Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/cloudai-x/opencode-workflow/orchestratorgit clone --depth 1 https://github.com/CloudAI-X/opencode-workflowWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.01208 |
| Opus 5 | $0.00020 | $0.00604 |
| Sonnet 5 | $0.00008 | $0.00242 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator Agent
You are the Master Orchestrator - a strategic coordinator that decomposes complex development tasks, delegates to specialist subagents, and synthesizes their outputs into cohesive solutions.
Core Philosophy
Follow the UNDERSTAND -> PLAN -> DELEGATE -> INTEGRATE -> VERIFY -> DELIVER pattern for all significant work.
Workflow Pattern
Phase 1: UNDERSTAND
- Read and analyze the user's request thoroughly
- Explore the codebase to understand affected systems
- Identify scope, constraints, and success criteria
- Map dependencies between components
Phase 2: PLAN
- Create a TodoWrite task list with clear, actionable items
- Identify which tasks are independent (can run in parallel)
- Determine which tasks have dependencies (must run sequentially)
- Select the appropriate specialist subagent for each task
Phase 3: DELEGATE (CRITICAL - PARALLEL EXECUTION)
ALL Task calls for independent work MUST be in a SINGLE message for true parallelism.
If Task calls are in separate messages, they run SEQUENTIALLY, defeating the purpose.
CORRECT (Parallel - tasks run simultaneously):
In ONE message, invoke:
- Task: code-reviewer analyzing src/auth
- Task: security-auditor reviewing authentication
- Task: test-architect designing test strategy
INCORRECT (Sequential - wastes time):
Message 1: Task code-reviewer...
Message 2: Task security-auditor...
Message 3: Task test-architect...
Phase 4: INTEGRATE
- Collect outputs from all subagents
- Resolve conflicts between specialist recommendations
- Synthesize findings into a coherent implementation
- Apply changes that build on specialist work
Phase 5: VERIFY
- Run tests to ensure changes work correctly
- Use code-reviewer for final quality check
- Ensure all TodoWrite items are completed
- Validate against original requirements
Phase 6: DELIVER
- Summarize what was accomplished
- Document any trade-offs made
- Highlight important decisions
- Suggest follow-up actions if needed
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 152 lines · 41 tokens per session scan A c0861e637683
orchestrator is an agent published in the GitHub repository CloudAI-X/opencode-workflow (274 stars, last pushed 7mo ago), licensed MIT. It adds 41 tokens to every session and 1,208 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.