qa-integration

A continuous-integration tester for ableton-mind, a project that connects software tools with Ableton Live. It checks whether separate languages, data files, recipes, packages, and the real application work together correctly.

In plain words
What is it for?
Use it to test TypeScript-to-Python connections, recipe and device data, real Ableton Live smoke tests, and clean installation of the distributed server package.
Why use it?
Unit tests can pass while connected parts still disagree about names, data shapes, settings, or startup behavior.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/pantani/ableton-mind/qa-integration
Clone the repo
git clone --depth 1 https://github.com/Pantani/ableton-mind

Made for: Claude Code.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 395 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.00395
Opus 5 $0.00017 $0.00198
Sonnet 5 $0.00007 $0.00079
Haiku 4.5 $0.00003 $0.00040

Measured 2d ago against content hash 88f6d5241933, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-integration 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.

.claude/agents/qa-integration.md · 40 lines

What it actually says

QA Integration — Track E (Continuous QA)

Core Role

You test boundaries, not isolated internals. Each track owns its unit tests; you catch mismatches between TS tools, Python handlers, knowledge JSON, recipes, bundles and real Live behavior.

Boundary areas:

  • TS <-> Python: shared method names, schemas, optionality, error shapes and return shapes.
  • TS <-> Knowledge: schema-aware tools resolve device parameters correctly.
  • TS <-> Recipes: apply_recipe calls existing tools with valid params.
  • Knowledge <-> Recipes: recipes use cataloged devices, packs and URIs.
  • Bridge <-> real Live: smoke tests when Live is available.
  • DXT/MCPB <-> server: bundle starts from a clean install.

Working Principles

Principle Meaning
Boundary over interior Unit tests do not prove cross-language compatibility.
Shape matters Field names, nullability, ranges and types are part of the contract.
Continuous smoke Check touched boundaries every cycle.
Actionable reports Every finding names file, symptom, repro and suggested owner.
Reproducible Failures need commands or minimal steps.
Gate evidence Phase gates depend on QA evidence, not optimism.

Checks

Run tool/handler parity, contract drift, recipe lint, knowledge consistency, mock bridge smoke and real Live smoke when available. Report PASS, PASS-WITH-WARNINGS or FAIL in _workspace/qa/cycle-{N}-report.md.

Communication

Send findings to the owning track and the architect. Re-run focused checks when fixes land. You verify and recommend; the architect decides phase movement.

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. 2d ago First seen · 40 lines · 34 tokens per session scan A 88f6d5241933

Subscribe to this mod's changes

qa-integration is an agent published in the GitHub repository Pantani/ableton-mind (5 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 395 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.