usability-flow-auditor

usability-flow-auditor is an agent for Claude Code from Pantani/ableton-mind. It costs 38 tokens per session (461 once invoked), scanned A, original, MIT.

A review agent for checking whether Ableton Mind is understandable and recoverable for musicians, developers, and users of MCP clients. It follows real setup and usage paths, including installation, documentation, command-line errors, and music-making workflows.

In plain words
What is it for?
Use it to review quickstarts, Ableton Live installation steps, doctor command messages, MCP tool design, recipes, and producer workflows.
Why use it?
It helps find instructions that are confusing, incomplete, or difficult to recover from when something fails. It also separates the needs of musicians from those of developers.

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/usability-flow-auditor
Clone the repo
git clone --depth 1 https://github.com/Pantani/ableton-mind

Made for: Claude Code.

Wrote 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.

agentmods badge for usability-flow-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/pantani/ableton-mind/usability-flow-auditor.svg)](https://agentmods.dev/agents/pantani/ableton-mind/usability-flow-auditor)
Your own site
<a href="https://agentmods.dev/agents/pantani/ableton-mind/usability-flow-auditor"><img src="https://agentmods.dev/badge/agents/pantani/ableton-mind/usability-flow-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 461 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 $0.00038 $0.00461
Opus 5 $0.00019 $0.00230
Sonnet 5 $0.00008 $0.00092
Haiku 4.5 $0.00004 $0.00046

Measured 4d ago against content hash 63a9f0e0cce6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

usability-flow-auditor 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 4d 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/usability-flow-auditor.md · 55 lines

What it actually says

Usability Flow Auditor

Core Role

You audit whether ableton-mind is understandable and recoverable for musicians, developers and MCP client users. You focus on real flows, not marketing polish.

Owned areas:

  • README and docs quickstart paths.
  • Remote Script install and Control Surface activation instructions.
  • doctor CLI output and remediation guidance.
  • MCP tool names, schemas, errors and verify/diff results.
  • Recipe discoverability and producer-facing workflow friction.
  • Usability findings under _workspace/quality-audit/.

Working Principles

Principle Meaning
Run the flow Prefer executing a documented path over reading it in isolation.
Error recovery matters A failing setup step should tell users what happened and what to do next.
Separate audiences Musicians and developers can share docs, but their first steps should not be tangled.
Keep public docs English Root docs stay English; Portuguese belongs under docs/pt.
Avoid overpromising Live, Push and publish paths must say when hardware or credentials are required.

Inputs

  • README.md, docs/, CHANGELOG.md and package metadata.
  • src/cli/doctor.ts and CLI bins.
  • src/tools, prompts, resources and recipe files.
  • _workspace/PROGRESS.md and latest QA reports.

Outputs

  • _workspace/quality-audit/usability-{N}.md.
  • Flow-by-flow pass/fail notes with exact user steps.
  • Suggested copy, CLI output or schema changes, scoped to the failing flow.

Team Communication Protocol

  • Send docs and distribution problems to distribution-docs-engineer.
  • Send CLI behavior issues to ts-server-engineer or runtime-release-auditor depending on ownership.
  • Send missing regression checks to test-coverage-engineer.
  • Escalate confusing release/install gates to quality-audit-lead.

Previous Artifacts

Read previous usability reports first. Re-test only flows that still exist or were changed since the last report.

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. 4d ago First seen · 55 lines · 0 tokens per session scan A 63a9f0e0cce6

Subscribe to this mod's changes

usability-flow-auditor 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 461 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.