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 instructions/6uclz1/ableton-cli/agents-mdgit clone --depth 1 https://github.com/6uclz1/ableton-cliWhat 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 | $0.01788 | $0.01788 |
| Opus 5 | $0.00894 | $0.00894 |
| Sonnet 5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade A, and why
ableton-cli AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose
Repository-level instructions for coding agents working on ableton-cli.
Keep this file stable and operational. Do not duplicate the full command catalog here. Use the source documents listed below for command coverage, action mappings, examples, and contributor workflow details.
Project Context
ableton-cli is a Python CLI for controlling and inspecting Ableton Live through a local Remote Script. The project is intended for both humans and automation, so deterministic CLI behavior, stable JSON output, fixed exit codes, and explicit failures are part of the product surface.
Non-Negotiable Principles
- TDD: use red -> green -> refactor for behavioral changes.
- DRY: do not duplicate command logic, validation, tests, fixtures, or documentation.
- SOLID: keep modules focused; make dependencies explicit and injectable where practical.
- No silent degradation: fail explicitly with the correct error code and hint.
- No fallback execution paths: do not add alternate analyzers, alternate transports, or best-effort branches that hide missing prerequisites.
- No compatibility shims: do not add deprecated aliases, dual-path behavior, or legacy adapters unless explicitly requested. If a public contract changes, update the contract artifacts instead of preserving both behaviors.
Source of Truth
Use these repository-relative documents before changing behavior:
README.md— user-facing setup, command examples, global option placement, protocol, security model, exit codes.CONTRIBUTING.md— developer workflow, public contract boundary, quality harness, merge gates.skills/ableton-cli/SKILL.md— agent-facing command catalog.docs/skills/skill-actions.md— stable automation action names and CLI mappings.docs/skills/examples/*.json— machine-oriented examples..cursor/rules/ableton-cli.mdc— Cursor-specific conventions mirroring this file..quality-harness.ymlanddocs/quality-harness-phase2.md— quality harness thresholds and limits.
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.
- 2d ago First seen · 167 lines · 1,788 tokens per session scan A 3e488b9d9741
ableton-cli AGENTS.md is an instructions file published in the GitHub repository 6uclz1/ableton-cli (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,788 tokens to every session, about $0.0089 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 instructions, from other repositories
ableton-skills CLAUDE.md
Instructions for glincker/ableton-skills, covering ableton project — ai producer context, connected tools, operating principles, available skills and what not to do.
ableton-for-ai AGENTS.md
AGENTS.md instructions for peterkolbe/ableton-for-ai, covering ai agents guide for ableton-for-ai, project purpose, core components, 1. oscdaemon.py (the bridge) and 2. abletonclient.py (the interface).
LivePilot CLAUDE.md
Claude Code instructions for dreamrec/LivePilot, covering livepilot v1.30.0 — ableton live 12, project, architecture, key rules and m4l bridge notes.
ableton-mind AGENTS.md
Instructions for Pantani/ableton-mind, covering agents.md, repository state, what ableton-mind is, planned architecture (three layers) and design invariants (apply to every tool added).
LivePilot AGENTS.md
AGENTS.md instructions for dreamrec/LivePilot, covering livepilot v1.30.0 — ableton live 12, project, architecture, key rules and m4l bridge notes.
claude-ableton CLAUDE.md
Instructions for rohailaltaf/claude-ableton, covering claude.md — working notes for claude in this repo, layout, release runbook — do this when asked to "do a release", gotchas (already learned — don't rediscover) and testing against live ableton.