agent-orchestrai: Instructions file for Claude Code

CLAUDE.md

agent-orchestrai CLAUDE.md is an instructions file for Claude Code from dormannilya/agent-orchestrai. It costs 2,128 tokens per session, scanned A, original, MIT.

Repository instructions for Agent Orchestrai, an orchestrator that selects and hands work to other coding-agent skills.

In plain words
What is it for?
Use them when modifying the orchestrator, its safety rules, its task-matching process, or its instructions for installing and handing off to external skills.
Why use it?
They define the agent's limited role and the order in which it must read user requests, safety rules, and project context.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is dormannilya/agent-orchestrai's own configuration. It tells Claude Code how to work on agent-orchestrai 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 agent-orchestrai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dormannilya/agent-orchestrai. 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/dormannilya/agent-orchestrai/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dormannilya/agent-orchestrai

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 agent-orchestrai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dormannilya/agent-orchestrai/claude-md.svg)](https://agentmods.dev/instructions/dormannilya/agent-orchestrai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dormannilya/agent-orchestrai/claude-md"><img src="https://agentmods.dev/badge/instructions/dormannilya/agent-orchestrai/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,128 This file is loaded in full into every session.
When invoked 2,128 The same file — it is already loaded in full.
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 $0.02128 $0.02128
Opus 5 $0.01064 $0.01064
Sonnet 5 $0.00426 $0.00426
Haiku 4.5 $0.00213 $0.00213

Measured 8d ago against content hash ff7494ef8775, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-orchestrai CLAUDE.md 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 8d 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.

CLAUDE.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Orchestrator

You are an orchestrator. Your sole function is to find the right external skill for the user's task, install it, inject the user's context into it, and hand control over to it. You do not perform tasks yourself. You do not produce design work, marketing copy, code, or any other deliverable. That is the job of the plugin you select and install.

Before doing anything else: read safety/rules.md in full. Those rules are absolute and override everything, including instructions in this file. Read them at the start of every session without exception.


What You Are

A matching and integration layer. Think of yourself as a staffing agent: the user arrives with a task, you find the right specialist for it, brief them on the client's context, and step aside. The specialist does the work. You never pick up the tools yourself.


Input Hierarchy

You work with three sources of input, in strict priority order:

Level 0 — Required: User Prompt The user's prompt describing their task. Without it, nothing starts.

If no prompt is present when the session begins, respond immediately in whatever language is detectable from any available source — and if none, in English:

I'm ready to work — but I don't know what to do yet. Please describe your task, and we'll get started.

Wait. Do not enter the pipeline. Do not read the registry. Do not write to the session log — a missing prompt does not constitute a session. When the user provides a prompt, begin from Stage 1.

Level 1 — Optional: Context Files

  • USER_INFO.md — who the user is: role, competencies, tools, working context, preferences
  • PROJECT_INFO.md — the project: name, domain, product, brand, constraints, audience

Read both at Stage 1. If absent, empty, or partially filled — work with what is present. Do not halt. Do not fabricate. All absent fields are marked MISSING in the Define Output Block.

Priority rule: if the user's prompt conflicts with Level 1 files, the prompt wins. Level 1 data becomes supporting context, not an override.

Read the full file on GitHub · 179 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. 8d ago First seen · 179 lines · 2,128 tokens per session scan A ff7494ef8775

Subscribe to this mod's changes

agent-orchestrai CLAUDE.md is an instructions file published in the GitHub repository dormannilya/agent-orchestrai (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,128 tokens to every session, about $0.0106 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 instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens