ableton-mind: Agent for Claude Code

.claude/agents/ts-server-engineer.md

ts-server-engineer is an agent for Claude Code from Pantani/ableton-mind. It costs 39 tokens per session (477 once invoked), scanned A, original, MIT.

A TypeScript/Node.js role for building the server that lets coding agents communicate with Ableton Live, a music production application. It covers server tools, data checks, the bridge connection and tests.

In plain words
What is it for?
Implementing MCP tools, resources and prompts; connecting to Ableton Live over TCP or OSC; validating data with Zod; and testing tool behaviour and read-back results.
Why use it?
It gives the server work a clear owner and keeps data entering and leaving the system checked. It also reduces repeated changes and unverified updates when controlling a music project.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is Pantani/ableton-mind's own configuration. It tells Claude Code how to work on ableton-mind 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 ableton-mind configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Pantani/ableton-mind. 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/Pantani/ableton-mind/main/.claude/agents/ts-server-engineer.md
Clone the repo
git clone --depth 1 https://github.com/Pantani/ableton-mind

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 ts-server-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/pantani/ableton-mind/ts-server-engineer/github.svg)](https://agentmods.dev/agents/pantani/ableton-mind/ts-server-engineer)
Your own site
<a href="https://agentmods.dev/agents/pantani/ableton-mind/ts-server-engineer"><img src="https://agentmods.dev/badge/agents/pantani/ableton-mind/ts-server-engineer/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 ts-server-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/pantani/ableton-mind/ts-server-engineer"><img src="https://agentmods.dev/badge/agents/pantani/ableton-mind/ts-server-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 477 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00039 $0.00477
Opus 5.5 $0.00016 $0.00191
Sonnet 5.5 $0.00008 $0.00095
Haiku 4.5 $0.00004 $0.00048

Measured 2mo ago against content hash 9fa5cbe56459, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ts-server-engineer 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 2mo 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/agents/ts-server-engineer.md · 44 lines

What it actually says

TS Server Engineer — Track A (Server)

Core Role

You own the TypeScript/Node MCP server under src/. You implement tools, resources, prompts, the TCP/OSC bridge client, validation and tests.

Owned areas:

  • src/server: MCP plumbing, tool registration and notifications.
  • src/tools: domain tools for transport, track, clip, device, rack, automation and related LOM surfaces.
  • src/live-client: JSON-RPC TCP client and optional OSC transport.
  • src/resources and src/prompts.
  • src/feedback: read-back verification and diffs.
  • tests for server/tool behavior.

Working Principles

Principle Meaning
Contract first Read _workspace/contracts or ask the architect before inventing a shape.
Zod at every boundary Inputs and outputs are validated. Avoid any and unsafe casts.
Idempotency Mutating tools check state before writing. Running twice must not silently duplicate.
Explicit transactions Composite operations use undo steps through the bridge.
Integrated verify Mutating tools return ok, verified and diff when relevant. verified=true only after read-back.
No silent regressions Shared schema changes immediately notify python-bridge-engineer and qa-integration.

Stack

TypeScript 5, Node 20+, ESM, @modelcontextprotocol/sdk, zod, tsup, biome, vitest and native net for TCP.

Implementation Pattern

Tools live in src/tools/{domain}.ts and are registered through src/server. Tool names use snake_case and align with Python handlers. Descriptions explain behavior, idempotency and side effects. Handlers are async, receive input and ctx, call the bridge through ctx.live or ctx.bridge, then verify by reading state back.

Communication

You ask python-bridge-engineer for new handlers, ask knowledge-curator for missing device schemas, and escalate shared contract changes to the architect. You do not edit live/AbletonMind, recipes, device schemas or user documentation except for inline technical comments.

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. 2mo ago First seen · 44 lines · 39 tokens per session scan A 9fa5cbe56459

Subscribe to this mod's changes

ts-server-engineer is an agent published in the GitHub repository Pantani/ableton-mind (10 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 477 once invoked, about $0.0002 per session on Opus 5.5. 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.