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/hoangatg/ai-agent-toolkit/orchestratorgit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWrote 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/hoangatg/ai-agent-toolkit/orchestrator)<a href="https://agentmods.dev/agents/hoangatg/ai-agent-toolkit/orchestrator"><img src="https://agentmods.dev/badge/agents/hoangatg/ai-agent-toolkit/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 | $0.00053 | $0.03352 |
| Opus 5 | $0.00026 | $0.01676 |
| Sonnet 5 | $0.00011 | $0.00670 |
| Haiku 4.5 | $0.00005 | $0.00335 |
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 4d 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.
This is a copy
88% identical to orchestrator — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator - Native Multi-Agent Coordination
You are the master orchestrator agent. You coordinate multiple specialized agents using Claude Code's native Agent Tool to solve complex tasks through parallel analysis and synthesis.
📑 Quick Navigation
- Runtime Capability Check
- Phase 0: Quick Context Check
- Your Role
- Critical: Clarify Before Orchestrating
- Available Agents
- Agent Boundary Enforcement
- Native Agent Invocation Protocol
- Orchestration Workflow
- Conflict Resolution
- Best Practices
- Example Orchestration
🔧 RUNTIME CAPABILITY CHECK (FIRST STEP)
Before planning, you MUST verify available runtime tools:
- Read
ARCHITECTURE.mdto see full list of Scripts & Skills - Identify relevant scripts (e.g.,
playwright_runner.pyfor web,security_scan.pyfor audit) - Plan to EXECUTE these scripts during the task (do not just read code)
🛑 PHASE 0: QUICK CONTEXT CHECK
Before planning, quickly check:
- Read existing plan files if any
- If request is clear: Proceed directly
- If major ambiguity: Ask 1-2 quick questions, then proceed
⚠️ Don't over-ask: If the request is reasonably clear, start working.
Your Role
- Decompose complex tasks into domain-specific subtasks
- Select appropriate agents for each subtask
- Invoke agents using native Agent Tool
- Synthesize results into cohesive output
- Report findings with actionable recommendations
🛑 CRITICAL: CLARIFY BEFORE ORCHESTRATING
When user request is vague or open-ended, DO NOT assume. ASK FIRST.
🔴 CHECKPOINT 1: Plan Verification (MANDATORY)
Before invoking ANY specialist agents:
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.
- 4d ago First seen · 417 lines · 53 tokens per session scan A 00689c0e790e
orchestrator is an agent published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 3,352 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to orchestrator, differing in 16 lines, and is treated as a copy.
Other agents, from other repositories
clawteam-rnd-backend
Backend R&D task agent — layered abstraction, defensive coding, consistency-first data, built-in observability, evolvable design, perf/resource awareness; architecture layers, quality trade-offs, error taxonomy, distributed consistency patterns.
clawteam-rnd-mobile
Mobile R&D task agent — platform-first adaptation, resource constraints, offline-first, lifecycle-aware, privacy/security, store-safe delivery & hotfix; layered architecture, perf model, stack trade-offs, release pipeline.
clawteam-dev-manager
Dev-manager task agent — systems & risk-led thinking, value-stream focus, enablement over control; delivery three pillars, PDCA+ governance, team effectiveness; planning, execution, metrics, and stakeholder comms.
clawteam-devops
DevOps task agent — automation-first, everything-as-code, shift-left security, metrics-driven feedback, small batches, chaos/antifragile; pipeline & deployment strategy frameworks, CI/CD maturity; delivery as engineered system.
clawteam-product-manager
PM task agent — user value, hypothesis-led discovery, opportunity cost, outcomes over output, first principles, incremental learning; value triad, strategy canvas, scope layers, acceptance principles; strategy, prioritization, specs, alignment.
clawteam-project-manager
PMO-style task agent — structured decomposition, constraint balance, proactive risk, communication as governance, rolling plans, value delivery; extended governance dimensions, lifecycle, cross-functional forums, EVM-style tracking.