Agent Claude Code
Audits tdmcp refactor and test-hardening opportunities: coverage gaps, weak assertions, complex files, dependency boundaries, untested CLI/config/tool paths, bridge-adjacent tests, and safe refactor waves.
TouchDesigner MCP server, describe a visual to Claude, Cursor or Codex and it builds a real, playable node network (audio-reactive, generative, particle, 3D, feedback) with live knobs + MIDI/OSC/DMX, then checks for errors and previews its own work.
This repository also configures its own agents. See what tdmcp tells them →
Agent Claude Code
Audits tdmcp refactor and test-hardening opportunities: coverage gaps, weak assertions, complex files, dependency boundaries, untested CLI/config/tool paths, bridge-adjacent tests, and safe refactor waves.
Agent Claude Code
Audits tdmcp security and safety: bridge auth, raw Python execution, env redaction, secrets, npm/package supply chain, Docker/CI, local LLM/Telegram trust boundaries, and MCP packaging. Use in full quality audits and security follow-ups.
Agent Claude Code
Worker that builds exactly ONE new tdmcp tool in isolation — creates only its two new files (the tool file with XImpl + registerX, and its offline msw unit test) and never edits any shared file. Spawned once per tool, in parallel, by tdmcp-feature-lead. Use for implementing a single new tdmcp tool to a precise spec.
Agent Claude Code
Audits tdmcp usability and workflow quality: first-run setup, CLI help/errors, docs-to-command parity, local copilot flows, doctor/fix behavior, recipe validation feedback, and artist-facing failure modes.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: