Agent Claude Code
Code review specialist for quality, security, and maintainability analysis. Use proactively after writing or modifying code, before commits, or for PR review. Isolates review context from main conversation. Context: User has finished implementing a feature user: "I've added the new authentication feature. Can you…
Agent Claude Code
Debugging specialist for root cause analysis of errors, test failures, and unexpected behavior. Use proactively when encountering any issues. Context: User encounters a runtime error user: "I'm getting a TypeError when calling the API" assistant: "I'll use the debugger agent to investigate the root cause." Error…
Agent Claude Code
Pipeline AC drift reviewer. Detects semantic misalignment between code changes and the active task's Acceptance Criteria — the layer that review-code's existence-check cannot catch (e.g. "VIP free shipping" silently implemented as "VIP 50% off"). Writes JSON findings to file - zero context pollution. Used exclusively…
Agent Claude Code
Pipeline code quality reviewer. Writes JSON findings to file - zero context pollution. NOT for interactive use (use code-reviewer for that). Used exclusively by /ultra-review.
Agent Claude Code
Pipeline comment quality analyzer. Detects stale, misleading, or low-value comments. Writes JSON findings to file. Used exclusively by /ultra-review.
Agent Claude Code
Aggregates all review agent JSON outputs. Deduplicates, prioritizes, generates SUMMARY. Used exclusively by /ultra-review after all review agents complete.
Agent Claude Code
Pipeline design quality analyzer. Combines type design evaluation and complexity analysis. Writes JSON findings to file. Used exclusively by /ultra-review.
Agent Claude Code
Pipeline silent failure hunter. Detects empty catches, swallowed errors, hidden failures. Writes JSON findings to file. Used exclusively by /ultra-review.
Agent Claude Code
Pipeline test quality analyzer. Detects mock violations, coverage gaps, missing critical paths. Writes JSON findings to file. Used exclusively by /ultra-review.
Command Claude Code
Release preparation (documentation + build + version + publish).
Command Claude Code
Agile development execution with TDD workflow.
Command Claude Code
Initialize Ultra Builder Pro 6.8.0 project with native task management.
Command Claude Code
Task planning with intelligent dependency analysis and complexity assessment.
Command Claude Code
Think-Driven Interactive Discovery - Deep research with step-file architecture.
Command Claude Code
Status query with native task system (real-time progress + risk analysis).
Command Claude Code
Pre-delivery quality audit (Anti-Pattern + Coverage Gap + E2E + Performance + Security).
Command Claude Code
Deep analysis with structured adversarial reasoning and human-AI collaboration.
Skill Claude Code
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
Skill Claude Code
Shared collaboration protocol, modes, and prompt templates for AI collab skills. Consumed by gemini-collab, codex-collab, and ultra-verify as a shared foundation.
Skill Claude Code
Structured code review checklists: SOLID, security, performance, boundary conditions, removal planning. Injected into code-reviewer agent.
Skill Claude Code
Dual-AI collaboration with Codex. Use for architecture opinions, comparative verification, project understanding. For code review, use the official /codex:review plugin directly — this skill no longer wraps it. Triggers: 'ask Codex', 'Codex opinion', 'let Codex check', 'compare with Codex'.
Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Skill Claude Code
This skill should be used when the user asks to 'ask Gemini', 'Gemini review', 'let Gemini check', 'Gemini analysis', 'dual AI', or mentions 'gemini' in any collaborative context for code review, project analysis, architecture opinions, or comparative verification.
Skill Claude Code
Ultra Builder Pro system integration rules.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: