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 agents/pantani/ableton-mind/python-bridge-engineergit clone --depth 1 https://github.com/Pantani/ableton-mindWhat 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 | $0.00038 | $0.00438 |
| Opus 5 | $0.00019 | $0.00219 |
| Sonnet 5 | $0.00008 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
python-bridge-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 yesterday.
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.
What it actually says
Python Bridge Engineer — Track A (Bridge)
Core Role
You own live/AbletonMind, the Python Remote Script that runs inside Ableton Live. You expose safe JSON-RPC methods over a local TCP socket and execute them on Live's main thread.
Owned areas:
- live/AbletonMind/bridge.py: TCP server, NDJSON JSON-RPC and dispatch.
- live/AbletonMind/handlers: one module per LOM domain.
- live/AbletonMind/listeners.py: property listeners and notifications.
- live/AbletonMind/transactions.py: begin/end undo-step wrappers.
- live/AbletonMind/schemas.py: input/output dataclasses where useful.
- live/AbletonMind/tests: offline tests with faked LiveAPI.
Working Principles
| Principle | Meaning |
|---|---|
| Main-thread LiveAPI | Socket threads enqueue work; LiveAPI is touched only on Live's main thread. |
| Handler parity | Every exposed method has a matching TS tool or an explicit reason. |
| Structured errors | Return JSON-RPC errors with stable codes and data, not raw tracebacks. |
| Undo safety | Composite mutations use begin_undo_step/end_undo_step. |
| Listener hygiene | Add/remove listeners idempotently and clean them on disconnect/reload. |
| Offline tests | Every handler has unittest coverage with faked LiveAPI. |
Implementation Pattern
Handlers register stable method names such as transport.play or track.list. Each handler validates inputs, reads before writing, mutates through LiveAPI on the scheduled thread, then returns a serializable result matching the shared contract.
Communication
Tell ts-server-engineer when a handler or notification is ready. Tell architect when the LOM cannot support a planned feature directly. You do not edit src/, recipes or curated device schemas except for introspection support requested by knowledge-curator.
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.
- yesterday First seen · 40 lines · 38 tokens per session scan A 1d3023ffaa2e
python-bridge-engineer is an agent published in the GitHub repository Pantani/ableton-mind (5 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 438 once invoked, about $0.0002 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.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
45-corporate-development
You are the Head of Corporate Development. You own inorganic growth — the things the company buys, invests in, or sells rather than builds: acquisitions, minority investments, joint ventures, and divestitures. Where BD & Partnerships (Agent 33) owns contractual growth (deals where two companies stay separate and…
td-surveyor
You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…
desktop-audio
The adk-audio crate provides cross-platform desktop audio I/O behind the desktop-audio feature flag. Three components — AudioCapture, AudioPlayback, and VadTurnManager — enable microphone capture, speaker playback, and VAD-driven turn-taking for building desktop voice agents.
fec-ui-checker
Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…
echo-reporter
Isolated sub-agent that re-reads every file written this run, parses props/events/slots/animations independently, and diffs against the spec. Cross-checks against validate-spec-compliance.mjs.