cc-dev-template 0.1.25 → 0.1.27

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.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "cc-dev-template",
3
- "version": "0.1.25",
3
+ "version": "0.1.27",
4
4
  "description": "Structured AI-assisted development framework for Claude Code",
5
5
  "bin": {
6
6
  "cc-dev-template": "./bin/install.js"
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: decomposition-agent
3
- description: Breaks approved plans into executable tasks with dependencies, or reviews a decomposition for quality and completeness.
3
+ description: Breaks approved plans into executable tasks with dependencies, or reviews a decomposition for quality and completeness. ORCHESTRATION ONLY - spawned by orchestrator during decomposition workflow. Requires plan context; do not use for general coding.
4
4
  tools: Read, Glob, Grep, Write, Edit
5
5
  model: opus
6
6
  color: cyan
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: execution-agent
3
- description: Implements a single task from a plan, or reviews an implementation for correctness and ADR compliance.
3
+ description: Implements a single task from a plan, or reviews an implementation for correctness and ADR compliance. ORCHESTRATION ONLY - spawned by orchestrator during execution workflow. Requires plan/task context; do not use for general coding.
4
4
  tools: Read, Glob, Grep, Write, Edit, Bash
5
5
  model: opus
6
6
  color: yellow
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: rca-agent
3
- description: Investigates bugs to form testable hypotheses. Reads debug context, explores code, and returns a hypothesis specific enough to verify with a test.
3
+ description: Investigates bugs to form testable hypotheses. Reads debug context, explores code, and returns a hypothesis specific enough to verify with a test. ORCHESTRATION ONLY - spawned by orchestrator during debugging workflow. Requires debug.yaml context; do not use for general coding.
4
4
  tools: Read, Glob, Grep, Edit, Bash
5
5
  model: opus
6
6
  color: orange
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  name: tdd-agent
3
- description: Writes failing tests to verify bug hypotheses, or fixes code to make tests pass. Used in debugging workflows for test-driven bug fixes.
3
+ description: Writes failing tests to verify bug hypotheses, or fixes code to make tests pass. ORCHESTRATION ONLY - spawned by orchestrator during debugging workflow. Requires debug.yaml and task context; do not use for general coding.
4
4
  tools: Read, Glob, Grep, Write, Edit, Bash
5
5
  model: opus
6
6
  color: red
@@ -10,8 +10,8 @@ cat << 'EOF'
10
10
  You are an ORCHESTRATOR, not an implementer. Your main thread is for coordination only.
11
11
 
12
12
  DELEGATE AGGRESSIVELY:
13
- - Use Explore agents (model: haiku) for read-only exploration: file search, code understanding, research
14
- - Use execution-agent (model: opus) for ALL reasoning, code changes, implementation, refactors
13
+ - Use Task with model: haiku for read-only exploration: file search, code understanding, research
14
+ - Use Task with model: opus for ALL reasoning, code changes, implementation, refactors
15
15
  - Default to opus when uncertain—it handles complexity better
16
16
  - Launch multiple agents in parallel when tasks are independent
17
17
  - The only tools you use directly: Task, TodoWrite, AskUserQuestion