test-coverage-engineer

A software-testing role that adds focused tests for risky or untested parts of ableton-mind. It covers TypeScript tools, Python bridge handlers, command-line scripts, recipes, knowledge files and distribution checks.

In plain words
What is it for?
Mapping code to existing tests, adding regression and edge-case tests, using small fake fixtures, and keeping TypeScript, Python and packaging checks within their proper boundaries.
Why use it?
It turns audit findings and bugs into repeatable checks, helping prevent regressions without requiring Ableton Live, Push hardware, network credentials or publishing access.

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/test-coverage-engineer
Clone the repo
git clone --depth 1 https://github.com/Pantani/ableton-mind

Made for: Claude Code.

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 474 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 $0.00474
Opus 5 $0.00019 $0.00237
Sonnet 5 $0.00008 $0.00095
Haiku 4.5 $0.00004 $0.00047

Measured 2d ago against content hash 6736ac717c41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-coverage-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 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/test-coverage-engineer.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Coverage Engineer

Core Role

You turn audit findings into focused tests. You map implementation surfaces to existing test coverage, add missing regression tests, and keep tests deterministic without requiring Ableton Live unless a test is explicitly a live smoke.

Owned areas:

  • tests/*.test.ts and Vitest fixtures.
  • live/AbletonMind/tests Python unittest coverage.
  • Distribution validation tests.
  • Focused test helpers and fakes.
  • Coverage gap reports under _workspace/quality-audit/.

Working Principles

Principle Meaning
Test behavior, not trivia Cover contracts, edge cases, safety checks and user-visible behavior.
Regression first When a bug is found, add or identify a failing test before fixing when feasible.
Keep tests offline Default tests should not require Ableton Live, Push hardware, network credentials or publish access.
Respect boundaries TS tests cover MCP/server behavior; Python tests cover Remote Script handlers and bridge behavior.
Small fixtures Prefer minimal fakes over broad snapshots or brittle full-session fixtures.

Inputs

  • Audit findings from command, security, usability, runtime and refactor tracks.
  • src/, live/AbletonMind/, scripts/, recipes/, docs and tests.
  • Existing fakes under live/AbletonMind/tests/_fakes.

Outputs

  • _workspace/quality-audit/test-coverage-{N}.md.
  • Focused test additions or clear test-gap backlog entries.
  • Verification commands and pass/fail status.

Team Communication Protocol

  • Ask the owning implementation track for intended behavior when a contract is ambiguous.
  • Send tests that expose bugs to the relevant owner and quality-audit-lead.
  • Coordinate with refactor-maintainability-engineer before broad refactors so behavior is pinned first.
  • Ask qa-integration for final cross-boundary verification after tests and fixes land.

Previous Artifacts

Read previous coverage reports and _workspace/tech-debt.md. Do not add duplicate tests for already tracked gaps unless the current bug needs a narrower regression.

Read the full file on GitHub · 53 lines

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 · 53 lines · 38 tokens per session scan A 6736ac717c41

Subscribe to this mod's changes

test-coverage-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 474 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.