mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-03-05 16:13:08 +08:00

Files

catlog22 26bda9c634 feat: Add coordinator commands and role specifications for UI design team

- Implemented the 'monitor' command for coordinator role to handle monitoring events, task completion, and pipeline management.
- Created role specifications for the coordinator, detailing responsibilities, command execution protocols, and session management.
- Added role specifications for the analyst, discussant, explorer, and synthesizer in the ultra-analyze skill, defining their context loading, analysis, and synthesis processes.

2026-03-03 23:35:41 +08:00

2.8 KiB

Raw Blame History

prefix, inner_loop, subagents, message_types

prefix

inner_loop

subagents

message_types

SCOUT

false

success	error	issues
scan_ready	error	issues_found

Multi-Perspective Scout

Scan codebase from multiple perspectives (bug, security, test-coverage, code-quality, UX) to discover potential issues. Produce structured scan results with severity-ranked findings.

Phase 2: Context & Scope Assessment

Input	Source	Required
Task description	From task subject/description	Yes
Session path	Extracted from task description	Yes
.msg/meta.json	/wisdom/.msg/meta.json	No

Extract session path and target scope from task description
Determine scan scope: explicit scope from task or **/* default
Get recent changed files: git diff --name-only HEAD~5 2>/dev/null || echo ""
Read .msg/meta.json for historical defect patterns (defect_patterns)
Select scan perspectives based on task description:
- Default: ["bug", "security", "test-coverage", "code-quality"]
- Add "ux" if task mentions UX/UI
Assess complexity to determine scan strategy:

Complexity	Condition	Strategy
Low	< 5 changed files, no specific keywords	ACE search + Grep inline
Medium	5-15 files or specific perspective requested	CLI fan-out (3 core perspectives)
High	> 15 files or full-project scan	CLI fan-out (all perspectives)

Phase 3: Multi-Perspective Scan

Low complexity: Use mcp__ace-tool__search_context for quick pattern-based scan.

Medium/High complexity: CLI fan-out -- one ccw cli --mode analysis per perspective:

For each active perspective, build prompt:

PURPOSE: Scan code from <perspective> perspective to discover potential issues
TASK: Analyze code patterns for <perspective> problems, identify anti-patterns, check for common issues
MODE: analysis
CONTEXT: @<scan-scope>
EXPECTED: List of findings with severity (critical/high/medium/low), file:line references, description
CONSTRAINTS: Focus on actionable findings only

Execute via: ccw cli -p "<prompt>" --tool gemini --mode analysis

After all perspectives complete:

Parse CLI outputs into structured findings
Deduplicate by file:line (merge perspectives for same location)
Compare against known defect patterns from .msg/meta.json
Rank by severity: critical > high > medium > low

Phase 4: Result Aggregation

Build discoveredIssues array from critical + high findings (with id, severity, perspective, file, line, description)
Write scan results to <session>/scan/scan-results.json:
- scan_date, perspectives scanned, total findings, by_severity counts, findings detail, issues_created count
Update <session>/wisdom/.msg/meta.json: merge discovered_issues field
Contribute to wisdom/issues.md if new patterns found

2.8 KiB Raw Blame History

Multi-Perspective Scout

Phase 2: Context & Scope Assessment

Phase 3: Multi-Perspective Scan

Phase 4: Result Aggregation

2.8 KiB

Raw Blame History