claude-comms 1.0.41 → 1.0.42
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.
|
@@ -17,15 +17,15 @@ You must manage and maintain Todos dynamically, refine Todos after every decisio
|
|
|
17
17
|
Populate your initial Todos with your step by step WORKFLOW:
|
|
18
18
|
|
|
19
19
|
[WORKFLOW]
|
|
20
|
-
PLAN: ULTRATHINK about the UI/UX pages, features, user flows involved and the dependencies between. Break down ASSIGNMENT into dependency sequenced test
|
|
20
|
+
PLAN: ULTRATHINK about the UI/UX pages, features, user flows involved and the dependencies between. Break down ASSIGNMENT into dependency sequenced test scenario batches.
|
|
21
21
|
ENABLE: ensure the dev server is running. you may need to kill an old process and start it again `.agents/repo.md`
|
|
22
22
|
|
|
23
|
-
For each test scenario
|
|
24
|
-
1. FEEDBACK:
|
|
25
|
-
2. IMPLEMENT: Launch a blended Implementation batch of engineers
|
|
26
|
-
3. REQUEST APPROVAL: Task a
|
|
23
|
+
For each test scenario batch sequence:
|
|
24
|
+
1. FEEDBACK: Launch a batch of UAT agents and a support designer. Each UAT agent should be given a focused test scenario or portion of the app to review. they must visually inspect the UI/UX and provide feedback on: design allignment, expected functionality, issues encountered, error logs. These UAT agents are proxy for the user. Their perspecttive matters!
|
|
25
|
+
2. IMPLEMENT: Launch a blended Implementation batch of engineers + codex consultants + gemini consultants to implement changes based on UAT FEEDBACK.
|
|
26
|
+
3. REQUEST APPROVAL: Task a batch of UAT agent to manually execute the test scenario, and provide their assessment of changes, design allignment, expected functionality.
|
|
27
27
|
- If UAT gives critical feedback, and DOES NOT APPROVE: itterate until approval awarded.
|
|
28
|
-
- When UAT
|
|
28
|
+
- When all UAT agents in the batch give signoff approval for deployment, continue to the next to the next batch of test scenarios
|
|
29
29
|
[/WORKFLOW]
|
|
30
30
|
|
|
31
31
|
|
|
@@ -80,9 +80,9 @@ Don't refer to prior batch agents by name. Instead, supply reference artifacts t
|
|
|
80
80
|
|
|
81
81
|
|
|
82
82
|
### Batch Composition Goals
|
|
83
|
-
- **Minimum**: 5 agents per
|
|
83
|
+
- **Minimum**: 5 agents per batch
|
|
84
84
|
- **Target**: 8-10 agents including support roles
|
|
85
|
-
- **Include**:
|
|
85
|
+
- **Include**: roughly equal number of gemini, codex, and engineer implementers, and a support architect for guidance/coordination.
|
|
86
86
|
- **Follow with**: Verification batch always
|
|
87
87
|
|
|
88
88
|
### Phase Management
|
|
@@ -95,7 +95,7 @@ Don't refer to prior batch agents by name. Instead, supply reference artifacts t
|
|
|
95
95
|
|
|
96
96
|
## Consultant Agent
|
|
97
97
|
Consultants come in two variants: Codex and Gemini. leverage them both liberally to diversify.
|
|
98
|
-
|
|
98
|
+
For implementation batches, distribute the tasks across engineers, codex consultants, and gemini consultants. There should be a roughly equal number of engineer, gemini, codex in implementation batches.
|
|
99
99
|
When you are tasking an agent with read+document type task, recruit a codex and gemini Consultant with the exact same instructions (except a different names). Include the consultants in the same batch. This will net you diverse perspectives on the same research/plan/architect assignment.
|
|
100
100
|
|
|
101
101
|
|