@devobsessed/code-captain 0.0.3
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/README.md +214 -0
- package/bin/install.js +1048 -0
- package/claude-code/README.md +276 -0
- package/claude-code/agents/code-captain.md +121 -0
- package/claude-code/agents/spec-generator.md +271 -0
- package/claude-code/agents/story-creator.md +309 -0
- package/claude-code/agents/tech-spec.md +440 -0
- package/claude-code/commands/cc-initialize.md +520 -0
- package/copilot/README.md +210 -0
- package/copilot/chatmodes/Code Captain.chatmode.md +60 -0
- package/copilot/docs/best-practices.md +74 -0
- package/copilot/prompts/create-adr.prompt.md +468 -0
- package/copilot/prompts/create-spec.prompt.md +430 -0
- package/copilot/prompts/edit-spec.prompt.md +396 -0
- package/copilot/prompts/execute-task.prompt.md +144 -0
- package/copilot/prompts/explain-code.prompt.md +292 -0
- package/copilot/prompts/initialize.prompt.md +65 -0
- package/copilot/prompts/new-command.prompt.md +310 -0
- package/copilot/prompts/plan-product.prompt.md +450 -0
- package/copilot/prompts/research.prompt.md +329 -0
- package/copilot/prompts/status.prompt.md +424 -0
- package/copilot/prompts/swab.prompt.md +217 -0
- package/cursor/README.md +224 -0
- package/cursor/cc.md +183 -0
- package/cursor/cc.mdc +69 -0
- package/cursor/commands/create-adr.md +504 -0
- package/cursor/commands/create-spec.md +430 -0
- package/cursor/commands/edit-spec.md +405 -0
- package/cursor/commands/execute-task.md +514 -0
- package/cursor/commands/explain-code.md +289 -0
- package/cursor/commands/initialize.md +397 -0
- package/cursor/commands/new-command.md +312 -0
- package/cursor/commands/plan-product.md +466 -0
- package/cursor/commands/research.md +317 -0
- package/cursor/commands/status.md +413 -0
- package/cursor/commands/swab.md +209 -0
- package/cursor/docs/best-practices.md +74 -0
- package/cursor/integrations/azure-devops/create-azure-work-items.md +403 -0
- package/cursor/integrations/azure-devops/sync-azure-work-items.md +486 -0
- package/cursor/integrations/github/create-github-issues.md +765 -0
- package/cursor/integrations/github/scripts/create-issues-batch.sh +272 -0
- package/cursor/integrations/github/sync-github-issues.md +237 -0
- package/cursor/integrations/github/sync.md +305 -0
- package/manifest.json +381 -0
- package/package.json +58 -0
- package/windsurf/README.md +254 -0
- package/windsurf/rules/cc.md +5 -0
- package/windsurf/workflows/create-adr.md +331 -0
- package/windsurf/workflows/create-spec.md +280 -0
- package/windsurf/workflows/edit-spec.md +273 -0
- package/windsurf/workflows/execute-task.md +276 -0
- package/windsurf/workflows/explain-code.md +292 -0
- package/windsurf/workflows/initialize.md +298 -0
- package/windsurf/workflows/new-command.md +321 -0
- package/windsurf/workflows/status.md +213 -0
|
@@ -0,0 +1,514 @@
|
|
|
1
|
+
# Execute Task Command (cc: execute-task)
|
|
2
|
+
|
|
3
|
+
## Overview
|
|
4
|
+
|
|
5
|
+
Execute a specific task and its sub-tasks systematically following a Test-Driven Development (TDD) workflow. This command reads task specifications from `.code-captain/specs/` directories and implements features with comprehensive testing, following established code standards and best practices.
|
|
6
|
+
|
|
7
|
+
## Usage
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
cc: execute-task
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
**Note:** This command automatically detects and lists available task specifications for selection, or executes a specific task if context is clear.
|
|
14
|
+
|
|
15
|
+
## CRITICAL REQUIREMENT: 100% Test Pass Rate
|
|
16
|
+
|
|
17
|
+
**⚠️ ZERO TOLERANCE FOR FAILING TESTS ⚠️**
|
|
18
|
+
|
|
19
|
+
This command enforces strict test validation:
|
|
20
|
+
- **NO story can be marked "COMPLETED" with ANY failing tests**
|
|
21
|
+
- **100% test pass rate is MANDATORY before completion**
|
|
22
|
+
- **"Edge case" or "minor" test failures are NOT acceptable**
|
|
23
|
+
- **Implementation is considered incomplete until all tests pass**
|
|
24
|
+
|
|
25
|
+
If tests fail, the story remains "IN PROGRESS" until all failures are resolved.
|
|
26
|
+
|
|
27
|
+
## Command Process
|
|
28
|
+
|
|
29
|
+
### Step 1: Task Discovery & Selection
|
|
30
|
+
|
|
31
|
+
**Scan for available specifications:**
|
|
32
|
+
|
|
33
|
+
- Search `.code-captain/specs/` for dated specification folders
|
|
34
|
+
- Load user stories from `user-stories/` folders in each spec
|
|
35
|
+
- Read `user-stories/README.md` for story overview and progress
|
|
36
|
+
- Parse individual `story-N-{name}.md` files for available tasks
|
|
37
|
+
- Present available stories and tasks organized by specification
|
|
38
|
+
|
|
39
|
+
**Create execution todo tracking:**
|
|
40
|
+
|
|
41
|
+
Use `todo_write` to track the execution process:
|
|
42
|
+
|
|
43
|
+
```json
|
|
44
|
+
{
|
|
45
|
+
"todos": [
|
|
46
|
+
{
|
|
47
|
+
"id": "task-discovery",
|
|
48
|
+
"content": "Discover and select task from available specifications",
|
|
49
|
+
"status": "in_progress"
|
|
50
|
+
},
|
|
51
|
+
{
|
|
52
|
+
"id": "context-gathering",
|
|
53
|
+
"content": "Gather context from spec documents and codebase analysis",
|
|
54
|
+
"status": "pending"
|
|
55
|
+
},
|
|
56
|
+
{
|
|
57
|
+
"id": "subtask-execution",
|
|
58
|
+
"content": "Execute all subtasks in TDD order",
|
|
59
|
+
"status": "pending"
|
|
60
|
+
},
|
|
61
|
+
{
|
|
62
|
+
"id": "test-verification",
|
|
63
|
+
"content": "Verify all task-specific tests pass",
|
|
64
|
+
"status": "pending"
|
|
65
|
+
},
|
|
66
|
+
{
|
|
67
|
+
"id": "task-completion",
|
|
68
|
+
"content": "Update task status and mark complete",
|
|
69
|
+
"status": "pending"
|
|
70
|
+
}
|
|
71
|
+
]
|
|
72
|
+
}
|
|
73
|
+
```
|
|
74
|
+
|
|
75
|
+
**Story selection process:**
|
|
76
|
+
|
|
77
|
+
1. **If multiple specs exist**: Present selection menu with spec dates and story summaries
|
|
78
|
+
2. **If single spec exists**: Show available stories and their tasks within that specification
|
|
79
|
+
3. **If story/task specified**: Validate story exists and select specific task for execution
|
|
80
|
+
4. **If no specs exist**: Guide user to run `cc: create-spec` first
|
|
81
|
+
|
|
82
|
+
**Selection format:**
|
|
83
|
+
```
|
|
84
|
+
Available specifications:
|
|
85
|
+
├── 2024-01-15-user-auth/ (3 stories, 12 total tasks)
|
|
86
|
+
│ ├── Story 1: User Registration (5 tasks) - Not Started
|
|
87
|
+
│ ├── Story 2: User Login (4 tasks) - Not Started
|
|
88
|
+
│ └── Story 3: Password Reset (3 tasks) - Not Started
|
|
89
|
+
└── 2024-01-20-payment-system/ (2 stories, 8 total tasks)
|
|
90
|
+
├── Story 1: Payment Processing (5 tasks) - In Progress (2/5)
|
|
91
|
+
└── Story 2: Refund Management (3 tasks) - Not Started
|
|
92
|
+
```
|
|
93
|
+
|
|
94
|
+
### Step 2: Context Gathering & Analysis
|
|
95
|
+
|
|
96
|
+
**Load specification context:**
|
|
97
|
+
|
|
98
|
+
- Read primary spec document: `spec.md`
|
|
99
|
+
- Load user stories overview: `user-stories/README.md`
|
|
100
|
+
- Read selected story file: `user-stories/story-N-{name}.md`
|
|
101
|
+
- Review technical specifications: `sub-specs/technical-spec.md`
|
|
102
|
+
- Parse task breakdown from individual story file
|
|
103
|
+
|
|
104
|
+
**Analyze current codebase:**
|
|
105
|
+
|
|
106
|
+
Use `codebase_search` to understand:
|
|
107
|
+
|
|
108
|
+
- Current architecture and patterns
|
|
109
|
+
- Related existing functionality
|
|
110
|
+
- Integration points for new features
|
|
111
|
+
- Testing frameworks and conventions
|
|
112
|
+
|
|
113
|
+
**Load project standards:**
|
|
114
|
+
|
|
115
|
+
- Code style guide: `.code-captain/docs/code-style.md`
|
|
116
|
+
- Technology stack: `.code-captain/docs/tech-stack.md`
|
|
117
|
+
- Best practices: `.code-captain/docs/best-practices.md`
|
|
118
|
+
|
|
119
|
+
### Step 3: Story & Task Analysis
|
|
120
|
+
|
|
121
|
+
**Parse selected story structure:**
|
|
122
|
+
|
|
123
|
+
- Load complete story file: `user-stories/story-N-{name}.md`
|
|
124
|
+
- Extract user story, acceptance criteria, and implementation tasks
|
|
125
|
+
- Analyze task dependencies and execution order within the story
|
|
126
|
+
- Understand test requirements (first task typically writes tests)
|
|
127
|
+
- Plan implementation approach based on story's task breakdown
|
|
128
|
+
|
|
129
|
+
**Validate TDD approach within story:**
|
|
130
|
+
|
|
131
|
+
- **First task**: Should write tests for the story functionality
|
|
132
|
+
- **Middle tasks**: Implement functionality to pass tests (max 5-7 tasks total)
|
|
133
|
+
- **Final task**: Verify all tests pass and acceptance criteria are met
|
|
134
|
+
- **Integration considerations**: Update adjacent/related tests as needed
|
|
135
|
+
|
|
136
|
+
**Example story structure verification:**
|
|
137
|
+
|
|
138
|
+
```markdown
|
|
139
|
+
# Story 1: User Authentication
|
|
140
|
+
|
|
141
|
+
## User Story
|
|
142
|
+
**As a** new user
|
|
143
|
+
**I want to** register with email and password
|
|
144
|
+
**So that** I can access personalized features
|
|
145
|
+
|
|
146
|
+
## Acceptance Criteria
|
|
147
|
+
- [ ] User can register with valid email/password
|
|
148
|
+
- [ ] Email validation prevents invalid formats
|
|
149
|
+
- [ ] Password meets security requirements
|
|
150
|
+
|
|
151
|
+
## Implementation Tasks
|
|
152
|
+
- [ ] 1.1 Write tests for authentication middleware
|
|
153
|
+
- [ ] 1.2 Implement JWT token generation
|
|
154
|
+
- [ ] 1.3 Create password hashing utilities
|
|
155
|
+
- [ ] 1.4 Build login/logout endpoints
|
|
156
|
+
- [ ] 1.5 Verify all tests pass and acceptance criteria met
|
|
157
|
+
```
|
|
158
|
+
|
|
159
|
+
### Step 4: Pre-Implementation Preparation
|
|
160
|
+
|
|
161
|
+
**Create execution tracking:**
|
|
162
|
+
|
|
163
|
+
Update todos to reflect specific story tasks:
|
|
164
|
+
|
|
165
|
+
```json
|
|
166
|
+
{
|
|
167
|
+
"todos": [
|
|
168
|
+
{
|
|
169
|
+
"id": "story-1-task-1",
|
|
170
|
+
"content": "1.1 Write tests for authentication middleware (Story 1: User Authentication)",
|
|
171
|
+
"status": "in_progress"
|
|
172
|
+
},
|
|
173
|
+
{
|
|
174
|
+
"id": "story-1-task-2",
|
|
175
|
+
"content": "1.2 Implement JWT token generation (Story 1: User Authentication)",
|
|
176
|
+
"status": "pending"
|
|
177
|
+
},
|
|
178
|
+
{
|
|
179
|
+
"id": "story-1-task-3",
|
|
180
|
+
"content": "1.3 Create password hashing utilities (Story 1: User Authentication)",
|
|
181
|
+
"status": "pending"
|
|
182
|
+
},
|
|
183
|
+
{
|
|
184
|
+
"id": "story-1-task-4",
|
|
185
|
+
"content": "1.4 Build login/logout endpoints (Story 1: User Authentication)",
|
|
186
|
+
"status": "pending"
|
|
187
|
+
},
|
|
188
|
+
{
|
|
189
|
+
"id": "story-1-task-5",
|
|
190
|
+
"content": "1.5 Verify all tests pass and acceptance criteria met (Story 1: User Authentication)",
|
|
191
|
+
"status": "pending"
|
|
192
|
+
}
|
|
193
|
+
]
|
|
194
|
+
}
|
|
195
|
+
```
|
|
196
|
+
|
|
197
|
+
**Validate testing setup:**
|
|
198
|
+
|
|
199
|
+
- Confirm testing framework is configured
|
|
200
|
+
- Verify test directories and naming conventions
|
|
201
|
+
- Check existing test patterns and utilities
|
|
202
|
+
- Ensure test runner is functional
|
|
203
|
+
|
|
204
|
+
### Step 5: Story Task Execution (TDD Workflow)
|
|
205
|
+
|
|
206
|
+
**Execute story tasks in sequential order:**
|
|
207
|
+
|
|
208
|
+
#### Task 1: Write Tests (Test-First Approach)
|
|
209
|
+
|
|
210
|
+
**Actions:**
|
|
211
|
+
|
|
212
|
+
- Write comprehensive test cases for the entire feature
|
|
213
|
+
- Include unit tests, integration tests, and edge cases
|
|
214
|
+
- Cover happy path, error conditions, and boundary cases
|
|
215
|
+
- Ensure tests fail appropriately (red phase)
|
|
216
|
+
|
|
217
|
+
**Test categories to include:**
|
|
218
|
+
|
|
219
|
+
- **Unit tests**: Individual function/method testing
|
|
220
|
+
- **Integration tests**: Component interaction testing
|
|
221
|
+
- **Edge cases**: Boundary conditions and error scenarios
|
|
222
|
+
- **Acceptance tests**: User story validation
|
|
223
|
+
|
|
224
|
+
#### Tasks 2-N: Implementation (Green Phase)
|
|
225
|
+
|
|
226
|
+
**For each implementation task within the story:**
|
|
227
|
+
|
|
228
|
+
1. **Focus on specific functionality**: Implement only what's needed for current task
|
|
229
|
+
2. **Make tests pass**: Write minimal code to satisfy failing tests
|
|
230
|
+
3. **Update related tests**: Modify adjacent tests if behavior changes
|
|
231
|
+
4. **Maintain compatibility**: Ensure no regressions in existing functionality
|
|
232
|
+
5. **Refactor when green**: Improve code quality while tests remain passing
|
|
233
|
+
|
|
234
|
+
**Implementation approach:**
|
|
235
|
+
|
|
236
|
+
- Start with simplest implementation that passes tests
|
|
237
|
+
- Add complexity incrementally as required by test cases
|
|
238
|
+
- Keep tests passing at each step
|
|
239
|
+
- Refactor for clarity and maintainability
|
|
240
|
+
|
|
241
|
+
#### Final Task: Test & Acceptance Verification
|
|
242
|
+
|
|
243
|
+
**CRITICAL: 100% Test Pass Rate Required**
|
|
244
|
+
|
|
245
|
+
**Mandatory Actions (ALL must succeed before story completion):**
|
|
246
|
+
|
|
247
|
+
1. **Run complete test suite for this story**
|
|
248
|
+
2. **Achieve 100% pass rate for ALL tests** - NO EXCEPTIONS
|
|
249
|
+
3. **Verify no regressions in existing test suites**
|
|
250
|
+
4. **Validate all acceptance criteria are met for the user story**
|
|
251
|
+
5. **Confirm story delivers the specified user value**
|
|
252
|
+
|
|
253
|
+
**⚠️ STORY CANNOT BE MARKED COMPLETE WITH ANY FAILING TESTS ⚠️**
|
|
254
|
+
|
|
255
|
+
If ANY tests fail:
|
|
256
|
+
- **STOP IMMEDIATELY** - Do not mark story as complete
|
|
257
|
+
- Debug and fix each failing test
|
|
258
|
+
- Re-run test suite until 100% pass rate achieved
|
|
259
|
+
- Only then proceed to mark story as complete
|
|
260
|
+
|
|
261
|
+
### Step 6: Story-Specific Test Validation
|
|
262
|
+
|
|
263
|
+
**Run targeted test validation:**
|
|
264
|
+
|
|
265
|
+
Use available testing tools to verify:
|
|
266
|
+
|
|
267
|
+
- All tests written in first task are passing
|
|
268
|
+
- New functionality works as specified in user story
|
|
269
|
+
- All acceptance criteria are satisfied
|
|
270
|
+
- No regressions introduced to existing features
|
|
271
|
+
- Performance requirements are met (if specified)
|
|
272
|
+
|
|
273
|
+
**Test execution strategy:**
|
|
274
|
+
|
|
275
|
+
- **First**: Run only tests for current story/feature
|
|
276
|
+
- **Then**: Run related test suites to check for regressions
|
|
277
|
+
- **Finally**: Consider full test suite if significant changes made
|
|
278
|
+
- **Acceptance**: Validate user story acceptance criteria are met
|
|
279
|
+
|
|
280
|
+
**Failure handling:**
|
|
281
|
+
|
|
282
|
+
**ZERO TOLERANCE FOR FAILING TESTS:**
|
|
283
|
+
- **If ANY tests fail**: Story CANNOT be marked complete
|
|
284
|
+
- **Required action**: Debug and fix ALL failing tests before proceeding
|
|
285
|
+
- **No exceptions**: "Edge case" or "minor" failing tests are NOT acceptable
|
|
286
|
+
- **If performance issues**: Optimize implementation until all tests pass
|
|
287
|
+
- **If regressions found**: Fix regressions - story completion is blocked until resolved
|
|
288
|
+
|
|
289
|
+
**Failure Resolution Process:**
|
|
290
|
+
1. Identify root cause of each failing test
|
|
291
|
+
2. Fix implementation to make test pass
|
|
292
|
+
3. Re-run ALL tests to ensure 100% pass rate
|
|
293
|
+
4. Repeat until NO tests fail
|
|
294
|
+
5. Only then mark story as complete
|
|
295
|
+
|
|
296
|
+
### Step 7: Story Completion & Status Updates
|
|
297
|
+
|
|
298
|
+
**Update story file status:**
|
|
299
|
+
|
|
300
|
+
Mark completed tasks in the individual story file (`user-stories/story-N-{name}.md`):
|
|
301
|
+
|
|
302
|
+
```markdown
|
|
303
|
+
# Story 1: User Authentication
|
|
304
|
+
|
|
305
|
+
> **Status:** Completed ✅
|
|
306
|
+
> **Priority:** High
|
|
307
|
+
> **Dependencies:** None
|
|
308
|
+
|
|
309
|
+
## User Story
|
|
310
|
+
**As a** new user
|
|
311
|
+
**I want to** register with email and password
|
|
312
|
+
**So that** I can access personalized features
|
|
313
|
+
|
|
314
|
+
## Acceptance Criteria
|
|
315
|
+
- [x] User can register with valid email/password ✅
|
|
316
|
+
- [x] Email validation prevents invalid formats ✅
|
|
317
|
+
- [x] Password meets security requirements ✅
|
|
318
|
+
|
|
319
|
+
## Implementation Tasks
|
|
320
|
+
- [x] 1.1 Write tests for authentication middleware ✅
|
|
321
|
+
- [x] 1.2 Implement JWT token generation ✅
|
|
322
|
+
- [x] 1.3 Create password hashing utilities ✅
|
|
323
|
+
- [x] 1.4 Build login/logout endpoints ✅
|
|
324
|
+
- [x] 1.5 Verify all tests pass and acceptance criteria met ✅
|
|
325
|
+
|
|
326
|
+
## Definition of Done
|
|
327
|
+
- [x] All tasks completed ✅
|
|
328
|
+
- [x] All acceptance criteria met ✅
|
|
329
|
+
- [x] **ALL tests passing (100% pass rate)** ✅ **MANDATORY**
|
|
330
|
+
- [x] Code reviewed ✅
|
|
331
|
+
- [x] Documentation updated ✅
|
|
332
|
+
|
|
333
|
+
**NOTE:** Story CANNOT be marked complete without 100% test pass rate
|
|
334
|
+
```
|
|
335
|
+
|
|
336
|
+
**Update stories overview:**
|
|
337
|
+
|
|
338
|
+
Update progress tracking in `user-stories/README.md`:
|
|
339
|
+
|
|
340
|
+
```markdown
|
|
341
|
+
| Story | Title | Status | Tasks | Progress |
|
|
342
|
+
|-------|-------|--------|-------|----------|
|
|
343
|
+
| 1 | User Authentication | Completed ✅ | 5 | 5/5 ✅ |
|
|
344
|
+
| 2 | Password Reset | Not Started | 4 | 0/4 |
|
|
345
|
+
| 3 | Profile Management | Not Started | 6 | 0/6 |
|
|
346
|
+
|
|
347
|
+
**Total Progress:** 5/15 tasks (33%)
|
|
348
|
+
```
|
|
349
|
+
|
|
350
|
+
**Document completion:**
|
|
351
|
+
|
|
352
|
+
- Update spec status if all stories in the specification are complete
|
|
353
|
+
- Note any deviations from original plan in story notes
|
|
354
|
+
- Document lessons learned or improvements made
|
|
355
|
+
- Identify any follow-up tasks or technical debt
|
|
356
|
+
|
|
357
|
+
**Present completion summary:**
|
|
358
|
+
|
|
359
|
+
**ONLY present if ALL tests pass (100% pass rate):**
|
|
360
|
+
|
|
361
|
+
```
|
|
362
|
+
Story completed successfully:
|
|
363
|
+
|
|
364
|
+
**Story:** Story 1: User Authentication
|
|
365
|
+
**Tasks completed:** 5/5 ✅
|
|
366
|
+
**Acceptance criteria met:** 3/3 ✅
|
|
367
|
+
**Tests written:** 12 test cases
|
|
368
|
+
**Tests passing:** 12/12 (100%) ✅ REQUIRED FOR COMPLETION
|
|
369
|
+
**Files modified:** 6 files
|
|
370
|
+
**User value delivered:** New users can register with email/password and access personalized features
|
|
371
|
+
|
|
372
|
+
Current specification progress: 5/15 tasks (33%)
|
|
373
|
+
|
|
374
|
+
Next available stories:
|
|
375
|
+
- Story 2: Password Reset (4 tasks) - Not Started
|
|
376
|
+
- Story 3: Profile Management (6 tasks) - Not Started
|
|
377
|
+
|
|
378
|
+
Would you like to proceed with the next story?
|
|
379
|
+
```
|
|
380
|
+
|
|
381
|
+
**If ANY tests fail, present this instead:**
|
|
382
|
+
|
|
383
|
+
```
|
|
384
|
+
Story implementation INCOMPLETE - Tests failing:
|
|
385
|
+
|
|
386
|
+
**Story:** Story 1: User Authentication
|
|
387
|
+
**Tasks completed:** 5/5 (implementation done, but validation failed)
|
|
388
|
+
**Tests written:** 12 test cases
|
|
389
|
+
**Tests passing:** 10/12 (83%) ❌ COMPLETION BLOCKED
|
|
390
|
+
**Failing tests:** 2 tests must be fixed before story completion
|
|
391
|
+
**Status:** IN PROGRESS - Cannot mark complete until 100% test pass rate
|
|
392
|
+
|
|
393
|
+
REQUIRED ACTIONS:
|
|
394
|
+
1. Debug and fix all failing tests
|
|
395
|
+
2. Re-run test suite to achieve 100% pass rate
|
|
396
|
+
3. Only then mark story as complete
|
|
397
|
+
```
|
|
398
|
+
|
|
399
|
+
## Tool Integration
|
|
400
|
+
|
|
401
|
+
**Primary Code Captain tools:**
|
|
402
|
+
|
|
403
|
+
- `todo_write` - Progress tracking throughout execution
|
|
404
|
+
- `codebase_search` - Understanding existing architecture and patterns
|
|
405
|
+
- `file_search` - Locating relevant specifications and test files
|
|
406
|
+
- `read_file` - Loading spec documents and existing code
|
|
407
|
+
- `search_replace` / `MultiEdit` - Implementing code changes
|
|
408
|
+
- `run_terminal_cmd` - Executing tests and build processes
|
|
409
|
+
|
|
410
|
+
**Parallel execution opportunities:**
|
|
411
|
+
|
|
412
|
+
- Context gathering (multiple spec files, codebase analysis)
|
|
413
|
+
- Test file analysis (existing patterns, framework configuration)
|
|
414
|
+
- Implementation validation (running tests, checking integration)
|
|
415
|
+
|
|
416
|
+
## Integration with Code Captain Ecosystem
|
|
417
|
+
|
|
418
|
+
**Specification dependency:**
|
|
419
|
+
|
|
420
|
+
- Requires existing spec created by `cc: create-spec`
|
|
421
|
+
- Uses story breakdown from `user-stories/` folder in spec directories
|
|
422
|
+
- Loads individual story files: `user-stories/story-N-{name}.md`
|
|
423
|
+
- Tracks progress in `user-stories/README.md`
|
|
424
|
+
- Follows technical approach from `sub-specs/technical-spec.md`
|
|
425
|
+
|
|
426
|
+
**Code style compliance:**
|
|
427
|
+
|
|
428
|
+
- Adheres to patterns in `.code-captain/docs/code-style.md`
|
|
429
|
+
- Uses technology stack from `.code-captain/docs/tech-stack.md`
|
|
430
|
+
- Follows best practices from `.code-captain/docs/best-practices.md`
|
|
431
|
+
|
|
432
|
+
**Cross-command integration:**
|
|
433
|
+
|
|
434
|
+
- Complements `cc: create-spec` for complete development workflow
|
|
435
|
+
- Can trigger `cc: research` if unknown technologies encountered
|
|
436
|
+
- Integrates with testing and validation workflows
|
|
437
|
+
|
|
438
|
+
## Quality Standards
|
|
439
|
+
|
|
440
|
+
**Test-Driven Development:**
|
|
441
|
+
|
|
442
|
+
- Tests written before implementation
|
|
443
|
+
- **100% test pass rate MANDATORY before task completion**
|
|
444
|
+
- **ZERO TOLERANCE for failing tests - no story completion with any failures**
|
|
445
|
+
- Comprehensive coverage including edge cases
|
|
446
|
+
- Regression testing for existing functionality
|
|
447
|
+
- Failed tests = incomplete implementation that must be fixed
|
|
448
|
+
|
|
449
|
+
**Code quality requirements:**
|
|
450
|
+
|
|
451
|
+
- Follows established project patterns and conventions
|
|
452
|
+
- Maintains backward compatibility unless specified otherwise
|
|
453
|
+
- Implements proper error handling and validation
|
|
454
|
+
- Includes appropriate logging and monitoring
|
|
455
|
+
|
|
456
|
+
**Documentation standards:**
|
|
457
|
+
|
|
458
|
+
- Code changes include appropriate comments
|
|
459
|
+
- Complex logic is documented inline
|
|
460
|
+
- API changes are reflected in technical specifications
|
|
461
|
+
- Task completion updates specification status
|
|
462
|
+
|
|
463
|
+
## Error Handling & Recovery
|
|
464
|
+
|
|
465
|
+
**Common failure scenarios:**
|
|
466
|
+
|
|
467
|
+
- **No specifications found**: Guide to `cc: create-spec`
|
|
468
|
+
- **Test framework issues**: Provide setup guidance
|
|
469
|
+
- **Implementation conflicts**: Suggest conflict resolution
|
|
470
|
+
- **Performance issues**: Recommend optimization approaches
|
|
471
|
+
|
|
472
|
+
**Blocking issue management:**
|
|
473
|
+
|
|
474
|
+
If blocked by technical issues:
|
|
475
|
+
|
|
476
|
+
```markdown
|
|
477
|
+
- [ ] N.X Task description ⚠️ Blocking issue: [DESCRIPTION]
|
|
478
|
+
```
|
|
479
|
+
|
|
480
|
+
Update story status and notes section to document the blocking issue.
|
|
481
|
+
|
|
482
|
+
**Resolution strategies:**
|
|
483
|
+
|
|
484
|
+
1. Try alternative implementation approach
|
|
485
|
+
2. Research solution using `cc: research`
|
|
486
|
+
3. Break down task into smaller components
|
|
487
|
+
4. Maximum 3 attempts before escalating or documenting as blocked
|
|
488
|
+
|
|
489
|
+
## Best Practices
|
|
490
|
+
|
|
491
|
+
**TDD adherence:**
|
|
492
|
+
|
|
493
|
+
- Always start with failing tests
|
|
494
|
+
- Implement minimal code to pass tests
|
|
495
|
+
- Refactor only when tests are green
|
|
496
|
+
- **MANDATORY: 100% test pass rate before story completion**
|
|
497
|
+
- **NO EXCEPTIONS: Failing tests = incomplete story**
|
|
498
|
+
|
|
499
|
+
**Incremental development:**
|
|
500
|
+
|
|
501
|
+
- Complete story tasks sequentially
|
|
502
|
+
- Verify functionality at each step
|
|
503
|
+
- Commit working code frequently
|
|
504
|
+
- Test integration points early
|
|
505
|
+
- Validate acceptance criteria incrementally
|
|
506
|
+
|
|
507
|
+
**Communication:**
|
|
508
|
+
|
|
509
|
+
- Update story file status immediately after task completion
|
|
510
|
+
- Update README.md progress tracking after story completion
|
|
511
|
+
- Document any deviations from specification in story notes
|
|
512
|
+
- Note technical decisions and rationale in story file
|
|
513
|
+
- Highlight areas requiring future attention
|
|
514
|
+
- Ensure user value is clearly demonstrated upon story completion
|