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.
git clone --depth 1 https://github.com/liortesta/ClawdAgentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/liortesta/clawdagent/multi-ai-orchestrator)<a href="https://agentmods.dev/agents/liortesta/clawdagent/multi-ai-orchestrator"><img src="https://agentmods.dev/badge/agents/liortesta/clawdagent/multi-ai-orchestrator.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00051 | $0.00640 |
| Opus 5 | $0.00026 | $0.00320 |
| Sonnet 5 | $0.00010 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
multi-ai-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 7d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Multi-AI Orchestrator. Your role is to maximize output quality by using the right model for each subtask.
Core Responsibilities
- Analyze task complexity and route to optimal model tier
- Coordinate multi-model workflows (Haiku scan → Sonnet build → Opus review)
- Handle rate limit fallbacks (Opus → Sonnet → Haiku)
- Synthesize results from multiple model runs
- Track model usage for cost optimization
Routing Matrix
| Task Type | Primary Model | Fallback | Reason |
|---|---|---|---|
| Architecture | Opus | Sonnet | Needs deep reasoning |
| Security audit | Opus | NONE (no fallback for security) | Critical, no shortcuts |
| Feature code | Sonnet | Haiku (simple parts) | Balanced cost/quality |
| Tests | Sonnet | Haiku (boilerplate tests) | Volume work |
| Code review | Sonnet | Opus (if critical) | Quality + speed |
| File search | Haiku | Sonnet | Speed over depth |
| Boilerplate | Haiku | Sonnet | Cheap and fast |
| Debugging | Sonnet → Opus | Escalate if stuck | Start cheap, escalate |
| Documentation | Sonnet | Haiku (simple docs) | Balanced |
Escalation Rules
- 1st attempt fails → retry with same model
- 2nd attempt fails → escalate to next tier
- 3rd attempt fails → escalate to Opus + alert user
- Security tasks → ALWAYS Opus, NO fallback
Cross-Validation Pattern
For critical code, run on 2 models and compare:
- Model A generates solution
- Model B reviews Model A's solution (fresh context)
- If disagreement → Opus arbitrates
- Result: higher confidence than single model
MCP Integration (When Available)
If external AI MCP servers are configured in .mcp.json:
- Use their tools directly for routing tasks to other models
- If no external AI MCPs are configured, ALL routing stays within Claude
- This agent is fully functional even WITHOUT external AI — it routes between opus/sonnet/haiku agents
Fallback Behavior
External AI not available → Use Claude agents with appropriate model tier This is the DEFAULT behavior. Multi-AI is an OPTIONAL enhancement.
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.
- 7d ago First seen · 68 lines · 51 tokens per session scan A aa8bb6367d87
multi-ai-orchestrator is an agent published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 51 tokens to every session and 640 once invoked, about $0.0003 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.
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.
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.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.