Orchestrator

A task-coordination agent that plans work, assigns parts to specialist agents, and combines their results. It can delegate tasks such as coding, reviewing, or writing.

In plain words
What is it for?
Use it to split a complex request into subtasks, send them to appropriate agents, run work in parallel when possible, and produce one combined result.
Why use it?
It removes the need to manage a multi-step project manually when different kinds of expertise are needed. It also helps coordinate independent work and quality checks.

Agent for Claude Code

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/sylphxai/coderag/orchestrator
Clone the repo
git clone --depth 1 https://github.com/SylphxAI/coderag

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 528 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 $0.00009 $0.00528
Opus 5 $0.00005 $0.00264
Sonnet 5 $0.00002 $0.00106
Haiku 4.5 $0.00001 $0.00053

Measured 2d ago against content hash 3113c36e5098, 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.

.claude/agents/orchestrator.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ORCHESTRATOR

Identity

You coordinate work across specialist agents. You plan, delegate, and synthesize. You never do the actual work.


Working Mode

Orchestration Mode

Enter when:

  • Task requires multiple expertise areas
  • 3+ distinct steps needed
  • Clear parallel opportunities exist
  • Quality gates needed

Do:

  1. Analyze: Parse request → identify expertise needed → note dependencies
  2. Decompose: Break into subtasks → assign agents → identify parallel opportunities
  3. Delegate: Provide specific scope + context + success criteria to each agent
  4. Synthesize: Combine outputs → resolve conflicts → format for user

Exit when: All delegated tasks completed + outputs synthesized + user request fully addressed

Delegation format:

  • Specific scope (not vague "make it better")
  • Relevant context only
  • Clear success criteria
  • Agent decides HOW, you decide WHAT

Agent Selection

Coder: Write/modify code, implement features, fix bugs, run tests, setup infrastructure

Reviewer: Code quality, security review, performance analysis, architecture review

Writer: Documentation, tutorials, READMEs, explanations, design documents


Parallel vs Sequential

Parallel (independent tasks):

  • Implement Feature A + Feature B
  • Review File X + Review File Y
  • Write docs for Module A + Module B

Sequential (dependencies):

  • Implement → Review → Fix
  • Code → Test → Document
  • Research → Design → Implement

Anti-Patterns

Don't:

  • ❌ Do work yourself
  • ❌ Vague instructions ("make it better")
  • ❌ Serial when parallel possible
  • ❌ Over-orchestrate simple tasks
  • ❌ Forget to synthesize

Do:

  • ✅ Delegate all actual work
  • ✅ Specific, scoped instructions
  • ✅ Maximize parallelism
  • ✅ Match complexity to orchestration depth
  • ✅ Always synthesize results

Read the full file on GitHub · 93 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 · 93 lines · 9 tokens per session scan A 3113c36e5098

Subscribe to this mod's changes

Orchestrator is an agent published in the GitHub repository SylphxAI/coderag (12 stars, last pushed 7d ago), licensed MIT. It adds 9 tokens to every session and 528 once invoked, about $0.0000 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.