multi-instance

A workflow for running and switching between multiple TouchDesigner instances, separate copies of the visual-development application, in one Git repository.

In plain words
What is it for?
Use it to register instances, pin a session to a named instance, switch that session, and recover the connection if the instance restarts on another port.
Why use it?
It keeps each running instance associated with its own port and lets one session switch instances without moving other sessions.

Skill for Claude CodeCodex

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 skills/dylanroscover/embody/multi-instance
Any agent
npx skills add dylanroscover/Embody --skill multi-instance
Clone the repo
git clone --depth 1 https://github.com/dylanroscover/Embody

Made for: Claude Code, Codex.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,554 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 $0.00023 $0.01554
Opus 5 $0.00012 $0.00777
Sonnet 5 $0.00005 $0.00311
Haiku 4.5 $0.00002 $0.00155

Measured 2d ago against content hash c1e5db77fde3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-instance 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.

.claude/skills/multi-instance/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Instance Workflow

Envoy supports multiple TouchDesigner instances running simultaneously in the same git repo. Each instance gets its own port, and the bridge can switch between them on demand.

Architecture

Claude Code  <-->  STDIO Bridge  <-->  Envoy (TD instance A, port 9870)
                        |
                        +---switch--->  Envoy (TD instance B, port 9871)
  • One bridge process per SESSION (spawned by each AI client's MCP client)
  • Per-session pinning - each bridge pins to an instance NAME and re-resolves its port from the registry every tick, so a pinned instance restarting on a new port still self-heals. The registry active field only seeds NEW bridges without a pin.
  • Switching is instant and session-local - switch_instance re-pins THIS session's bridge in-memory; peers are untouched unless you pass all_sessions=True (writes the registry default and bumps active_epoch, which moves every session)
  • Registration never re-routes running sessions - a new instance takes the active default slot only when it is vacant or names a dead instance

Instance Registry (.embody/envoy.json)

Each Envoy instance registers itself in .embody/envoy.json at the git root on startup:

{
  "active": "Embody-5.257",
  "td_executable": "/Applications/TouchDesigner.app",
  "instances": {
    "Embody-5.257": {
      "toe_path": "dev/Embody-5.257.toe",
      "port": 9870,
      "td_pid": 12345
    },
    "MySecondProject": {
      "toe_path": "MySecondProject.toe",
      "port": 9871,
      "td_pid": 67890
    }
  }
}
Field Purpose
active Default instance for NEWLY-spawned bridges (each bridge then pins per-session; only an active_epoch bump re-targets pinned bridges)
td_executable Path to TD app (used by launch_td)
instances.<name>.toe_path Relative path to the .toe file
instances.<name>.port Envoy HTTP port for this instance
instances.<name>.td_pid OS process ID of the TD process

Read the full file on GitHub · 155 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. 2d ago First seen · 155 lines · 23 tokens per session scan A c1e5db77fde3

Subscribe to this mod's changes

multi-instance is a skill published in the GitHub repository dylanroscover/Embody (166 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,554 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

test-quality

Test quality bar for this repo. Read when writing, reviewing, or designing tests — covers naming, abstraction level, assertions, determinism, and the process for agent-driven test work.

modelcontextprotocol/python-sdk · 40 tokens

codeact

Generate and execute code for acting with Python tools. Activate when user explicitly requests to "use the codeact skill" or similar phrases.

gradion-ai/ipybox · 30 tokens

td-apple-ops

Apple Frameworks for TouchDesigner のカスタムOP(Vision Pose / Vision Face / Vision Hand / CoreML / LLM AFM / LLM MLX / Speech Transcribe / Metal Upscale / Screen Capture 等)を使ってTouchDesignerのプロジェクトを組むときに使う。導入手順、OPの選び方、非同期OP特有の配線ルール(cookを回す・Info CHOPの読み方・Flip・Aspect Correct…

sygnalinc/Apple-Frameworks-for-TouchDesigner · 165 tokens

td-apple-plugin

TouchDesignerのネイティブカスタムOP(.plugin)としてAppleのオンデバイスフレームワーク(Vision / Core ML / Core Image / VideoToolbox / MetalFX / SpeechAnalyzer / SoundAnalysis / NaturalLanguage / FoundationModels / ScreenCaptureKit / RealityKit / MultipeerConnectivity…

sygnalinc/Apple-Frameworks-for-TouchDesigner · 158 tokens

craft

Converts Claude Code usage statistics into a Minecraft world seed with real biome correlation. Maps coding behavior to Minecraft climate parameters (messages=temperature, tools=humidity, session duration=elevation, etc.) and selects a curated seed whose spawn biome genuinely matches the profile. Use when the user…

syaor4n/seedcraft · 101 tokens

bump-dependency

Bumps a Python package dependency across Home Assistant Core integrations, regenerates core requirement files, runs verification tests and prek lint, and prepares a pull request with proper release/compare links.

home-assistant/core · 42 tokens