Vexjoy Agent

Deterministic palette/matrix pixel art (not AI). Use for procedural tile art, color-quantized output, matrix sprites.

AI sprite generation: portraits, idle loops, animated sheets via Codex/Nano Banana. Per-row generation, animation presets, video-to-sprite, identity lock. Use for generated character art.

Kubernetes operations: debugging, security, RBAC, and infrastructure tooling.

Analyze agent/skill reference depth and generate missing domain-specific reference files.

Feature lifecycle: design, plan, implement, validate, release. Phase-gated workflow.

Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.

Extract video transcripts: yt-dlp subtitles to clean paragraphs.

Generate blog topic ideas: problem mining, gap analysis, expansion.

Maintain /do routing tables when skills or agents change.

Question-only debugging: guide users to find root causes themselves.

Statistical rule discovery from Go codebase patterns.

Systematic codebase exploration and architecture mapping.

Verify cross-component wiring and data flow.

Standalone WebGL fragment shaders for card visual effects: holographic foil, shimmer, rarity glow.

Convert PDF, Office, HTML, data, media, ZIP to Markdown.

Parallel 3-reviewer code review: Security, Business-Logic, Architecture.

TypeScript type checking via tsc --noEmit with actionable error output.

Enterprise search: relevance tuning, query understanding, index management, search quality, ranking optimization, schema design.

4-phase code review: UNDERSTAND, VERIFY, ASSESS risks, DOCUMENT findings.

Audit CVE/vulnerability source coverage for a technology stack. Maps each component (container, library, base image, runtime) to authoritative CVE feeds, flags gaps, and produces audit-ready reports. Generic: works for any service or stack.

Improve architecture across modules by deepening interfaces.

Critique a written proposal or design artifact via 5 philosophical personas in parallel, with consensus synthesis.

RED-GREEN-REFACTOR cycle with strict phase gates for TDD.

Python quality checks: ruff, pytest, mypy, bandit in deterministic order.

Run the full evidence-to-live implementation workflow for large, multi-system, multi-wave, or CPU-delegated 5 Star Booker GM programs.

Drive the Hermes/Maia Concourse dev-branch deploy workflow — test stack changes in a live lab before merging to master. Use for "dev branch", "deploy to dev", "hermes-dev-branch", "maia-dev-branch", "test in labs", "dev lane". Covers both the hermes and maia stacks.

Publish a public website safely: DNS, web server, HTTPS, hardening, verify. Routes raw dev servers through nginx/Caddy/Apache/Cloudflare Pages.

Deterministic API endpoint validation with pass/fail reporting.

Anti-rationalization enforcement for maximum-rigor task execution.

Draft interpersonal and meeting messages: emails, memos, status updates, structured pushback or disagreement.

Triage GitHub notifications and issue/PR queues.

Multi-language code quality gate with auto-detection and linters.

Service health monitoring, endpoint validation, and CVE source auditing.

Fresh-subagent-per-task execution with two-stage review gates.

Context-driven aesthetic exploration with anti-cliche validation.

Generate headless Claude Code cron jobs with safety.

Safely start, supervise, and terminate shell processes: background jobs, PID capture, signals, traps, cleanup verification.

Defense-in-depth verification before declaring any task complete.

OpenSearch SIEM detection: SIGMA, query DSL, MITRE ATT&CK mapping, anomaly/correlation rules, alert validation, SOC escalation.