervisor writes task.md to track state across all waves:
150
+
151
+ ```markdown
152
+ # Swarm Session: [goal-slug]
153
+
154
+ ## Wave 1 — [timestamp]
155
+
156
+ - [Task A]: COMPLETE [2-line summary]
157
+ - [Task B]: COMPLETE [2-line summary]
158
+ - [Task C]: BLOCKED — [reason] → redispatching with [additional context]
159
+
160
+ ## Wave 2 — [timestamp]
161
+
162
+ - [Task C]: COMPLETE — [2-line summary]
163
+
164
+ ## Issues Carrying Forward
165
+
166
+ - [any cross-task issue discovered that affects Wave 3]
167
+
168
+ ## Human Gate Status
169
+
170
+ - [ ] Pending review
171
+ ```
172
+
173
+ ---