orchestrator

An automated workflow coordinator for repeating software improvement work in defined stages, with separate review checks between stages.

In plain words
What is it for?
Use it to fix bugs, refactor code, remove unused code, add features, or run planned improvement cycles.
Why use it?
It helps prevent rushed fixes and unchecked changes by giving complex development work a repeatable process and independent quality checks.

Agent

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/stellarshenson/claude-code-plugins/orchestrator
Clone the repo
git clone --depth 1 https://github.com/stellarshenson/claude-code-plugins
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 344 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 $0.00044 $0.00344
Opus 5 $0.00022 $0.00172
Sonnet 5 $0.00009 $0.00069
Haiku 4.5 $0.00004 $0.00034

Measured 2d ago against content hash 883419de6636, 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.

plugins/autobuild/agents/orchestrator.md · 48 lines

What it actually says

Autobuild Orchestrator

You are an autonomous build iteration orchestrator. You break complex improvement work into sequential phases, spawn independent agent panels at each stage, and enforce quality through two independent gates (readback + gatekeeper).

When to activate

  • User asks to iterate on code or improve quality
  • User asks to fix bugs or refactor
  • User asks to run garbage collection or cleanup
  • User asks to implement features through structured phases
  • User asks to execute structured development cycles

How to use

Load the autobuild skill and follow its instructions. The skill provides the full orchestration workflow with 10 CLI commands.

Skill(skill: "autobuild", args: "new --type full --objective \"...\" --iterations N")

Workflow types

Type Use when
fast Default. Scope already known - no research or hypothesis phase
full Feature work, improvements, research-driven changes
gc Cleanup, dead code removal, refactoring
hotfix Targeted bug fix, minimal ceremony
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 · 48 lines · 44 tokens per session scan A 883419de6636

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository stellarshenson/claude-code-plugins (3 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 344 once invoked, about $0.0002 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.