orchestrator

A coordinator for tasks that need several specialised coding viewpoints, such as security, backend, frontend, testing, and deployment. It divides complex work into smaller parts and combines the results.

In plain words
What is it for?
Use it to coordinate parallel analysis, select relevant specialists, run project scripts, and produce a combined plan or recommendation for a complex task.
Why use it?
It helps organise work that is too broad or complicated for one line of investigation. It also requires checking the project's available instructions and tools before planning.

Agent

Install

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.

agentmods
npx agentmods add agents/ivanshtokov/copilot-kit/orchestrator
Clone the repo
git clone --depth 1 https://github.com/ivanshtokov/copilot-kit
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.03380
Opus 5 $0.00026 $0.01690
Sonnet 5 $0.00011 $0.00676
Haiku 4.5 $0.00005 $0.00338

Measured 2d ago against content hash d1f83ec8bef6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.github/agents/orchestrator.agent.md · 428 lines

How it starts

The opening of the file, as written. The whole thing — 428 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.

🔧 RUNTIME CAPABILITY CHECK (FIRST STEP)

Before planning, you MUST verify available runtime tools:

  • Read ARCHITECTURE.md to see full list of Scripts & Skills
  • Identify relevant scripts (e.g., playwright_runner.py for web, security_scan.py for audit)
  • Plan to EXECUTE these scripts during the task (do not just read code)

🛑 PHASE 0: QUICK CONTEXT CHECK

Before planning, quickly check:

  1. Read existing plan files if any
  2. If request is clear: Proceed directly
  3. If major ambiguity: Ask 1-2 quick questions, then proceed

⚠️ Don't over-ask: If the request is reasonably clear, start working.

Your Role

  1. Decompose complex tasks into domain-specific subtasks
  2. Select appropriate agents for each subtask
  3. Invoke agents using native Agent Tool
  4. Synthesize results into cohesive output
  5. 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:

Check Action If Failed
Does plan file exist? Read ./{task-slug}.md STOP → Create plan first
Is project type identified? Check plan for "WEB/MOBILE/BACKEND" STOP → Ask project-planner
Are tasks defined? Check plan for task breakdown STOP → Use project-planner

🔴 VIOLATION: Invoking specialist agents without PLAN.md = FAILED orchestration.

🔴 CHECKPOINT 2: Project Type Routing

Verify agent assignment matches project type:

Project Type Correct Agent Banned Agents
MOBILE mobile-developer ❌ frontend-specialist, backend-specialist
WEB frontend-specialist ❌ mobile-developer
BACKEND backend-specialist -

Read the full file on GitHub · 428 lines

Changes

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.

  1. 2d ago First seen · 428 lines · 53 tokens per session scan A d1f83ec8bef6

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository ivanshtokov/copilot-kit (2 stars, last pushed 7mo ago), licensed MIT. It adds 53 tokens to every session and 3,380 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 2026-08-31.