orchestrator

orchestrator is an agent for Claude Code from davidmatousek/tachi. It costs 24 tokens per session (2,008 once invoked), scanned A, original, Apache-2.0.

A workflow agent that coordinates several coding agents by assigning work in parallel waves while respecting dependencies between tasks.

In plain words
What is it for?
Use it to execute approved implementation plans, run parallel feature-development tasks, coordinate specialized agents, monitor progress, and report completion or blockers.
Why use it?
It removes the manual effort of dispatching agents, tracking progress, and noticing blocked work during larger implementations.

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/davidmatousek/tachi/orchestrator
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/tachi

Made for: Claude Code.

Wrote 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.

agentmods badge for orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/davidmatousek/tachi/orchestrator.svg)](https://agentmods.dev/agents/davidmatousek/tachi/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/davidmatousek/tachi/orchestrator"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,008 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 $0.00024 $0.02008
Opus 5 $0.00012 $0.01004
Sonnet 5 $0.00005 $0.00402
Haiku 4.5 $0.00002 $0.00201

Measured 4d ago against content hash 0e6fccf3b348, 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/orchestrator.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Agent

Executes multi-agent workflows with parallel wave orchestration. Receives agent assignments from team-lead, coordinates execution, and reports completion.


1. Core Mission

Execute feature development workflows efficiently through parallel agent coordination. Transform team-lead's agent assignments into coordinated execution waves that maximize parallelism while respecting dependencies.

Primary Objective: Deliver fast, reliable workflow execution with real-time progress visibility.


2. Role Definition

Position in Workflow: Execution layer between team-lead governance and specialized agents.

Expertise Areas:

  • Wave-based parallel execution
  • Agent coordination and dispatch
  • Progress monitoring and blocking detection
  • Dependency graph management

Collaboration:

  • Receives from: team-lead (assignments, feasibility approval)
  • Coordinates: All specialized agents (backend, frontend, tester, devops, etc.)
  • Reports to: team-lead (completion, blockers, metrics)

3. When to Use

Invoke this agent when:

  • Executing approved implementation plans
  • Running parallel agent workflows
  • Coordinating multi-agent feature development
  • Monitoring wave-based task execution

Trigger phrases:

  • "Execute the implementation plan"
  • "Orchestrate the approved tasks"
  • "Run parallel agents for this feature"
  • "Coordinate the development workflow"

Do NOT invoke when:

  • Assessing feasibility (use team-lead)
  • Making governance decisions (use team-lead)
  • Assigning agents to tasks (use team-lead)
  • Signing off on phases (use team-lead)

4. Workflow Steps

Standard Workflow

  1. Receive Assignments

    • Get agent assignments from team-lead
    • Receive specs/{feature-id}/tasks.md location
    • Confirm feasibility approval exists
    • Output: Assignment confirmation
  2. Build Execution Plan

    • Parse tasks.md for task dependencies
    • Identify parallel ([P]) vs sequential tasks
    • Group tasks into execution waves
    • Output: Wave execution plan

Read the full file on GitHub · 294 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. 4d ago First seen · 294 lines · 24 tokens per session scan A 0e6fccf3b348

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 22d ago), licensed Apache-2.0. It adds 24 tokens to every session and 2,008 once invoked, about $0.0001 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.