# Send Oh My OpenCode to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "oh-my-opencode",
    "name": "Oh My OpenCode",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/McOso/oh-my-opencode",
    "canonicalUrl": "https://clawhub.ai/McOso/oh-my-opencode",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/oh-my-opencode",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=oh-my-opencode",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "_meta.json",
      "SKILL.md",
      "scripts/run-ulw.sh",
      "scripts/doctor.sh",
      "references/troubleshooting.md",
      "references/configuration.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "oh-my-opencode",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-06T08:18:56.201Z",
      "expiresAt": "2026-05-13T08:18:56.201Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=oh-my-opencode",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=oh-my-opencode",
        "contentDisposition": "attachment; filename=\"oh-my-opencode-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "oh-my-opencode"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/oh-my-opencode"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/oh-my-opencode",
    "downloadUrl": "https://openagent3.xyz/downloads/oh-my-opencode",
    "agentUrl": "https://openagent3.xyz/skills/oh-my-opencode/agent",
    "manifestUrl": "https://openagent3.xyz/skills/oh-my-opencode/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/oh-my-opencode/agent.md"
  }
}
```
## Documentation

### Oh My OpenCode

Multi-agent orchestration plugin that transforms OpenCode into a full agent harness with specialized agents, background task execution, category-based model routing, and autonomous work modes.

Package: oh-my-opencode (install via bunx oh-my-opencode install)
Repository: https://github.com/code-yeongyu/oh-my-opencode
Schema: https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json

### Prerequisites

OpenCode installed and configured (opencode --version should be 1.0.150+)
curl -fsSL https://opencode.ai/install | bash
# or: npm install -g opencode-ai
# or: bun install -g opencode-ai


At least one LLM provider authenticated (opencode auth login)
Strongly recommended: Anthropic Claude Pro/Max subscription (Sisyphus uses Claude Opus 4.5)

### Installation

Run the interactive installer:

bunx oh-my-opencode install

Non-interactive mode with provider flags:

bunx oh-my-opencode install --no-tui \\
  --claude=<yes|no|max20> \\
  --openai=<yes|no> \\
  --gemini=<yes|no> \\
  --copilot=<yes|no> \\
  --opencode-zen=<yes|no> \\
  --zai-coding-plan=<yes|no>

Verify:

opencode --version
cat ~/.config/opencode/opencode.json  # should contain "oh-my-opencode" in plugin array

### Mode 1: Ultrawork (Quick Autonomous Work)

Include ultrawork or ulw in your prompt. That's it.

ulw add authentication to my Next.js app

The agent will automatically:

Explore your codebase to understand existing patterns
Research best practices via specialized background agents
Implement the feature following your conventions
Verify with diagnostics and tests
Keep working until 100% complete

### Mode 2: Prometheus (Precise Planned Work)

For complex or critical tasks:

Press Tab → switches to Prometheus (Planner) mode
Describe your work → Prometheus interviews you, asking clarifying questions while researching your codebase
Confirm the plan → review generated plan in .sisyphus/plans/*.md
Run /start-work → Atlas orchestrator takes over:

Distributes tasks to specialized sub-agents
Verifies each task completion independently
Accumulates learnings across tasks
Tracks progress across sessions (resume anytime)

Critical rule: Do NOT use Atlas without /start-work. Prometheus and Atlas are a pair — always use them together.

### Agents

All agents are enabled by default. Each has a default model and provider priority fallback chain.

AgentRoleDefault ModelProvider Priority ChainSisyphusPrimary orchestratorclaude-opus-4-5anthropic → kimi-for-coding → zai-coding-plan → openai → googleSisyphus-JuniorFocused task executor (used by delegate_task with categories)Determined by categoryPer-category chainHephaestusAutonomous deep worker — goal-oriented, explores before actinggpt-5.2-codex (medium)openai → github-copilot → opencode (requires gpt-5.2-codex)OracleArchitecture, debugging, high-IQ reasoning (read-only)gpt-5.2openai → google → anthropicLibrarianOfficial docs, OSS search, remote codebase analysisglm-4.7zai-coding-plan → opencode → anthropicExploreFast codebase grep (contextual search)claude-haiku-4-5anthropic → github-copilot → opencodeMultimodal LookerImage/PDF/diagram analysisgemini-3-flashgoogle → openai → zai-coding-plan → kimi-for-coding → anthropic → opencodePrometheusWork planner (interview-based plan generation)claude-opus-4-5anthropic → kimi-for-coding → openai → googleMetisPre-planning consultant (ambiguity/failure-point analysis)claude-opus-4-5anthropic → kimi-for-coding → openai → googleMomusPlan reviewer (clarity, verifiability, completeness)gpt-5.2openai → anthropic → googleAtlasPlan orchestrator (executes Prometheus plans via /start-work)k2p5 / claude-sonnet-4-5kimi-for-coding → opencode → anthropic → openai → googleOpenCode-BuilderDefault build agent (disabled by default when Sisyphus is active)System defaultSystem default

### Agent Invocation

Agents are invoked via delegate_task() or the --agent CLI flag — NOT with @ prefix.

// Invoke a specific agent
delegate_task(subagent_type="oracle", prompt="Review this architecture...")

// Invoke via category (routes to Sisyphus-Junior with category model)
delegate_task(category="visual-engineering", load_skills=["frontend-ui-ux"], prompt="...")

// Background execution (non-blocking)
delegate_task(subagent_type="explore", run_in_background=true, prompt="Find auth patterns...")

CLI:

opencode --agent oracle
opencode run --agent librarian "Explain how auth works in this codebase"

### When to Use Which Agent

SituationAgentGeneral coding tasksSisyphus (default)Autonomous goal-oriented deep workHephaestus (requires gpt-5.2-codex)Architecture decisions, debugging after 2+ failuresOracleLooking up library docs, finding OSS examplesLibrarianFinding code patterns in your codebaseExploreAnalyzing images, PDFs, diagramsMultimodal LookerComplex multi-day projects needing a planPrometheus + Atlas (via Tab → /start-work)Pre-planning scope analysisMetisReviewing a generated plan for gapsMomusQuick single-file changesdelegate_task with quick category

### Categories

Categories route tasks to Sisyphus-Junior with domain-optimized models via delegate_task().

CategoryDefault ModelVariantProvider Priority ChainBest Forvisual-engineeringgemini-3-pro—google → anthropic → zai-coding-planFrontend, UI/UX, design, styling, animationultrabraingpt-5.2-codexxhighopenai → google → anthropicDeep logical reasoning, complex architecturedeepgpt-5.2-codexmediumopenai → anthropic → googleGoal-oriented autonomous problem-solving (Hephaestus-style)artistrygemini-3-promaxgoogle → anthropic → openaiCreative/novel approaches, unconventional solutionsquickclaude-haiku-4-5—anthropic → google → opencodeTrivial tasks, single file changes, typo fixesunspecified-lowclaude-sonnet-4-5—anthropic → openai → googleGeneral tasks, low effortunspecified-highclaude-opus-4-5maxanthropic → openai → googleGeneral tasks, high effortwritinggemini-3-flash—google → anthropic → zai-coding-plan → openaiDocumentation, prose, technical writing

### Category Usage

delegate_task(category="visual-engineering", load_skills=["frontend-ui-ux"], prompt="Create a dashboard component")
delegate_task(category="ultrabrain", load_skills=[], prompt="Design the payment processing flow")
delegate_task(category="quick", load_skills=["git-master"], prompt="Fix the typo in README.md")
delegate_task(category="deep", load_skills=[], prompt="Investigate and fix the memory leak in the worker pool")

### Critical: Model Resolution Priority

Categories do NOT use their built-in defaults unless configured. Resolution order:

User-configured model (in oh-my-opencode.json) — highest priority
Category's built-in default (if category is in config)
System default model (from opencode.json) — fallback

To use optimal models, add categories to your config. See references/configuration.md.

### Built-in Skills

SkillPurposeUsageplaywrightBrowser automation via Playwright MCP (default browser engine)load_skills=["playwright"]agent-browserVercel's agent-browser CLI with session managementSwitch via browser_automation_engine configgit-masterGit expert: atomic commits, rebase/squash, history searchload_skills=["git-master"]frontend-ui-uxDesigner-turned-developer for stunning UI/UXload_skills=["frontend-ui-ux"]

Skills are injected into subagents via delegate_task(load_skills=[...]).

### Slash Commands

CommandDescription/init-deepInitialize hierarchical AGENTS.md knowledge base/start-workExecute a Prometheus plan with Atlas orchestrator/ralph-loopStart self-referential development loop until completion/ulw-loopStart ultrawork loop — continues until completion/cancel-ralphCancel active Ralph Loop/refactorIntelligent refactoring with LSP, AST-grep, architecture analysis, TDD/stop-continuationStop all continuation mechanisms (ralph loop, todo continuation, boulder)

### Background Agents

Fire multiple agents in parallel for exploration and research:

// Launch background agents (non-blocking)
delegate_task(subagent_type="explore", run_in_background=true, prompt="Find auth patterns in codebase")
delegate_task(subagent_type="librarian", run_in_background=true, prompt="Find JWT best practices")

// Collect results when needed
background_output(task_id="bg_abc123")

// Cancel all background tasks before final answer
background_cancel(all=true)

### Concurrency Configuration

{
  "background_task": {
    "defaultConcurrency": 5,
    "staleTimeoutMs": 180000,
    "providerConcurrency": { "anthropic": 3, "google": 10 },
    "modelConcurrency": { "anthropic/claude-opus-4-5": 2 }
  }
}

Priority: modelConcurrency > providerConcurrency > defaultConcurrency

### Tmux Integration

Run background agents in separate tmux panes for visual multi-agent execution:

{
  "tmux": {
    "enabled": true,
    "layout": "main-vertical",
    "main_pane_size": 60
  }
}

Requires running OpenCode in server mode inside a tmux session:

tmux new -s dev
opencode --port 4096

Layout options: main-vertical (default), main-horizontal, tiled, even-horizontal, even-vertical

### Pattern 1: Explore + Librarian (Research Phase)

// Internal codebase search
delegate_task(subagent_type="explore", run_in_background=true, prompt="Find how auth middleware is implemented")
delegate_task(subagent_type="explore", run_in_background=true, prompt="Find error handling patterns in the API layer")

// External documentation search
delegate_task(subagent_type="librarian", run_in_background=true, prompt="Find official JWT documentation and security recommendations")

// Continue working immediately — collect results when needed

### Pattern 2: Category-Based Delegation (Implementation Phase)

// Frontend work → visual-engineering category
delegate_task(category="visual-engineering", load_skills=["frontend-ui-ux"], prompt="Build the settings page")

// Quick fix → quick category
delegate_task(category="quick", load_skills=["git-master"], prompt="Create atomic commit for auth changes")

// Hard problem → ultrabrain category
delegate_task(category="ultrabrain", load_skills=[], prompt="Design the caching invalidation strategy")

### Pattern 3: Session Continuity

// First delegation returns a session_id
result = delegate_task(category="quick", load_skills=["git-master"], prompt="Fix the type error")
// session_id: "ses_abc123"

// Follow-up uses session_id to preserve full context
delegate_task(session_id="ses_abc123", prompt="Also fix the related test file")

### Core Commands

opencode                           # Start TUI
opencode --port 4096               # Start TUI with server mode (for tmux integration)
opencode -c                        # Continue last session
opencode -s <session-id>           # Continue specific session
opencode --agent <agent-name>      # Start with specific agent
opencode -m provider/model         # Start with specific model

### Non-Interactive Mode

opencode run "Explain closures in JavaScript"
opencode run --agent oracle "Review this architecture"
opencode run -m openai/gpt-5.2 "Complex reasoning task"
opencode run --format json "Query"    # Raw JSON output

### Auth & Provider Management

opencode auth login                # Add/configure a provider
opencode auth list                 # List authenticated providers
opencode auth logout               # Remove a provider
opencode models                    # List all available models
opencode models anthropic          # List models for specific provider
opencode models --refresh          # Refresh models cache

### Session Management

opencode session list              # List all sessions
opencode session list -n 10        # Last 10 sessions
opencode export <session-id>       # Export session as JSON
opencode import session.json       # Import session
opencode stats                     # Token usage and cost statistics
opencode stats --days 7            # Stats for last 7 days

### Plugin & MCP Management

bunx oh-my-opencode install        # Install/configure oh-my-opencode
bunx oh-my-opencode doctor         # Diagnose configuration issues
opencode mcp list                  # List configured MCP servers
opencode mcp add                   # Add an MCP server

### Server Mode

opencode serve --port 4096         # Headless server
opencode web --port 4096           # Server with web UI
opencode attach http://localhost:4096  # Attach TUI to running server

### Built-in MCPs

Oh My OpenCode includes these MCP servers out of the box:

MCPToolPurposeExaweb_search_exaWeb search with clean LLM-ready contentContext7resolve-library-id, query-docsOfficial library/framework documentation lookupGrep.appsearchGitHubSearch real-world code examples from public GitHub repos

### Hooks

All hooks are enabled by default. Disable specific hooks via disabled_hooks config:

HookPurposetodo-continuation-enforcerForces agent to continue if it quits halfwaycontext-window-monitorMonitors and manages context window usagesession-recoveryRecovers sessions after crashessession-notificationNotifies on session eventscomment-checkerPrevents AI from adding excessive code commentsgrep-output-truncatorTruncates large grep outputstool-output-truncatorTruncates large tool outputsdirectory-agents-injectorInjects AGENTS.md from subdirectories (auto-disabled on OpenCode 1.1.37+)directory-readme-injectorInjects README.md contextempty-task-response-detectorDetects and handles empty task responsesthink-modeExtended thinking mode controlanthropic-context-window-limit-recoveryRecovers from Anthropic context limitsrules-injectorInjects project rulesbackground-notificationNotifies when background tasks completeauto-update-checkerChecks for oh-my-opencode updatesstartup-toastShows startup notification (sub-feature of auto-update-checker)keyword-detectorDetects keywords like ultrawork/ulw to trigger modesagent-usage-reminderReminds to use specialized agentsnon-interactive-envHandles non-interactive environmentsinteractive-bash-sessionManages interactive bash/tmux sessionscompaction-context-injectorInjects context during compactionthinking-block-validatorValidates thinking blocksclaude-code-hooksClaude Code compatibility hooksralph-loopRalph Loop continuation mechanismpreemptive-compactionTriggers compaction before context overflowauto-slash-commandAuto-triggers slash commandssisyphus-junior-notepadNotepad for Sisyphus-Junior subagentsedit-error-recoveryRecovers from edit errorsdelegate-task-retryRetries failed task delegationsprometheus-md-onlyEnforces Prometheus markdown-only outputstart-workHandles /start-work commandatlasAtlas orchestrator hook

### Do

Use ulw for quick autonomous tasks — just include the keyword in your prompt
Use Prometheus + /start-work for complex projects — interview-based planning leads to better outcomes
Configure categories for your providers — ensures optimal model selection instead of falling back to system default
Fire explore/librarian agents in parallel — always use run_in_background=true
Use session continuity — pass session_id for follow-up interactions with the same subagent
Let the agent delegate — Sisyphus is an orchestrator, not a solo implementer
Run bunx oh-my-opencode doctor to diagnose issues

### Don't

Don't use Atlas without /start-work — Atlas requires a Prometheus plan
Don't manually specify models for every agent — the fallback chain handles this
Don't disable todo-continuation-enforcer — it's what keeps the agent completing work
Don't use Claude Haiku for Sisyphus — Opus 4.5 is strongly recommended
Don't run explore/librarian synchronously — always background them

### When to Use This Skill

Installing or configuring oh-my-opencode
Understanding agent roles and delegation patterns
Troubleshooting model resolution or provider issues
Setting up tmux integration for visual multi-agent execution
Configuring categories for cost optimization
Understanding the ultrawork vs Prometheus workflow choice

### When NOT to Use This Skill

General OpenCode usage unrelated to oh-my-opencode plugin features
Provider authentication issues (use opencode auth directly)
OpenCode core configuration (use OpenCode docs at https://opencode.ai/docs/)

### Rules for the Agent

Package name is oh-my-opencode — NOT @anthropics/opencode or any other name
Use bunx (officially recommended) — not npx for oh-my-opencode CLI commands
Agent invocation uses --agent flag or delegate_task() — NOT @agent prefix
Never change model settings or disable features unless the user explicitly requests it
Sisyphus strongly recommends Opus 4.5 — using other models degrades the experience significantly
Categories do NOT use built-in defaults unless configured — always verify with bunx oh-my-opencode doctor --verbose
Prometheus and Atlas are always paired — never use Atlas without a Prometheus plan
Background agents should always use run_in_background=true — never block on exploration
Session IDs should be preserved and reused — saves 70%+ tokens on follow-ups
When using Ollama, set stream: false — required to avoid JSON parse errors

### Auto-Notify on Completion

Background tasks automatically notify when complete via the background-notification hook. No polling needed — the system pushes completion events. Use background_output(task_id="...") only when you need to read the result.

### Reference Documents

Configuration Reference — Complete config with all agents, categories, provider chains, hooks, and options
Troubleshooting Guide — Common issues and solutions
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: McOso
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-06T08:18:56.201Z
- Expires at: 2026-05-13T08:18:56.201Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/oh-my-opencode)
- [Send to Agent page](https://openagent3.xyz/skills/oh-my-opencode/agent)
- [JSON manifest](https://openagent3.xyz/skills/oh-my-opencode/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/oh-my-opencode/agent.md)
- [Download page](https://openagent3.xyz/downloads/oh-my-opencode)