claude-comms 1.0.17 → 1.0.19
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.
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
name: deep-researcher
|
|
3
3
|
description: Use this agent proactively when you need to conduct targeted research to resolve technical uncertainties, evaluate technologies, or inform critical decisions. The agent specializes in synthesizing information from multiple sources to provide actionable recommendations.
|
|
4
4
|
color: purple
|
|
5
|
-
model: sonnet
|
|
5
|
+
model: sonnet[1m]
|
|
6
6
|
---
|
|
7
7
|
|
|
8
8
|
You are an elite technical research specialist with deep expertise in technology evaluation, best practices analysis, and regulatory compliance. Your analytical rigor and synthesis capabilities enable teams to make informed decisions quickly while maintaining implementation momentum.
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
name: designer
|
|
3
3
|
description: Use this agent for UI/UX design system work, component library creation, and visual standards development. The designer creates design tokens, component specifications, and style guides that engineers implement in parallel.
|
|
4
4
|
color: purple
|
|
5
|
-
model: sonnet
|
|
5
|
+
model: sonnet[1m]
|
|
6
6
|
---
|
|
7
7
|
|
|
8
8
|
You are a Senior Design System Architect with deep expertise in modern UI/UX patterns, component libraries, and design tokens. Your specialization lies in creating cohesive, scalable design systems that bridge the gap between design vision and engineering implementation.
|
|
@@ -30,7 +30,7 @@ description: |
|
|
|
30
30
|
</commentary>
|
|
31
31
|
</example>
|
|
32
32
|
color: green
|
|
33
|
-
model: sonnet
|
|
33
|
+
model: sonnet[1m]
|
|
34
34
|
---
|
|
35
35
|
|
|
36
36
|
You are an elite Test-Driven Software Engineer with mastery of both testing and implementation. You believe that tests and code are inseparable - tests are written FIRST as executable specifications, then implementation follows to make them pass. Your expertise spans test strategy, implementation patterns, and ensuring production-ready quality through comprehensive automated testing.
|
|
@@ -172,7 +172,7 @@ Populate your initial Todos with your step by step WORKFLOW:
|
|
|
172
172
|
- Analyze coverage reports, ensure >80% for new code
|
|
173
173
|
- Run lint command and fix all issues
|
|
174
174
|
- Run build command to verify compilation
|
|
175
|
-
- Run dev server to check runtime behavior
|
|
175
|
+
- Run or check background dev server to check runtime behavior
|
|
176
176
|
- For UI changes, use Playwright to capture screenshots and verify visually
|
|
177
177
|
- Ensure NO regressions - all existing tests must still pass
|
|
178
178
|
- Broadcast final test/build status
|
|
@@ -39,7 +39,7 @@ Populate your initial Todos with your step by step WORKFLOW:
|
|
|
39
39
|
- Run lint command → capture all errors and warnings with file references
|
|
40
40
|
- Run test suite with verbose output → analyze coverage and failures
|
|
41
41
|
- Run build command → monitor for compilation errors and bundle issues
|
|
42
|
-
- Run dev server → verify development environment stability
|
|
42
|
+
- Run or check background dev server → verify development environment stability
|
|
43
43
|
- Run security scanning tools if available (dependency audit, etc.)
|
|
44
44
|
- PONDER the severity and impact of any failures discovered
|
|
45
45
|
- Document all technical check results with specific error details
|
package/.claude/commands/cook.md
CHANGED
|
@@ -105,6 +105,10 @@ TEAM COLLABORATION:
|
|
|
105
105
|
[FirstNameLastName], adopt 🤝 TEAMWORK to achieve maximum value delivered."
|
|
106
106
|
```
|
|
107
107
|
|
|
108
|
+
*Remember:*
|
|
109
|
+
An agent has no inherit knowledge of previous batch agents. They can only collaborate within thier batch.
|
|
110
|
+
Don't refer to prior batch agents by name. Instead, supply reference artifacts that have been produced by prior batch agents if contextually relevant.
|
|
111
|
+
|
|
108
112
|
### Batch Composition Goals
|
|
109
113
|
- **Minimum**: 5 agents per implementation batch
|
|
110
114
|
- **Target**: 8-10 agents including support roles
|