What is orchestration?

A workflow for coordinating research or implementation work between coding agents such as Claude and Codex. It chooses a worker based on the available coding environment and can prepare handoff instructions for another session.

Use it to delegate read-only investigation, planning, or implementation, launch the appropriate worker, and pass decision-complete instructions to a later session.

It removes the need to manually decide which agent should do each delegated task or to write incomplete handoff notes. It also keeps delegated work aligned with the user's choice of agent.

orchestration — Skill for Claude Code and Codex by PaulRBerg

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 PaulRBerg/agent-skills --skill orchestration

Clone the repo

git clone --depth 1 https://github.com/PaulRBerg/agent-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/paulrberg/agent-skills/orchestration/github.svg)](https://agentmods.dev/skills/paulrberg/agent-skills/orchestration)

Your own site

<a href="https://agentmods.dev/skills/paulrberg/agent-skills/orchestration"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/orchestration/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/paulrberg/agent-skills/orchestration"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,671 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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.05671
Opus 5.5	$0.00021	$0.02268
Sonnet 5.5	$0.00010	$0.01134
Haiku 4.5	$0.00005	$0.00567

Measured 1mo ago against content hash 827a451635d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

orchestration 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 1mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/run-codex-agent.sh, scripts/select-model.py, scripts/watch-codex-wave.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/orchestration/SKILL.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestration

This skill delegates read-only investigation or plans and implements requested work within the current session. Task-handoff writes a decision-complete file for a fresh, separate session. Use it when work continues later or elsewhere. Use an in-session handoff skill to implement requested work now.

If a slash or dollar invocation already supplied these instructions in the conversation, follow them directly. In that case, do not invoke this skill again through a skill tool.

Follow the shared contract below. Select the worker family separately from the host that runs this conversation.

Host and Worker Selection

Identify the host from its callable tools. Codex exposes spawn_agent, wait_agent, send_message, and followup_task. Claude Code exposes Agent and Bash. Do not infer the host from environment variables, process ancestry, or a requested worker name. If neither surface identifies the host, classify it as another harness and use a CLI route.

Default to Claude workers in Claude Code. Default to Codex workers in Codex and every other harness. An explicit user choice overrides this default. Apply that choice to research and implementation unless the user limits its scope. A named model also selects its family: Sonnet or Opus selects Claude, and a GPT model selects Codex. Preserve an exact requested model, custom agent name, or effort instead of replacing it with a default tier.

Select the route from the actual host and requested worker family. Read the selected reference completely before launch:

Host	Worker family	Route
Claude Code	Claude (default)	Native Claude
Codex	Codex (default)	Native Codex
Claude Code	Codex (explicit choice)	Claude to Codex
Codex	Claude (explicit choice)	Codex to Claude
Other harness	Codex (default)	Codex CLI
Other harness	Claude (explicit choice)	Claude CLI

Read the full file on GitHub · 382 lines

Files

What ships with it

12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed · +13 lines 827a451635d2
1mo ago First seen · 369 lines · 52 tokens per session scan A 4d8e1a7551f5

Subscribe to this mod's changes

orchestration is a skill published in the GitHub repository PaulRBerg/agent-skills (104 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 5,671 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-07.

Building agents agent-skills ai-agents

orchestration next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
orchestrationPaulRBerg/agent-skills	Skill	104	2d ago	MIT	A	52	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	2d ago	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code