@yeongjaeyou/claude-code-config 0.18.3 → 0.18.4
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.
|
@@ -11,8 +11,6 @@ Break down large work items into manageable, independent issues. Follow project
|
|
|
11
11
|
1. Check issue numbers: Run `gh issue list` to view current issue numbers
|
|
12
12
|
2. **Discover available components**:
|
|
13
13
|
- Scan `.claude/agents/` for custom agents (read YAML frontmatter)
|
|
14
|
-
- Scan `.claude/skills/` for available skills (read SKILL.md)
|
|
15
|
-
- Check `.mcp.json` for configured MCP servers
|
|
16
14
|
- Detect test frameworks (jest.config.*, pytest.ini, vitest.config.*, pyproject.toml, etc.)
|
|
17
15
|
3. **Check TDD applicability** (if user hasn't specified):
|
|
18
16
|
- Analyze work type: code implementation vs docs/infra/config
|
|
@@ -80,16 +78,12 @@ Examples (vary by project, for reference only):
|
|
|
80
78
|
**Execution strategy**:
|
|
81
79
|
- **Pattern**: main-only | sequential | parallel | delegation
|
|
82
80
|
- **Delegate to**: (delegation only) agent name
|
|
83
|
-
- **Skills**: [discovered skills, or none]
|
|
84
|
-
- **MCP**: [discovered MCP servers, or none]
|
|
85
81
|
|
|
86
82
|
**Execution diagram**:
|
|
87
83
|
```
|
|
88
84
|
+------+
|
|
89
85
|
| main |
|
|
90
86
|
+------+
|
|
91
|
-
Skills: none
|
|
92
|
-
MCP: none
|
|
93
87
|
```
|
|
94
88
|
|
|
95
89
|
**References** (optional):
|
|
@@ -102,36 +96,34 @@ MCP: none
|
|
|
102
96
|
|
|
103
97
|
### Component Discovery
|
|
104
98
|
|
|
105
|
-
Before decomposing issues, scan for available
|
|
99
|
+
Before decomposing issues, scan for available agents:
|
|
106
100
|
- **Agents**: `.claude/agents/*.md` (extract name, description from YAML frontmatter)
|
|
107
|
-
- **Skills**: `.claude/skills/*/SKILL.md` (extract name, description from YAML frontmatter)
|
|
108
|
-
- **MCP**: `.mcp.json` (extract server names and purposes)
|
|
109
101
|
|
|
110
102
|
### Execution Patterns
|
|
111
103
|
|
|
112
104
|
```
|
|
113
105
|
Pattern A: main-only
|
|
114
|
-
+------+
|
|
115
|
-
| main |
|
|
106
|
+
+------+
|
|
107
|
+
| main |
|
|
116
108
|
+------+
|
|
117
109
|
|
|
118
110
|
Pattern B: sequential
|
|
119
|
-
+---------+ +------+
|
|
120
|
-
| explore | --> | main |
|
|
111
|
+
+---------+ +------+
|
|
112
|
+
| explore | --> | main |
|
|
121
113
|
+---------+ +------+
|
|
122
114
|
|
|
123
115
|
Pattern C: parallel
|
|
124
116
|
+---------+
|
|
125
117
|
| explore |--+
|
|
126
|
-
+---------+ | +------+
|
|
127
|
-
| explore |--+->| main |
|
|
118
|
+
+---------+ | +------+
|
|
119
|
+
| explore |--+->| main |
|
|
128
120
|
+---------+ | +------+
|
|
129
121
|
| explore |--+
|
|
130
122
|
+---------+
|
|
131
123
|
|
|
132
124
|
Pattern D: delegation
|
|
133
|
-
+------+ +----------------+
|
|
134
|
-
| main | --> | python-pro |
|
|
125
|
+
+------+ +----------------+
|
|
126
|
+
| main | --> | python-pro |
|
|
135
127
|
+------+ | web-researcher |
|
|
136
128
|
+----------------+
|
|
137
129
|
|
|
@@ -156,22 +148,16 @@ Always include an ASCII diagram in the issue body to visualize the execution flo
|
|
|
156
148
|
+------+
|
|
157
149
|
| main |
|
|
158
150
|
+------+
|
|
159
|
-
Skills: /code-review
|
|
160
|
-
MCP: serena
|
|
161
151
|
|
|
162
152
|
// delegation
|
|
163
153
|
+------+ +--------------------+
|
|
164
154
|
| main | --> | deepfake-cv-expert |
|
|
165
155
|
+------+ +--------------------+
|
|
166
|
-
Skills: none
|
|
167
|
-
MCP: none
|
|
168
156
|
|
|
169
157
|
// sequential
|
|
170
158
|
+---------+ +------+
|
|
171
159
|
| explore | --> | main |
|
|
172
160
|
+---------+ +------+
|
|
173
|
-
Skills: ...
|
|
174
|
-
MCP: ...
|
|
175
161
|
```
|
|
176
162
|
|
|
177
163
|
---
|
|
@@ -53,6 +53,7 @@ Act as an expert developer who systematically analyzes and resolves GitHub issue
|
|
|
53
53
|
|
|
54
54
|
7. **Resolve Issue**: Spawn sub-agents to modify code and implement features according to the plan.
|
|
55
55
|
- **If TDD enabled** (marker detected in Step 1):
|
|
56
|
+
- **Reference**: See `feature-planner` skill for detailed TDD methodology
|
|
56
57
|
1. 🔴 RED: Write failing tests first based on requirements
|
|
57
58
|
2. 🟢 GREEN: Implement minimal code to pass tests
|
|
58
59
|
3. 🔵 REFACTOR: Clean up while keeping tests green
|