knowzcode 0.3.7 → 0.4.0
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/.claude-plugin/marketplace.json +61 -61
- package/.claude-plugin/plugin.json +8 -8
- package/LICENSE +121 -121
- package/README.md +354 -320
- package/agents/analyst.md +114 -114
- package/agents/architect.md +200 -200
- package/agents/builder.md +104 -104
- package/agents/closer.md +177 -177
- package/agents/context-scout.md +54 -54
- package/agents/knowledge-migrator.md +349 -349
- package/agents/knowz-scout.md +83 -83
- package/agents/knowz-scribe.md +180 -180
- package/agents/microfix-specialist.md +135 -135
- package/agents/project-advisor.md +111 -111
- package/agents/reviewer.md +172 -172
- package/agents/security-officer.md +194 -194
- package/agents/test-advisor.md +162 -162
- package/agents/update-coordinator.md +394 -394
- package/bin/knowzcode.mjs +1199 -956
- package/commands/audit.md +328 -328
- package/commands/connect-mcp.md +549 -549
- package/commands/fix.md +107 -107
- package/commands/init.md +500 -439
- package/commands/learn.md +332 -332
- package/commands/plan.md +272 -272
- package/commands/register.md +733 -733
- package/commands/status.md +309 -309
- package/commands/telemetry-setup.md +368 -368
- package/commands/telemetry.md +188 -188
- package/commands/work.md +1204 -1202
- package/knowzcode/automation_manifest.md +59 -59
- package/knowzcode/claude_code_execution.md +431 -420
- package/knowzcode/copilot_execution.md +231 -231
- package/knowzcode/enterprise/compliance_manifest.md +137 -137
- package/knowzcode/enterprise/compliance_status.md +30 -30
- package/knowzcode/enterprise/guidelines/code-quality.md +67 -67
- package/knowzcode/enterprise/guidelines/security.md +355 -355
- package/knowzcode/enterprise/templates/guideline-template.md +55 -55
- package/knowzcode/gitignore.template +13 -13
- package/knowzcode/knowzcode_architecture.md +51 -51
- package/knowzcode/knowzcode_log.md +142 -142
- package/knowzcode/knowzcode_loop.md +596 -596
- package/knowzcode/knowzcode_orchestration.md +66 -66
- package/knowzcode/knowzcode_project.md +48 -48
- package/knowzcode/knowzcode_tracker.md +40 -40
- package/knowzcode/knowzcode_vaults.md +257 -257
- package/knowzcode/mcp_config.md +191 -191
- package/knowzcode/planning/Readme.md +6 -6
- package/knowzcode/platform_adapters.md +1260 -1047
- package/knowzcode/prompts/Execute_Micro_Fix.md +57 -57
- package/knowzcode/prompts/Investigate_Codebase.md +227 -227
- package/knowzcode/prompts/Migrate_Knowledge.md +301 -301
- package/knowzcode/prompts/Refactor_Node.md +72 -72
- package/knowzcode/prompts/Spec_Verification_Checkpoint.md +59 -59
- package/knowzcode/prompts/[LOOP_1A]__Propose_Change_Set.md +52 -52
- package/knowzcode/prompts/[LOOP_1B]__Draft_Specs.md +75 -75
- package/knowzcode/prompts/[LOOP_2A]__Implement_Change_Set.md +55 -55
- package/knowzcode/prompts/[LOOP_2B]__Verify_Implementation.md +72 -72
- package/knowzcode/prompts/[LOOP_3]__Finalize_And_Commit.md +67 -67
- package/knowzcode/specs/Readme.md +10 -10
- package/knowzcode/telemetry_config.md +89 -89
- package/knowzcode/user_preferences.md +120 -120
- package/package.json +53 -53
- package/skills/alias-resolver.json +1 -1
- package/skills/architecture-diff.json +1 -1
- package/skills/check-installation-status.json +1 -1
- package/skills/continue.md +126 -126
- package/skills/environment-guard.json +1 -1
- package/skills/generate-workgroup-id.json +1 -1
- package/skills/install-knowzcode.json +1 -1
- package/skills/load-core-context.json +1 -1
- package/skills/log-entry-builder.json +1 -1
- package/skills/spec-quality-check.json +1 -1
- package/skills/spec-template.json +1 -1
- package/skills/spec-validator.json +1 -1
- package/skills/start-work.md +224 -224
- package/skills/tracker-scan.json +1 -1
- package/skills/tracker-update.json +1 -1
- package/skills/validate-installation.json +1 -1
|
@@ -1,120 +1,120 @@
|
|
|
1
|
-
# User Development Preferences
|
|
2
|
-
|
|
3
|
-
---
|
|
4
|
-
|
|
5
|
-
**Purpose:** This document captures your personal development preferences and coding standards. These preferences integrate with KnowzCode's workflow while respecting your style and approach.
|
|
6
|
-
|
|
7
|
-
**Last Updated:** [ISO timestamp - to be filled during init]
|
|
8
|
-
**Source:** User-provided during initialization
|
|
9
|
-
|
|
10
|
-
---
|
|
11
|
-
|
|
12
|
-
## Core Principles
|
|
13
|
-
|
|
14
|
-
[User-provided principles, or "Not configured"]
|
|
15
|
-
|
|
16
|
-
*Examples:*
|
|
17
|
-
- Test-Driven Development (TDD mandatory)
|
|
18
|
-
- Immutable data structures preferred
|
|
19
|
-
- Functional programming patterns
|
|
20
|
-
- Domain-Driven Design (DDD)
|
|
21
|
-
- SOLID principles
|
|
22
|
-
|
|
23
|
-
---
|
|
24
|
-
|
|
25
|
-
## Testing Approach
|
|
26
|
-
|
|
27
|
-
[User-provided testing preferences, or "Follows KnowzCode TDD requirements"]
|
|
28
|
-
|
|
29
|
-
*Examples:*
|
|
30
|
-
- **Framework:** XUnit / Jest / PyTest / Playwright
|
|
31
|
-
- **Style:** Behavior-driven / Unit-first / Integration-focused
|
|
32
|
-
- **Coverage:** Minimum 80% / All public APIs / Critical paths only
|
|
33
|
-
- **Patterns:** AAA (Arrange-Act-Assert) / Given-When-Then
|
|
34
|
-
- **Mocking:** Moq / Jest mocks / unittest.mock
|
|
35
|
-
|
|
36
|
-
---
|
|
37
|
-
|
|
38
|
-
## Code Style
|
|
39
|
-
|
|
40
|
-
[User-provided style preferences, or "Standard for language/framework"]
|
|
41
|
-
|
|
42
|
-
*Examples:*
|
|
43
|
-
- **Naming:** PascalCase for methods, camelCase for variables
|
|
44
|
-
- **Structure:** Small functions (max 20 lines), single responsibility
|
|
45
|
-
- **Comments:** Self-documenting code, minimal comments
|
|
46
|
-
- **Formatting:** Prettier / Black / Standard formatter
|
|
47
|
-
- **Linting:** ESLint / Flake8 / Custom rules
|
|
48
|
-
|
|
49
|
-
---
|
|
50
|
-
|
|
51
|
-
## Language-Specific Patterns
|
|
52
|
-
|
|
53
|
-
[User-provided language-specific preferences, or "N/A"]
|
|
54
|
-
|
|
55
|
-
*Examples (C#):*
|
|
56
|
-
- Nullable reference types always enabled
|
|
57
|
-
- Records for immutable DTOs
|
|
58
|
-
- No null-suppression operators
|
|
59
|
-
- FluentValidation for schema validation
|
|
60
|
-
|
|
61
|
-
*Examples (JavaScript/TypeScript):*
|
|
62
|
-
- Strict TypeScript mode
|
|
63
|
-
- Functional components with hooks (React)
|
|
64
|
-
- Async/await over promises
|
|
65
|
-
- ESM imports
|
|
66
|
-
|
|
67
|
-
*Examples (Python):*
|
|
68
|
-
- Type hints for all public functions
|
|
69
|
-
- Dataclasses for structured data
|
|
70
|
-
- f-strings for formatting
|
|
71
|
-
- PEP 8 compliance
|
|
72
|
-
|
|
73
|
-
---
|
|
74
|
-
|
|
75
|
-
## Quality Priorities
|
|
76
|
-
|
|
77
|
-
[User-provided quality focus areas, or "Standard KnowzCode priorities"]
|
|
78
|
-
|
|
79
|
-
*Rank your top priorities (1-5):*
|
|
80
|
-
1. [e.g., Reliability / Security / Performance / Maintainability / Testability]
|
|
81
|
-
2. [...]
|
|
82
|
-
3. [...]
|
|
83
|
-
4. [...]
|
|
84
|
-
5. [...]
|
|
85
|
-
|
|
86
|
-
---
|
|
87
|
-
|
|
88
|
-
## Project-Specific Conventions
|
|
89
|
-
|
|
90
|
-
[Any project-specific rules or patterns, or "See project CLAUDE.md"]
|
|
91
|
-
|
|
92
|
-
*Examples:*
|
|
93
|
-
- Database migrations must be reviewed before merge
|
|
94
|
-
- All API endpoints require OpenAPI documentation
|
|
95
|
-
- Error handling uses Result types (no exceptions)
|
|
96
|
-
- Logging format: structured JSON with correlation IDs
|
|
97
|
-
|
|
98
|
-
---
|
|
99
|
-
|
|
100
|
-
## Integration with KnowzCode
|
|
101
|
-
|
|
102
|
-
**Non-Negotiable (KnowzCode Framework):**
|
|
103
|
-
- Test-Driven Development (TDD) is mandatory
|
|
104
|
-
- Quality gates must pass at each phase
|
|
105
|
-
- Living documentation must be maintained
|
|
106
|
-
- Incremental verified progress required
|
|
107
|
-
|
|
108
|
-
**Flexible (Your Preferences):**
|
|
109
|
-
- Testing framework choice (as long as TDD followed)
|
|
110
|
-
- Code style and naming conventions
|
|
111
|
-
- Language-specific patterns
|
|
112
|
-
- Quality priority ranking
|
|
113
|
-
- Project-specific conventions
|
|
114
|
-
|
|
115
|
-
**Conflict Resolution:**
|
|
116
|
-
When your preferences conflict with KnowzCode requirements, the framework takes precedence for workflow aspects (TDD, quality gates), but your preferences apply for implementation style (naming, patterns, tools).
|
|
117
|
-
|
|
118
|
-
---
|
|
119
|
-
|
|
120
|
-
*This document should be reviewed and updated as project conventions evolve.*
|
|
1
|
+
# User Development Preferences
|
|
2
|
+
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
**Purpose:** This document captures your personal development preferences and coding standards. These preferences integrate with KnowzCode's workflow while respecting your style and approach.
|
|
6
|
+
|
|
7
|
+
**Last Updated:** [ISO timestamp - to be filled during init]
|
|
8
|
+
**Source:** User-provided during initialization
|
|
9
|
+
|
|
10
|
+
---
|
|
11
|
+
|
|
12
|
+
## Core Principles
|
|
13
|
+
|
|
14
|
+
[User-provided principles, or "Not configured"]
|
|
15
|
+
|
|
16
|
+
*Examples:*
|
|
17
|
+
- Test-Driven Development (TDD mandatory)
|
|
18
|
+
- Immutable data structures preferred
|
|
19
|
+
- Functional programming patterns
|
|
20
|
+
- Domain-Driven Design (DDD)
|
|
21
|
+
- SOLID principles
|
|
22
|
+
|
|
23
|
+
---
|
|
24
|
+
|
|
25
|
+
## Testing Approach
|
|
26
|
+
|
|
27
|
+
[User-provided testing preferences, or "Follows KnowzCode TDD requirements"]
|
|
28
|
+
|
|
29
|
+
*Examples:*
|
|
30
|
+
- **Framework:** XUnit / Jest / PyTest / Playwright
|
|
31
|
+
- **Style:** Behavior-driven / Unit-first / Integration-focused
|
|
32
|
+
- **Coverage:** Minimum 80% / All public APIs / Critical paths only
|
|
33
|
+
- **Patterns:** AAA (Arrange-Act-Assert) / Given-When-Then
|
|
34
|
+
- **Mocking:** Moq / Jest mocks / unittest.mock
|
|
35
|
+
|
|
36
|
+
---
|
|
37
|
+
|
|
38
|
+
## Code Style
|
|
39
|
+
|
|
40
|
+
[User-provided style preferences, or "Standard for language/framework"]
|
|
41
|
+
|
|
42
|
+
*Examples:*
|
|
43
|
+
- **Naming:** PascalCase for methods, camelCase for variables
|
|
44
|
+
- **Structure:** Small functions (max 20 lines), single responsibility
|
|
45
|
+
- **Comments:** Self-documenting code, minimal comments
|
|
46
|
+
- **Formatting:** Prettier / Black / Standard formatter
|
|
47
|
+
- **Linting:** ESLint / Flake8 / Custom rules
|
|
48
|
+
|
|
49
|
+
---
|
|
50
|
+
|
|
51
|
+
## Language-Specific Patterns
|
|
52
|
+
|
|
53
|
+
[User-provided language-specific preferences, or "N/A"]
|
|
54
|
+
|
|
55
|
+
*Examples (C#):*
|
|
56
|
+
- Nullable reference types always enabled
|
|
57
|
+
- Records for immutable DTOs
|
|
58
|
+
- No null-suppression operators
|
|
59
|
+
- FluentValidation for schema validation
|
|
60
|
+
|
|
61
|
+
*Examples (JavaScript/TypeScript):*
|
|
62
|
+
- Strict TypeScript mode
|
|
63
|
+
- Functional components with hooks (React)
|
|
64
|
+
- Async/await over promises
|
|
65
|
+
- ESM imports
|
|
66
|
+
|
|
67
|
+
*Examples (Python):*
|
|
68
|
+
- Type hints for all public functions
|
|
69
|
+
- Dataclasses for structured data
|
|
70
|
+
- f-strings for formatting
|
|
71
|
+
- PEP 8 compliance
|
|
72
|
+
|
|
73
|
+
---
|
|
74
|
+
|
|
75
|
+
## Quality Priorities
|
|
76
|
+
|
|
77
|
+
[User-provided quality focus areas, or "Standard KnowzCode priorities"]
|
|
78
|
+
|
|
79
|
+
*Rank your top priorities (1-5):*
|
|
80
|
+
1. [e.g., Reliability / Security / Performance / Maintainability / Testability]
|
|
81
|
+
2. [...]
|
|
82
|
+
3. [...]
|
|
83
|
+
4. [...]
|
|
84
|
+
5. [...]
|
|
85
|
+
|
|
86
|
+
---
|
|
87
|
+
|
|
88
|
+
## Project-Specific Conventions
|
|
89
|
+
|
|
90
|
+
[Any project-specific rules or patterns, or "See project CLAUDE.md"]
|
|
91
|
+
|
|
92
|
+
*Examples:*
|
|
93
|
+
- Database migrations must be reviewed before merge
|
|
94
|
+
- All API endpoints require OpenAPI documentation
|
|
95
|
+
- Error handling uses Result types (no exceptions)
|
|
96
|
+
- Logging format: structured JSON with correlation IDs
|
|
97
|
+
|
|
98
|
+
---
|
|
99
|
+
|
|
100
|
+
## Integration with KnowzCode
|
|
101
|
+
|
|
102
|
+
**Non-Negotiable (KnowzCode Framework):**
|
|
103
|
+
- Test-Driven Development (TDD) is mandatory
|
|
104
|
+
- Quality gates must pass at each phase
|
|
105
|
+
- Living documentation must be maintained
|
|
106
|
+
- Incremental verified progress required
|
|
107
|
+
|
|
108
|
+
**Flexible (Your Preferences):**
|
|
109
|
+
- Testing framework choice (as long as TDD followed)
|
|
110
|
+
- Code style and naming conventions
|
|
111
|
+
- Language-specific patterns
|
|
112
|
+
- Quality priority ranking
|
|
113
|
+
- Project-specific conventions
|
|
114
|
+
|
|
115
|
+
**Conflict Resolution:**
|
|
116
|
+
When your preferences conflict with KnowzCode requirements, the framework takes precedence for workflow aspects (TDD, quality gates), but your preferences apply for implementation style (naming, patterns, tools).
|
|
117
|
+
|
|
118
|
+
---
|
|
119
|
+
|
|
120
|
+
*This document should be reviewed and updated as project conventions evolve.*
|
package/package.json
CHANGED
|
@@ -1,53 +1,53 @@
|
|
|
1
|
-
{
|
|
2
|
-
"name": "knowzcode",
|
|
3
|
-
"version": "0.
|
|
4
|
-
"description": "Platform-agnostic AI development methodology with TDD, quality gates, and structured workflows",
|
|
5
|
-
"type": "module",
|
|
6
|
-
"bin": {
|
|
7
|
-
"knowzcode": "./bin/knowzcode.mjs"
|
|
8
|
-
},
|
|
9
|
-
"files": [
|
|
10
|
-
"bin/",
|
|
11
|
-
"knowzcode/",
|
|
12
|
-
"agents/",
|
|
13
|
-
"commands/",
|
|
14
|
-
"skills/",
|
|
15
|
-
".claude-plugin/"
|
|
16
|
-
],
|
|
17
|
-
"scripts": {
|
|
18
|
-
"prepublishOnly": "node bin/knowzcode.mjs --version"
|
|
19
|
-
},
|
|
20
|
-
"keywords": [
|
|
21
|
-
"ai",
|
|
22
|
-
"tdd",
|
|
23
|
-
"workflow",
|
|
24
|
-
"methodology",
|
|
25
|
-
"quality-gates",
|
|
26
|
-
"platform-agnostic",
|
|
27
|
-
"claude",
|
|
28
|
-
"codex",
|
|
29
|
-
"gemini",
|
|
30
|
-
"cursor",
|
|
31
|
-
"copilot",
|
|
32
|
-
"windsurf",
|
|
33
|
-
"development"
|
|
34
|
-
],
|
|
35
|
-
"author": {
|
|
36
|
-
"name": "Alex Headscarf"
|
|
37
|
-
},
|
|
38
|
-
"homepage": "https://github.com/knowz-io/knowzcode",
|
|
39
|
-
"bugs": {
|
|
40
|
-
"url": "https://github.com/knowz-io/knowzcode/issues"
|
|
41
|
-
},
|
|
42
|
-
"repository": {
|
|
43
|
-
"type": "git",
|
|
44
|
-
"url": "git+https://github.com/knowz-io/knowzcode.git"
|
|
45
|
-
},
|
|
46
|
-
"publishConfig": {
|
|
47
|
-
"access": "public"
|
|
48
|
-
},
|
|
49
|
-
"license": "MIT",
|
|
50
|
-
"engines": {
|
|
51
|
-
"node": ">=18"
|
|
52
|
-
}
|
|
53
|
-
}
|
|
1
|
+
{
|
|
2
|
+
"name": "knowzcode",
|
|
3
|
+
"version": "0.4.0",
|
|
4
|
+
"description": "Platform-agnostic AI development methodology with TDD, quality gates, and structured workflows",
|
|
5
|
+
"type": "module",
|
|
6
|
+
"bin": {
|
|
7
|
+
"knowzcode": "./bin/knowzcode.mjs"
|
|
8
|
+
},
|
|
9
|
+
"files": [
|
|
10
|
+
"bin/",
|
|
11
|
+
"knowzcode/",
|
|
12
|
+
"agents/",
|
|
13
|
+
"commands/",
|
|
14
|
+
"skills/",
|
|
15
|
+
".claude-plugin/"
|
|
16
|
+
],
|
|
17
|
+
"scripts": {
|
|
18
|
+
"prepublishOnly": "node bin/knowzcode.mjs --version"
|
|
19
|
+
},
|
|
20
|
+
"keywords": [
|
|
21
|
+
"ai",
|
|
22
|
+
"tdd",
|
|
23
|
+
"workflow",
|
|
24
|
+
"methodology",
|
|
25
|
+
"quality-gates",
|
|
26
|
+
"platform-agnostic",
|
|
27
|
+
"claude",
|
|
28
|
+
"codex",
|
|
29
|
+
"gemini",
|
|
30
|
+
"cursor",
|
|
31
|
+
"copilot",
|
|
32
|
+
"windsurf",
|
|
33
|
+
"development"
|
|
34
|
+
],
|
|
35
|
+
"author": {
|
|
36
|
+
"name": "Alex Headscarf"
|
|
37
|
+
},
|
|
38
|
+
"homepage": "https://github.com/knowz-io/knowzcode",
|
|
39
|
+
"bugs": {
|
|
40
|
+
"url": "https://github.com/knowz-io/knowzcode/issues"
|
|
41
|
+
},
|
|
42
|
+
"repository": {
|
|
43
|
+
"type": "git",
|
|
44
|
+
"url": "git+https://github.com/knowz-io/knowzcode.git"
|
|
45
|
+
},
|
|
46
|
+
"publishConfig": {
|
|
47
|
+
"access": "public"
|
|
48
|
+
},
|
|
49
|
+
"license": "MIT",
|
|
50
|
+
"engines": {
|
|
51
|
+
"node": ">=18"
|
|
52
|
+
}
|
|
53
|
+
}
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "alias-resolver",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.4.0",
|
|
4
4
|
"description": "Resolves friendly natural-language aliases to KnowzCode canonical values (phase, audit, plan, workgroup_type).",
|
|
5
5
|
"parameters": [
|
|
6
6
|
{"name": "domain", "type": "string", "required": true},
|
package/skills/continue.md
CHANGED
|
@@ -1,126 +1,126 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: continue
|
|
3
|
-
description: Detect continuation intent and resume active WorkGroup workflow
|
|
4
|
-
trigger: User says "continue", "keep going", "resume", or similar continuation intent
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# Continue Skill
|
|
8
|
-
|
|
9
|
-
**Purpose**: Detect when user wants to continue work and resume the active WorkGroup with proper context restoration.
|
|
10
|
-
|
|
11
|
-
## Trigger Patterns
|
|
12
|
-
|
|
13
|
-
Activate when user message matches ANY of these patterns:
|
|
14
|
-
- "continue"
|
|
15
|
-
- "keep going"
|
|
16
|
-
- "resume"
|
|
17
|
-
- "carry on"
|
|
18
|
-
- "next"
|
|
19
|
-
- "continue with this"
|
|
20
|
-
- "let's continue"
|
|
21
|
-
- "keep working"
|
|
22
|
-
|
|
23
|
-
**Context Requirements**:
|
|
24
|
-
- Must be in a KnowzCode-initialized project (knowzcode/ directory exists)
|
|
25
|
-
- Should NOT trigger if user is clearly giving new instructions
|
|
26
|
-
- Should NOT trigger during explicit command execution
|
|
27
|
-
|
|
28
|
-
## When NOT to Trigger
|
|
29
|
-
|
|
30
|
-
- User is giving specific new instructions
|
|
31
|
-
- User is asking a question
|
|
32
|
-
- Already executing a /kc:* command
|
|
33
|
-
- knowzcode/ directory doesn't exist
|
|
34
|
-
|
|
35
|
-
## Skill Behavior
|
|
36
|
-
|
|
37
|
-
When triggered:
|
|
38
|
-
|
|
39
|
-
### Step 1: Find Active WorkGroup
|
|
40
|
-
|
|
41
|
-
Search `knowzcode/knowzcode_tracker.md` for `[WIP]` entries.
|
|
42
|
-
|
|
43
|
-
- **One active WorkGroup**: Use it automatically
|
|
44
|
-
- **Multiple active**: Present options to user
|
|
45
|
-
- **None active**: Inform user and suggest `/kc:work`
|
|
46
|
-
|
|
47
|
-
### Step 2: Load WorkGroup Context
|
|
48
|
-
|
|
49
|
-
Read `knowzcode/workgroups/{WorkGroupID}.md` to determine:
|
|
50
|
-
- Current phase
|
|
51
|
-
- Primary goal
|
|
52
|
-
- Change Set
|
|
53
|
-
- Outstanding todos
|
|
54
|
-
- **Autonomous Mode**: If the WorkGroup file contains `**Autonomous Mode**: Active`, restore `AUTONOMOUS_MODE = true` and announce: `> **Autonomous Mode: RESTORED** — continuing with auto-approved gates.`
|
|
55
|
-
- **Orchestration Config**: If `knowzcode/knowzcode_orchestration.md` exists, parse and restore `MAX_BUILDERS`, `SCOUT_MODE`, `MCP_AGENTS_ENABLED`, `DEFAULT_SPECIALISTS` (same logic as work.md Step 2.4). Defaults apply if file is absent.
|
|
56
|
-
|
|
57
|
-
### Step 3: Resume at Current Phase
|
|
58
|
-
|
|
59
|
-
Read `knowzcode/knowzcode_loop.md` and resume the workflow at the detected phase.
|
|
60
|
-
|
|
61
|
-
#### Parallel Mode Detection
|
|
62
|
-
|
|
63
|
-
If the WorkGroup file contains a `## Current Stage` section (instead of `Current Phase`):
|
|
64
|
-
- This is a **parallel-mode WorkGroup**
|
|
65
|
-
- Read the per-NodeID phase table to determine what's in progress
|
|
66
|
-
- Resume by recreating the team and spawning agents appropriate for the current stage:
|
|
67
|
-
- **Stage 0/1**: Spawn analyst + architect. If `SCOUT_MODE != "none"` and context is stale, re-spawn scout(s) per SCOUT_MODE.
|
|
68
|
-
- **Stage 2**: Spawn builder(s) per the dependency map + reviewer if any NodeIDs are past implementation
|
|
69
|
-
- **Stage 3**: Spawn closer
|
|
70
|
-
- Builders and reviewer persist through gap loops (don't respawn per iteration)
|
|
71
|
-
- Announce: `**Resuming Parallel Teams** — Stage {N}: {description}`
|
|
72
|
-
|
|
73
|
-
If resuming mid-Stage-2 (e.g., builder was implementing, reviewer had started auditing):
|
|
74
|
-
- Read the per-NodeID status table to determine which NodeIDs need builders and which need reviewer
|
|
75
|
-
- Carry forward existing context by reading the WorkGroup file
|
|
76
|
-
|
|
77
|
-
#### Sequential Mode Detection
|
|
78
|
-
|
|
79
|
-
If the WorkGroup file contains `Current Phase:` (standard format):
|
|
80
|
-
- This is a **sequential-mode WorkGroup**
|
|
81
|
-
- Create tasks only for the **remaining** phases (not completed ones):
|
|
82
|
-
|
|
83
|
-
| Detected Phase | Remaining Work |
|
|
84
|
-
|----------------|----------------|
|
|
85
|
-
| 1A | All phases (1A → 1B → 2A → 2B → 3) |
|
|
86
|
-
| 1B | Specs + implementation + audit + finalization |
|
|
87
|
-
| 2A | Implementation + audit + finalization |
|
|
88
|
-
| 2B | Audit + finalization |
|
|
89
|
-
| 3 | Finalization only |
|
|
90
|
-
|
|
91
|
-
**Set up execution mode** — check `~/.claude/settings.json` and `.claude/settings.json` for `"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"` in the `env` block. If found, Agent Teams is available — create a team named `kc-{wgid}` and activate delegate mode (you coordinate only, never write code directly). Read `knowzcode/claude_code_execution.md` for team conventions. For each remaining phase, spawn one teammate with the spawn prompt from the corresponding phase section of `/kc:work`, create a task, wait for completion, present quality gate, shut down teammate. Shut down all teammates when done or on cancel.
|
|
92
|
-
|
|
93
|
-
If Agent Teams is not available, announce `**Execution Mode: Subagent Delegation** — Agent Teams not available (add "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" to the env block in settings.json, then restart Claude Code)` and use `Task()` calls to delegate each remaining phase to the named agent.
|
|
94
|
-
|
|
95
|
-
Follow the same phase delegation patterns (spawn prompts, quality gates, gap loop) as `/kc:work`.
|
|
96
|
-
|
|
97
|
-
### Step 4: Present Status
|
|
98
|
-
|
|
99
|
-
```markdown
|
|
100
|
-
## Resuming WorkGroup: {wgid}
|
|
101
|
-
|
|
102
|
-
**Goal**: {primary goal}
|
|
103
|
-
**Phase**: {current phase}
|
|
104
|
-
**NodeIDs**: {list}
|
|
105
|
-
|
|
106
|
-
**Outstanding Todos**:
|
|
107
|
-
{list from WorkGroup file}
|
|
108
|
-
|
|
109
|
-
Continuing from where we left off...
|
|
110
|
-
```
|
|
111
|
-
|
|
112
|
-
Then proceed with the appropriate phase using the same agents as `/kc:work`.
|
|
113
|
-
|
|
114
|
-
## Logging
|
|
115
|
-
|
|
116
|
-
```markdown
|
|
117
|
-
---
|
|
118
|
-
**Type:** SkillActivation
|
|
119
|
-
**Timestamp:** [timestamp]
|
|
120
|
-
**Skill:** continue
|
|
121
|
-
**Trigger:** User said "{user_message}"
|
|
122
|
-
**WorkGroup:** {wgid}
|
|
123
|
-
**Phase:** {current phase}
|
|
124
|
-
**Logged By:** AI-Agent
|
|
125
|
-
---
|
|
126
|
-
```
|
|
1
|
+
---
|
|
2
|
+
name: continue
|
|
3
|
+
description: Detect continuation intent and resume active WorkGroup workflow
|
|
4
|
+
trigger: User says "continue", "keep going", "resume", or similar continuation intent
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
# Continue Skill
|
|
8
|
+
|
|
9
|
+
**Purpose**: Detect when user wants to continue work and resume the active WorkGroup with proper context restoration.
|
|
10
|
+
|
|
11
|
+
## Trigger Patterns
|
|
12
|
+
|
|
13
|
+
Activate when user message matches ANY of these patterns:
|
|
14
|
+
- "continue"
|
|
15
|
+
- "keep going"
|
|
16
|
+
- "resume"
|
|
17
|
+
- "carry on"
|
|
18
|
+
- "next"
|
|
19
|
+
- "continue with this"
|
|
20
|
+
- "let's continue"
|
|
21
|
+
- "keep working"
|
|
22
|
+
|
|
23
|
+
**Context Requirements**:
|
|
24
|
+
- Must be in a KnowzCode-initialized project (knowzcode/ directory exists)
|
|
25
|
+
- Should NOT trigger if user is clearly giving new instructions
|
|
26
|
+
- Should NOT trigger during explicit command execution
|
|
27
|
+
|
|
28
|
+
## When NOT to Trigger
|
|
29
|
+
|
|
30
|
+
- User is giving specific new instructions
|
|
31
|
+
- User is asking a question
|
|
32
|
+
- Already executing a /kc:* command
|
|
33
|
+
- knowzcode/ directory doesn't exist
|
|
34
|
+
|
|
35
|
+
## Skill Behavior
|
|
36
|
+
|
|
37
|
+
When triggered:
|
|
38
|
+
|
|
39
|
+
### Step 1: Find Active WorkGroup
|
|
40
|
+
|
|
41
|
+
Search `knowzcode/knowzcode_tracker.md` for `[WIP]` entries.
|
|
42
|
+
|
|
43
|
+
- **One active WorkGroup**: Use it automatically
|
|
44
|
+
- **Multiple active**: Present options to user
|
|
45
|
+
- **None active**: Inform user and suggest `/kc:work`
|
|
46
|
+
|
|
47
|
+
### Step 2: Load WorkGroup Context
|
|
48
|
+
|
|
49
|
+
Read `knowzcode/workgroups/{WorkGroupID}.md` to determine:
|
|
50
|
+
- Current phase
|
|
51
|
+
- Primary goal
|
|
52
|
+
- Change Set
|
|
53
|
+
- Outstanding todos
|
|
54
|
+
- **Autonomous Mode**: If the WorkGroup file contains `**Autonomous Mode**: Active`, restore `AUTONOMOUS_MODE = true` and announce: `> **Autonomous Mode: RESTORED** — continuing with auto-approved gates.`
|
|
55
|
+
- **Orchestration Config**: If `knowzcode/knowzcode_orchestration.md` exists, parse and restore `MAX_BUILDERS`, `SCOUT_MODE`, `MCP_AGENTS_ENABLED`, `DEFAULT_SPECIALISTS` (same logic as work.md Step 2.4). Defaults apply if file is absent.
|
|
56
|
+
|
|
57
|
+
### Step 3: Resume at Current Phase
|
|
58
|
+
|
|
59
|
+
Read `knowzcode/knowzcode_loop.md` and resume the workflow at the detected phase.
|
|
60
|
+
|
|
61
|
+
#### Parallel Mode Detection
|
|
62
|
+
|
|
63
|
+
If the WorkGroup file contains a `## Current Stage` section (instead of `Current Phase`):
|
|
64
|
+
- This is a **parallel-mode WorkGroup**
|
|
65
|
+
- Read the per-NodeID phase table to determine what's in progress
|
|
66
|
+
- Resume by recreating the team and spawning agents appropriate for the current stage:
|
|
67
|
+
- **Stage 0/1**: Spawn analyst + architect. If `SCOUT_MODE != "none"` and context is stale, re-spawn scout(s) per SCOUT_MODE.
|
|
68
|
+
- **Stage 2**: Spawn builder(s) per the dependency map + reviewer if any NodeIDs are past implementation
|
|
69
|
+
- **Stage 3**: Spawn closer
|
|
70
|
+
- Builders and reviewer persist through gap loops (don't respawn per iteration)
|
|
71
|
+
- Announce: `**Resuming Parallel Teams** — Stage {N}: {description}`
|
|
72
|
+
|
|
73
|
+
If resuming mid-Stage-2 (e.g., builder was implementing, reviewer had started auditing):
|
|
74
|
+
- Read the per-NodeID status table to determine which NodeIDs need builders and which need reviewer
|
|
75
|
+
- Carry forward existing context by reading the WorkGroup file
|
|
76
|
+
|
|
77
|
+
#### Sequential Mode Detection
|
|
78
|
+
|
|
79
|
+
If the WorkGroup file contains `Current Phase:` (standard format):
|
|
80
|
+
- This is a **sequential-mode WorkGroup**
|
|
81
|
+
- Create tasks only for the **remaining** phases (not completed ones):
|
|
82
|
+
|
|
83
|
+
| Detected Phase | Remaining Work |
|
|
84
|
+
|----------------|----------------|
|
|
85
|
+
| 1A | All phases (1A → 1B → 2A → 2B → 3) |
|
|
86
|
+
| 1B | Specs + implementation + audit + finalization |
|
|
87
|
+
| 2A | Implementation + audit + finalization |
|
|
88
|
+
| 2B | Audit + finalization |
|
|
89
|
+
| 3 | Finalization only |
|
|
90
|
+
|
|
91
|
+
**Set up execution mode** — check `~/.claude/settings.json` and `.claude/settings.json` for `"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"` in the `env` block. If found, Agent Teams is available — create a team named `kc-{wgid}` and activate delegate mode (you coordinate only, never write code directly). Read `knowzcode/claude_code_execution.md` for team conventions. For each remaining phase, spawn one teammate with the spawn prompt from the corresponding phase section of `/kc:work`, create a task, wait for completion, present quality gate, shut down teammate. Shut down all teammates when done or on cancel.
|
|
92
|
+
|
|
93
|
+
If Agent Teams is not available, announce `**Execution Mode: Subagent Delegation** — Agent Teams not available (add "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" to the env block in settings.json, then restart Claude Code)` and use `Task()` calls to delegate each remaining phase to the named agent.
|
|
94
|
+
|
|
95
|
+
Follow the same phase delegation patterns (spawn prompts, quality gates, gap loop) as `/kc:work`.
|
|
96
|
+
|
|
97
|
+
### Step 4: Present Status
|
|
98
|
+
|
|
99
|
+
```markdown
|
|
100
|
+
## Resuming WorkGroup: {wgid}
|
|
101
|
+
|
|
102
|
+
**Goal**: {primary goal}
|
|
103
|
+
**Phase**: {current phase}
|
|
104
|
+
**NodeIDs**: {list}
|
|
105
|
+
|
|
106
|
+
**Outstanding Todos**:
|
|
107
|
+
{list from WorkGroup file}
|
|
108
|
+
|
|
109
|
+
Continuing from where we left off...
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
Then proceed with the appropriate phase using the same agents as `/kc:work`.
|
|
113
|
+
|
|
114
|
+
## Logging
|
|
115
|
+
|
|
116
|
+
```markdown
|
|
117
|
+
---
|
|
118
|
+
**Type:** SkillActivation
|
|
119
|
+
**Timestamp:** [timestamp]
|
|
120
|
+
**Skill:** continue
|
|
121
|
+
**Trigger:** User said "{user_message}"
|
|
122
|
+
**WorkGroup:** {wgid}
|
|
123
|
+
**Phase:** {current phase}
|
|
124
|
+
**Logged By:** AI-Agent
|
|
125
|
+
---
|
|
126
|
+
```
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "generate-workgroup-id",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.4.0",
|
|
4
4
|
"description": "Generates a WorkGroupID following the KnowzCode convention [type]-[slug]-YYYYMMDD-HHMMSS. The slug is a 2-4 word descriptor extracted from the goal.",
|
|
5
5
|
"parameters": [
|
|
6
6
|
{
|