orchestrator

orchestrator is a skill for Claude Code from pranav8494/team-of-agents. It costs 66 tokens per session (4,453 once invoked), scanned A, original, MIT.

A coordinator for choosing and directing specialist coding-agent roles. It breaks a broad request into smaller tasks, assigns suitable specialists, and combines their results.

In plain words
What is it for?
Planning complex tasks, selecting specialists for engineering or product work, dispatching parallel subtasks, and synthesising their findings.
Why use it?
It helps organise work that spans several technical or product areas. It also makes the proposed work and required approvals clear before actions are taken.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the team-of-agents plugin — 18 skills, 17 agents, 1 hook shipped together

Good fit Planning complex tasks, selecting specialists for engineering or product work, dispatching parallel subtasks, and synthesising their findings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pranav8494/team-of-agents/orchestrator
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.

Any agent
npx skills add pranav8494/team-of-agents --skill orchestrator
Clone the repo
git clone --depth 1 https://github.com/pranav8494/team-of-agents

Made for: Claude Code.

Or install team-of-agents, the plugin that ships this one along with the rest of its 18 skills, 17 agents, 1 hook.

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/skills/pranav8494/team-of-agents/orchestrator/github.svg)](https://agentmods.dev/skills/pranav8494/team-of-agents/orchestrator)
Your own site
<a href="https://agentmods.dev/skills/pranav8494/team-of-agents/orchestrator"><img src="https://agentmods.dev/badge/skills/pranav8494/team-of-agents/orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/pranav8494/team-of-agents/orchestrator"><img src="https://agentmods.dev/badge/skills/pranav8494/team-of-agents/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00066 $0.04453
Opus 5 $0.00033 $0.02227
Sonnet 5 $0.00013 $0.00891
Haiku 4.5 $0.00007 $0.00445

Measured 12d ago against content hash db85a0c46d97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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.

skills/orchestrator/SKILL.md · 403 lines

How it starts

The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator

What You Do

You are the planning and dispatch layer for the team-of-agents. When invoked, you do not solve problems yourself, you understand the request, decompose it into subtasks, assign the right specialists, dispatch them as subagents, and synthesise their output into a unified result.

You separate planning from execution. You never dispatch an agent without first showing the user a work plan and getting confirmation for any actions that write files, run commands, or access external resources.


Available Specialists

The table below is the authoritative specialist list. Refer to it when selecting agents.

Engineering

Specialist Best For
backend-engineer APIs, databases, microservices, authentication, server-side logic
kotlin-backend-engineer Kotlin/Spring Boot, fintech backend, Spring Security, JVM architecture
frontend-designer UI components, React, CSS, design systems, accessibility, web performance
fintech-frontend-engineer React/Tailwind in fintech, payment UIs, financial data display, Core Web Vitals
senior-engineer Architecture review, cross-cutting technical decisions, refactoring strategy
devex CI/CD pipelines, developer tooling, build optimisation, local dev setup
sre SLOs/error budgets, production observability, incident response, postmortems, PRRs, toil, Kubernetes/Terraform, chaos engineering
kotlin-code-reviewer Kotlin/Java PR review, Spring Boot correctness, JVM idioms, migration review
frontend-code-reviewer Frontend PR review, React patterns, TypeScript strictness, accessibility audit
qa-engineer Test plans, test automation, edge cases, quality standards

Product

Specialist Best For
product-manager Discovery, requirements, user stories, roadmaps, prioritisation
project-manager Delivery planning, sprint execution, RAID logs, milestones, status reports
ux-researcher User research, personas, journey maps, usability testing
data-analyst Data analysis, SQL, metrics, charts, insights from data

Read the full file on GitHub · 403 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. 12d ago First seen · 403 lines · 66 tokens per session scan A db85a0c46d97

Subscribe to this mod's changes

orchestrator is a skill published in the GitHub repository pranav8494/team-of-agents (7 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 4,453 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.

Related

Other skills, from other repositories

loop-setup

Session 0. Sets up the loop in this project - detects the stack, checks which connections actually work (git, database, browser, payments sandbox), asks the few decisions only the owner can make, and writes the .loop/ files. Run this once per project, before any planning or building.

cbdreamer11/CB-loop-kit-claude-plugin · 65 tokens

loop-plan

The planning session. Turns a goal into an ordered list of thin complete slices, decides which role and model runs each following session, and writes it all to the plan file. Use at the start of an epic, before any code.

cbdreamer11/CB-loop-kit-claude-plugin · 50 tokens

tasks

Turn an approved SPEC.md into a complete TASKS.md (phases, parallel tracks, dependency map), then create matching GitHub issues, a GitHub Project board, and empty-directory scaffolding from the spec's package layout. Use whenever the user invokes /ank:tasks, says "break this into tasks", "create the issues", "wire up…

ananthanandanan/skills · 138 tokens

visualise-plan

Produce a visual HTML implementation plan for a feature BEFORE writing any code. Use this skill whenever the user invokes /ank:visualise-plan, asks for an "implementation plan", says "plan this out before you build it", asks you to "visualise the plan", or otherwise signals they want to review the approach as a…

ananthanandanan/skills · 142 tokens

review-board

Generate a single-file HTML "story-paced" walkthrough of a finished feature for human code review. Use after completing a feature or merging a PR — produces docs/review/ .html with sidebar nav, Why/Tradeoff/Deferred callouts, status pills, and a reviewer's checklist.

ananthanandanan/skills · 62 tokens

no-yap

Answer in ASD-STE100 Simplified Technical English — the numbered-clause, one-idea-per-sentence style of an aircraft maintenance manual — instead of a wall of prose. Works for any expert domain — software, biology, physics, medicine, law, finance, aerospace. Use whenever the user invokes /ank:no-yap, or says "explain…

ananthanandanan/skills · 154 tokens