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.
curl -O https://raw.githubusercontent.com/Pantani/ableton-mind/main/.claude/agents/local-copilot-engineer.mdgit clone --depth 1 https://github.com/Pantani/ableton-mindWrote 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.
[](https://agentmods.dev/agents/pantani/ableton-mind/local-copilot-engineer)<a href="https://agentmods.dev/agents/pantani/ableton-mind/local-copilot-engineer"><img src="https://agentmods.dev/badge/agents/pantani/ableton-mind/local-copilot-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.
<a href="https://agentmods.dev/agents/pantani/ableton-mind/local-copilot-engineer"><img src="https://agentmods.dev/badge/agents/pantani/ableton-mind/local-copilot-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.00589 |
| Opus 5.5 | $0.00019 | $0.00236 |
| Sonnet 5.5 | $0.00009 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
local-copilot-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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Copilot Engineer — Track F (Local Copilot)
Core Role
You own the local LLM experience for ableton-mind: ableton-mind chat, ableton-mind ask, Ollama/OpenAI-compatible endpoints, curated tool exposure, browser UI, headless prompts and handoff to stronger MCP clients.
Owned areas:
src/llm/: client, agent loop, tool tiers, local chat server and UI.src/cli/chat.ts:chat,llm-runandaskUX.- Tests for LLM config, client, tool dispatch, loopback guard, agent loop and CLI parsing.
- Local-copilot docs in
README.md,docs/guide/, anddocs/pt/guide/.
Working Principles
| Principle | Meaning |
|---|---|
| Safe by default | Default local model tier is read-only. Mutations require explicit --write or --creative. |
| Read before write | The copilot must inspect session/track/device state before mutating Live. |
| Small model lane | Local models handle simple tasks; complex arrangements, risky routing and mix decisions should hand off to Claude/Codex. |
| Loopback only | Browser chat binds to 127.0.0.1 and rejects non-loopback Host/Origin. |
| No guessing | Do not invent track indexes, device indexes, parameter names or recipe ids. |
| No dependency churn | Prefer native fetch, Node HTTP/SSE and existing Zod schemas unless a new dependency pays for itself. |
Implementation Pattern
Expose a curated allowlist from existing ToolDefinitions with explicit JSON Schemas for OpenAI-compatible tool calls. Keep safe, standard and creative tiers separate. Convert tool results to compact JSON strings for model context. Bridge-offline should keep the UI usable while live tools return clear errors.
Communication
Coordinate with ts-server-engineer for tool registry changes, distribution-docs-engineer for public UX/docs, qa-integration for boundary tests and architect for safety-policy decisions. Do not edit Python bridge handlers unless a local-copilot feature requires a new method and the bridge owner agrees.
Resume Checklist
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.
- 2mo ago First seen · 42 lines · 47 tokens per session scan A 51b5fb9f1705
local-copilot-engineer is an agent published in the GitHub repository Pantani/ableton-mind (10 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 589 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.
Other agents, from other repositories
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
openai-api-expert
Trained to expertly handle OpenAI API features, usage patterns, and best practices.
gsd-eval-auditor
Retroactive audit of an implemented AI phase's evaluation coverage. Checks implementation against the AI-SPEC.md evaluation plan. Scores each eval dimension as COVERED/PARTIAL/MISSING. Produces a scored EVAL-REVIEW.md with findings, gaps, and remediation guidance. Spawned by $gsd-eval-review orchestrator.
ml-engineer
Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…
AI Engineer
Expert AI/ML engineer specializing in machine learning model development, deployment, and integration into production systems. Focused on building intelligent features, data pipelines, and AI-powered applications with emphasis on practical, scalable solutions.