Ibrahim-3d

Master coordinator for the Evaluate-Loop workflow v3. Supports GOAL-DRIVEN entry, PARALLEL execution via worker agents, BOARD OF DIRECTORS deliberation, and message bus coordination. Dispatches specialized workers dynamically, monitors via message bus, aggregates results. Uses metadata.json v3 for parallel state tracking. Use when: '/go <goal>', '/conductor implement', 'start track', 'run the loop', 'orchestrate', 'automate track'.

File-based message queue for inter-agent coordination. Used by workers AND board directors to communicate. Provides: progress updates, task completion signals, file locking, board deliberation. Core infrastructure for parallel execution.

Loads relevant patterns and known errors before track planning. Searches conductor/knowledge/ for solutions we've used before and errors we've encountered. Injects findings into the planner prompt to prevent reinventing solutions and repeating mistakes. Triggered automatically by orchestrator before PLAN step.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Manage Conductor tracks, phases, and tasks. Use when working with track status, updating task markers, or navigating between tracks. Enforces the Evaluate-Loop workflow.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Evaluate-Loop Step 1: PLAN. Use this agent when starting a new track or feature to create a detailed execution plan. Reads spec.md, loads project context, and produces a phased plan.md with specific tasks, acceptance criteria, and dependencies. Triggered by: 'plan feature', 'create plan', 'start track', '/conductor implement' (planning phase).

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Author a single skill from a short brief. Use to add a skill to an existing plugin or iterate on a skill's description/body.

Write or refactor Claude Code sub-agent definitions (files in agents/*.md). Use when the user asks to "create a subagent", "add an agent for X", "build a specialist agent", "make a research agent", "write an agent file", "agent YAML", "delegate to a subagent", "design a multi-agent workflow", or when a task needs a fresh context window, restricted tools, or isolation. Covers frontmatter (tools/model/effort/maxTurns/isolation), delegation patterns, read-only constraints, and orchestrator↔specialist contracts.

Write or refactor Claude Code slash commands (files in commands/<ns>/<cmd>.md). Use when the user asks to "create a slash command", "add /<name>", "write a command file", "make a /command", "turn this workflow into a command", "argument hints", "allowed-tools", or when packaging a repeatable workflow as a one-keystroke invocation. Covers frontmatter, $ARGUMENTS parsing, @-imports for context files, and orchestration patterns.

Design and optimize context windows for agentic workflows. Use when the user asks to "manage context", "optimize context", "compact context", "context budget", "CLAUDE.md", "memory hierarchy", "context degradation", "agent is forgetting", "agent hallucinating after many turns", "long conversation", "hit token limit", "prune context", "memory tiers", or when a multi-turn workflow shows quality decay. Covers CLAUDE.md authoring, tiered memory, scratchpads, /compact strategies, read-depth rules, and subagent delegation for context relief.

Research a domain end-to-end before scaffolding an agentic system for it. Use when the user asks to "research [domain]", "learn about [field]", "what are the best practices for X", "survey the tools for Y", "what MCPs exist for Z", "before we build the agent, understand [topic]", or when kicking off a new /agents-architect:new for an unfamiliar domain. Covers methodology: taxonomy → tools → MCPs → idioms → anti-patterns → eval cases. Produces DOMAIN.md.

Select, scaffold, or integrate Model Context Protocol (MCP) servers with a Claude Code plugin. Use when the user asks to "add an MCP", "which MCP for X", "connect to [service]", "find a server for [API/tool]", "wrap [tool] as an MCP", ".mcp.json", "MCP server config", or when a domain needs external tools Claude doesn't have (Blender, Figma, ClickUp, arxiv, a CAD program, etc.). Covers MCP discovery via registry, config schema, env/userConfig wiring, and fallback to CLI when no MCP exists.

Package a collection of skills/agents/commands/hooks as a distributable Claude Code plugin. Use when the user asks to "package this as a plugin", "create a plugin.json", "build a marketplace entry", "make this installable", "publish my plugin", "plugin manifest", "validate my plugin", or when bundling work for others to install via /plugin marketplace add. Covers plugin.json schema, marketplace.json, CLAUDE_PLUGIN_ROOT, userConfig, and validation.

Write, refactor, or improve Claude Code / Claude skill files (SKILL.md). Use when the user asks to "create a skill", "write a SKILL.md", "add a skill for X", "make Claude better at Y", "turn this into a skill", "optimize skill triggers", "my skill isn't firing", or when building any reusable capability that Claude should auto-invoke on matching prompts. Covers trigger-phrase engineering, progressive disclosure, reference-library pattern, scripts, and eval design.

Generate, edit, or create any image — photos, illustrations, icons, thumbnails, hero images, banners, placeholder visuals, website graphics, social media assets, product shots, logos, diagrams, or any visual content. Use this skill whenever the task involves creating an image, populating a UI with visuals, generating placeholder or mockup images, editing or retouching a photo, applying style transfer, composing multiple images, or producing any graphic asset. Triggers on requests like "generate an image", "create a visual", "make a placeholder", "add a hero image", "design a thumbnail", "edit this photo", "create website graphics", "populate with images", or any task requiring image creation or manipulation.