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.
npx agentmods add instructions/oxgeneral/orch/claude-mdgit clone --depth 1 https://github.com/oxgeneral/ORCHWhat 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 | $0.01725 | $0.01725 |
| Opus 5 | $0.00863 | $0.00863 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
ORCH 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 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Positioning
ORCH is an AI agent runtime — not just a CLI tool. The core engine (domain + application + infrastructure) has zero dependencies on CLI/TUI layers. The npm package @oxgeneral/orch exports the full engine API via src/index.ts, enabling programmatic use from any Node.js application.
User-facing messaging: "Turn your AI tools into a coordinated engineering team" Technical category: "AI agent runtime" Internal architecture term: "ORCH Engine"
Commands
npm run build # Build ESM + DTS bundles (tsup)
npm run dev # Run via tsx (no build needed)
npm test # Run all tests (vitest)
npm test -- test/unit/application/orchestrator-resilience.test.ts # Single file
npm test -- --grep "state machine" # By pattern
npm run typecheck # tsc --noEmit (strict mode)
npm run coverage # Tests with coverage report
Release: ./scripts/release.sh patch|minor|major && git push && git push --tags
Architecture
Layered DDD with dependency injection — no frameworks, no decorators.
Domain (models, state machine, errors)
↓
Application (services, orchestrator, event bus)
↓
Infrastructure (adapters, file storage, process manager, templates, workspaces)
↓
CLI (Commander.js) / TUI (Ink/React)
Container (DI)
src/container.ts defines two tiers:
- LightContainer: stores + services only — used by read-only commands (task, agent, logs, config, context, msg, goal, team, status)
- Container (extends Light): + orchestrator + adapters + ProcessManager + LiquidJS — used by run, tui, doctor
The CLI entry point (src/bin/cli.ts) determines which tier to build based on the subcommand, then lazy-imports only the needed command module.
State Machine
src/domain/transitions.ts — tasks flow through: todo → in_progress → review → done, with retrying and failed branches. All transitions validated by canTransition(). Terminal statuses: done, failed, cancelled.
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.
- 2d ago First seen · 149 lines · 1,725 tokens per session scan A 468f7be22338
ORCH CLAUDE.md is an instructions file published in the GitHub repository oxgeneral/ORCH (155 stars, last pushed 1mo ago), licensed MIT. It adds 1,725 tokens to every session, about $0.0086 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 2026-08-30.
Other instructions, from other repositories
oh-my-agent AGENTS.md
Instructions for first-fluke/oh-my-agent, covering oh-my-agent, architecture, per-agent dispatch, code search and workflows.
oh-my-subagents AGENTS.md
Instructions for ringlochid/oh-my-subagents, covering oh my subagents coding agent contract, product purpose, design philosophy, principles and authority split.
dos-kernel CLAUDE.md
Instructions for anthony-chaudhary/dos-kernel, covering dos — the dispatch operating system, the layering — keep these apart, the syscall abi, install & test and dos on dos — dogfood the kernel here.
PuPu CLAUDE.md
Instructions for haoxiang-xu/PuPu, covering gitnexus — code intelligence, always do, never do, resources and cli.
dos-kernel GEMINI.md
Instructions for anthony-chaudhary/dos-kernel, covering dos — the part that doesn't believe the agents, the rule, why this matters and setup.
rondoflow CLAUDE.md
Instructions for rondoflow/rondoflow, covering rondoflow, project overview, tech stack, development and setup.