orchestrator: Skill for Claude Code

.claude/skills/orchestrator-guide/SKILL.md

orchestrator-guide is a skill for Claude Code from c9r-io/orchestrator. It costs 159 tokens per session (2,866 once invoked), scanned C, original, MIT.

A reference for using Agent Orchestrator, a command-line tool for automating software-development workflows with agents. It covers resource files, workflow steps, commands, and the daemon that runs jobs for the command-line client.

In plain words
What is it for?
Use it when writing YAML definitions, creating workflow pipelines, configuring agents or secrets, running orchestrator commands, and writing expression-based workflow conditions.
Why use it?
It helps developers find current command syntax and understand how the client, daemon, and workflow definitions fit together. It also explains where to look before relying on static examples.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is c9r-io/orchestrator's own configuration. It tells Claude Code how to work on orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to c9r-io/orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/c9r-io/orchestrator/main/.claude/skills/orchestrator-guide/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/c9r-io/orchestrator

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-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/c9r-io/orchestrator/orchestrator-guide/github.svg)](https://agentmods.dev/skills/c9r-io/orchestrator/orchestrator-guide)
Your own site
<a href="https://agentmods.dev/skills/c9r-io/orchestrator/orchestrator-guide"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/orchestrator-guide/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-guide

Your own site · 80×15
<a href="https://agentmods.dev/skills/c9r-io/orchestrator/orchestrator-guide"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/orchestrator-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,866 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00159 $0.02866
Opus 5 $0.00079 $0.01433
Sonnet 5 $0.00032 $0.00573
Haiku 4.5 $0.00016 $0.00287

Measured 9d ago against content hash 5e61a1043fd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

orchestrator-guide scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/c9r-io/orchestrator/main/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/c9r-io/orchestrator/main/install.sh | sh
.claude/skills/orchestrator-guide/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Orchestrator Guide

CLI Command Reference (Dynamic)

Before reading static documentation, query the orchestrator itself:

orchestrator guide                         # full categorized command reference
orchestrator guide task                    # filter by command name
orchestrator guide --category resource     # filter by category
orchestrator guide --format json           # machine-readable output

The guide subcommand outputs up-to-date command descriptions with usage examples, grouped by functional category. Use it as your primary CLI reference.

Architecture (Client/Server)

The orchestrator uses a client/server model over gRPC:

  • orchestratord — daemon binary (gRPC server + embedded worker pool). Listens on UDS (~/.orchestratord/orchestrator.sock) by default, or TCP with --bind.
  • orchestrator — thin CLI client binary that forwards all commands to the daemon via gRPC.

Install via the one-line installer or download from GitHub Releases:

curl -fsSL https://raw.githubusercontent.com/c9r-io/orchestrator/main/install.sh | sh

Start the daemon first, then use the CLI:

# Start daemon (standalone binary, not a CLI subcommand)
orchestratord --foreground --workers 2           # foreground (recommended for monitoring)
nohup orchestratord --foreground --workers 2 &   # background via nohup
orchestratord --bind 0.0.0.0:9090 --workers 4   # TCP instead of UDS

# Monitor daemon
ps aux | grep orchestratord | grep -v grep       # check process

# Stop daemon
kill <pid>                                        # graceful SIGTERM

Core Workflow

  1. Start the daemon: orchestratord --foreground --workers 2
  2. orchestrator init — initialize orchestrator runtime (creates ~/.orchestratord/ with DB, secrets, etc.)
  3. orchestrator apply -f manifest.yaml --project <name> — load resources (daemon atomically hot-reloads an ArcSwap config snapshot, no restart needed)
  4. orchestrator task create --name X --goal Y --workflow Z --project <name> — create and run (auto-enqueues to worker)
  5. orchestrator task info <id> / task trace <id> / task logs <id> — inspect results

Read the full file on GitHub · 292 lines

Files

What ships with it

4 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.

  1. 9d ago First seen · 292 lines · 159 tokens per session scan C 5e61a1043fd5

Subscribe to this mod's changes

orchestrator-guide is a skill published in the GitHub repository c9r-io/orchestrator (21 stars, last pushed 7d ago), licensed MIT. It adds 159 tokens to every session and 2,866 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

recall_ai

Use recall.ai to record video meetings, retrieve transcripts, and access recordings. Use when the user wants to record a meeting, get a transcript, summarize a call, or access meeting audio/video.

mathematic-inc/earl · 43 tokens

claude-code-expert

Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agentes, permissoes e integracao com ecossistemas.

aAAaqwq/AGI-Super-Team · 59 tokens

compact-now

Operator-triggered proactive compaction — Chrono externalizes load-bearing state (active decisions, open tasks, next action) to a snapshot + a durable Vault learning note before invoking Claude Code's native /compact, then resumes from the snapshot. Use when the operator says "/compact-now" / "compact now" or when…

mtarcure/claude-vibe-squad · 82 tokens

openrig-herdr

Use when opening OpenRig fleet terminals as a herdr wall — turning a rig, pod, mission, slice, or saved view into live interactive agent tiles via rig terminal, watching another rig read-only, or driving herdr on an agent's request ("open all my rigs + a mission as views"). Covers the rig terminal open|views|status…

mvschwarz/openrig · 132 tokens

slack

Read bounded Slack search and thread evidence, plan an exact reply, and deliver an approved reply through any compatible Slack binding with stable-message readback.

runxhq/runx · 32 tokens