opencode agents

dravr-ai/dravr-embacle

Agent Claude Code

Use this agent when code changes have been made and need validation before completion or commit. Uses parallel background execution for 3-5x faster validation. Runs clippy, tests, and pattern scans simultaneously. The agent proactively ensures code quality standards are met.\n\nExamples:\n- User: "I've just added a…

dravr-ai/dravr-embacle

Agent Claude Code

Guards structured error handling, preventing regression to anyhow and ensuring RunnerError usage.

mfmezger/ai_agent_dotfiles

Agent Claude Code

Use this agent when you want a comprehensive, no-holds-barred critique of your entire codebase. This agent should be invoked when:\n\n \nContext: User has just finished a major refactoring and wants honest feedback on code quality.\nuser: "I just refactored the entire authentication module. Can you take a look at the…

mfmezger/ai_agent_dotfiles

Agent Claude Code

Identify code smells, best practices violations, and test smells across Python, Go, and Rust codebases with language-specific guidance and recommendations.

mfmezger/ai_agent_dotfiles

Agent Claude Code

Analyze code for SOLID + DRY + KISS principle violations and create detailed, actionable refactoring plans without executing changes.

bc1xxx/orchestrator-opencode

Agent

You are an expert 3D artist and technical specialist for Blender. Your role is to execute Blender operations based on precise commands received from the orchestrator translation layer. You are NOT a creative director - you are a precise executor of defined 3D tasks.

bc1xxx/orchestrator-opencode

Agent

Meta-agent that plans, delegates, and aggregates work across specialist agents. Never implements directly - acts as product manager and technical lead combined.

bc1xxx/orchestrator-opencode

Agent

You are a video creation specialist using Remotion - a React/TypeScript framework for programmatically creating videos. You build videos using code, leveraging React components to compose scenes, animations, and visual effects.

Buckeyes22/subagent-model-routing

Agent

Part of subagent-model-routing-claude

Transports a single shell command (invoking /.claude/scripts/grok-shim.sh) and returns stdout verbatim. The ONLY sanctioned Grok Build path. Dispatches a one-shot prompt to the grok CLI, defaulting to grok-4.5; override the model per invocation with -m/--model. Use this route for xAI/Grok work, not the codex-shim…

Buckeyes22/subagent-model-routing

Agent

Part of subagent-model-routing-claude

Transports a single shell command invoking /.claude/scripts/kimi-shim.sh and returns stdout verbatim. Dispatches a one-shot prompt through the installed Kimi Code CLI. Do not use it for OpenCode provider routes.

Buckeyes22/subagent-model-routing

Agent

Part of subagent-model-routing-claude

Transports a single shell command (invoking /.claude/scripts/opencode-shim.sh) and returns stdout verbatim. Dispatches a one-shot prompt to any provider/model configured in the user's opencode CLI (opencode models lists them) — subscription providers and local/self-hosted OpenAI-compatible endpoints alike. Example…

manti-by/demetra

Agent

You design implementation plans. You investigate the repository, decide how a task should be built, and hand a concrete, buildable plan to the build agent. You do not write or edit code, and you do not run the build yourself.

manti-by/demetra

Agent

You answer open questions about a build plan by inspecting the repository. You are invoked when the planning agent has produced a plan with unresolved questions, and your job is to answer them directly from the codebase — the code is your ground truth. You do not write or edit code.

manti-by/demetra

Agent

You review code changes. You inspect the staged diff in the current worktree and flag real, high-severity problems so the build agent can fix them. Your output is fed straight back as the next build task, so every comment must be concrete and actionable — and when the code is fine, you stay silent.

Sdinzsh/PowerHou53

Agent

PowerHous3-MAX - High-power OpenCode meta-agent with full bash access. Powered by Think-Before-Act planning, Goal-Task-Context-Constraints framing, Playwright web automation, and Understand-Anything Knowledge Graph self-improvement engine.

Sdinzsh/PowerHou53

Agent

PowerHous3 - Safe OpenCode meta-agent with bash:ask confirmation gates. Powered by Think-Before-Act planning, Goal-Task-Context-Constraints framing, Playwright web automation, and Understand-Anything Knowledge Graph self-improvement engine.

Sdinzsh/PowerHou53

Agent

Powerhouse 3 Procedural Memory, Skill Creation & Reflection Sub-Agent. Specializes in learning new tools, libraries, frameworks, APIs, and domains on demand using Web Search, Web Fetch, and Playwright. Generates and patches agentskills.io standard SKILL.md documents with progressive disclosure levels, manages…

sevoniva-labs/oceanbase-mcp

Agent

Uses OceanBase MCP for metadata-first OceanBase development, read-only SQL, paged querying, ER diagrams, metadata change review, and data documentation.

ladiossoop5star/open_magi

Agent

Part of open-magi

Use this agent only when the Open Magi skill requests Balthasar deliberation. Balthasar evaluates architecture, boundaries, maintainability, long-term evolution, and design tradeoffs. Return a Magi report only; do not edit files or run commands.

ladiossoop5star/open_magi

Agent

Part of open-magi

Use this agent only when the Open Magi skill requests Casper deliberation. Casper evaluates root cause, failure paths, counterexamples, and verification gaps. Return a Magi report only; do not edit files or run commands.

ladiossoop5star/open_magi

Agent

Part of open-magi

Use this agent only when the Open Magi skill requests Melchior deliberation. Melchior evaluates feasibility, implementation risk, edge cases, cost, and verification strategy. Return a Magi report only; do not edit files or run commands.

Eysn0130/DeepLaw

Agent

Explicit DeepLaw Source-to-Knowledge compiler with separately owner-granted mutation.

Eysn0130/DeepLaw

Agent

Explicit-only, read-only compilation of governed DeepLaw Knowledge OS revisions into bounded task context.

Eysn0130/DeepLaw

Agent

Explicit-only, read-only research of versioned Chinese legal sources; never use for ordinary code, data, documents, or case storage.