메뉴
Continuous AI engineering analysis system for Alexander Vault — architecture, security, dependency, and concurrency scanners with visualization dashboard.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | vault-analysis |
| description | Continuous AI engineering analysis system for Alexander Vault — architecture, security, dependency, and concurrency scanners with visualization dashboard. |
| user-invocable | false |
Automated static analysis pipeline for Alexander Vault. Runs architecture, security, dependency, and concurrency scans with live event-driven results.
The analysis system provides a continuous quality engineering loop that can be triggered manually, from git hooks, or via CLI. It scans the codebase for architectural violations, security vulnerabilities, dependency issues, and concurrency bugs.
| Analyzer | File | Detects |
|---|---|---|
| Architecture | architecture-analyzer.ts | Circular deps, tight coupling, module boundary violations, event flow |
| Security | security-scanner.ts | Hardcoded keys, auth gaps, path traversal, stack trace leaks |
| Dependency | dependency-auditor.ts | npm vulns, unused deps, outdated packages |
| Concurrency | concurrency-analyzer.ts | Missing await, race conditions, EventBus error handling |
| Orchestrator | analysis-orchestrator.ts | Coordinates all 4 analyzers, caches results, persists to knowledge/ |
| Method | Path | Purpose |
|---|---|---|
| POST | /api/analysis/run | Run full analysis (all 4 analyzers) |
| POST | /api/analysis/run/:type | Run single analyzer |
| GET | /api/analysis/results | Get latest run results |
| GET | /api/analysis/results/:runId | Get specific run by ID |
| GET | /api/analysis/architecture-map | Module dependency graph |
| GET | /api/analysis/event-bus-map | EventBus emitter/subscriber map |
| GET | /api/analysis/history | List of past analysis runs |
// Finding — single issue found by an analyzer // Fields: id, type, severity (critical|high|medium|low|info), title, description, file?, line?, suggestion?
// AnalysisResult — from a single analyzer run // Fields: analyzerId, timestamp, duration, findings[], summary, severityCounts
// AnalysisRunResult — from running all analyzers // Fields: id, timestamp, analyzers (Record<string, AnalysisResult>), overallStatus (pass|warn|fail)
// Analysis events flow through the same SSE stream as extraction events // Event types: analysis:start, analysis:progress, analysis:complete, analysis:error // Server: extractionEventBus.emitAnalysis(event) // Client: SSE stream at /api/extraction/events includes analysis events
// Architecture.tsx — visualization page with: // - Force-directed module dependency graph (canvas-based) // - Run buttons for full and individual analyzers // - Findings panel with severity tabs and grouping // - History timeline // - Selected module detail (imports from/imported by) // Hook: client/src/hooks/use-analysis.ts (React Query)
npm run analysis:run # Full analysis (all 4 analyzers)
npm run analysis:security # Security scan only
npm run docs:generate # Generate architecture-map.md, event-bus-map.md, security-architecture.md
npm run hooks:install # Install git pre-commit + post-commit hooks
// pre-commit: Runs security scan. Blocks commit if critical findings detected. // post-commit: Runs full analysis (non-blocking, informational only). // Install: npm run hooks:install // Bypass: git commit --no-verify
To add a new analyzer:
Wraps gsd-pi (Get Shit Done coding agent CLI) with Marcus's project constraints and coding standards so gsd tasks inherit observer pattern, no em-dashes, no Co-Authored-By, and AgenticOS event integration automatically. Use when the user says "run this with gsd", "hand this off to gsd", "use gsd-pi for this", "delegate to gsd", or wants to execute a coding task using gsd-pi as the execution engine rather than Claude Code directly. Also trigger when autonomous-workflow needs to fan out a phase to gsd-pi for execution.
Meta-skill that runs the full skill lifecycle in one command: create, eval, improve, and publish. Use when the user says "forge a skill", "create and improve a skill", "run the skill loop on X", "build and publish a skill", "skill-forge", or wants to go from idea to production-ready skill without manually chaining skill-creator and skill-self-improver. Also trigger when the user wants to combine or upgrade existing skills, write eval.json for a skill, or push skills to GitHub. Wraps skill-creator + skill-self-improver into one /skill-forge command.
Recover from interrupted AI agent coding sessions by detecting the exact interruption point, reconstructing intent from pre-written step comments, completing unfinished implementations, and validating through build + supervisor review. Use this skill whenever a user mentions session recovery, interrupted work, picking up where an agent left off, completing unfinished code, finding where a session dropped, resuming development, or anything related to detecting and finishing incomplete AI-assisted coding sessions. Also trigger when users mention Claude Code agent sessions that were cut off, lost progress, or need continuation. This skill works across all languages and frameworks — C++, C#, Python, TypeScript, Rust, Java, Go, Unreal Engine, Unity, .NET, React, Node.js. Trigger aggressively — if a user says anything about resuming, continuing, recovering, or picking up work, use this skill.
Agent state-writing protocol for the AgenticOS Command Center. Any Claude sub-agent running in a multi-agent parallel session reads this skill to participate in dashboard tracking, approval gates, and reviewer spawning.
Cross-domain protocol for supervised parallel multi-agent runs against the AgenticOS Command Center. Use whenever Marcus says "spawn parallel agents", "multi-agent task", "review agent output", "approval gate", "monitor sub-agents", "supervised pipeline", "gate the next stage", "run several agents", "watch the agents", or kicks off a session with named AGENT-01, AGENT-02 roster. Defines the AgentState contract, the approval gate handshake, the reviewer-agent pattern, and the parallel etiquette every sub-agent must follow to appear in the Command Center dashboard with no extra wiring.
Workflow automation and multi-agent orchestration tools. Use when the user mentions n8n, Langflow, claude-squad, container-use, Dagger, workflow automation, pipeline orchestration, multi-agent coordination, or wants to set up automated workflows. Also trigger for 'automate this process', 'create a workflow', 'run agents in parallel', or integration of multiple tools into a pipeline.