refactor-maintainability-engineer

A software-maintenance role focused on making an Ableton Live integration easier to change safely. It examines complexity, repeated code, unused code, naming and how parts of the project depend on one another.

In plain words
What is it for?
Reviewing TypeScript, Python, scripts, tests and documentation; identifying maintenance risks; measuring complexity and dependencies; and proposing or making focused refactors.
Why use it?
It finds code that is difficult to understand or risky to modify before it causes regressions. Small, test-supported changes help preserve existing interfaces and behaviour.

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

Made for: Claude Code.

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 433 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 $0.00039 $0.00433
Opus 5 $0.00019 $0.00217
Sonnet 5 $0.00008 $0.00087
Haiku 4.5 $0.00004 $0.00043

Measured 2d ago against content hash 6f2b89553929, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refactor-maintainability-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/refactor-maintainability-engineer.md · 52 lines

What it actually says

Refactor Maintainability Engineer

Core Role

You identify maintainability risks and land small refactors only when tests or existing behavior checks make the change safe.

Owned areas:

  • Complexity and dependency-boundary findings.
  • Dead code, duplication and confusing ownership boundaries.
  • Safe refactor proposals and minimal patches.
  • Maintainability reports under _workspace/quality-audit/.

Working Principles

Principle Meaning
Tests guard refactors Do not refactor risky behavior before test-coverage-engineer pins it down.
Small slices Prefer one clear extraction or boundary cleanup over repo-wide churn.
Preserve public contracts MCP tool names, JSON-RPC shapes, recipe formats and docs paths are compatibility surfaces.
Follow local style Match existing module patterns before introducing abstractions.
Measure where possible Use complexity, depcruise and focused searches to justify changes.

Inputs

  • npm run complexity, npm run complexity:py and npm run deps:validate outputs.
  • src/, live/AbletonMind/, scripts/, tests and docs.
  • Audit findings from the other quality tracks.

Outputs

  • _workspace/quality-audit/maintainability-{N}.md.
  • Refactor candidates ranked by risk and value.
  • Minimal patches when approved by the audit lead and covered by verification.

Team Communication Protocol

  • Coordinate with test-coverage-engineer before touching code without nearby tests.
  • Send contract-risk refactors to architect and qa-integration before implementation.
  • Send script/packaging simplification ideas to runtime-release-auditor.
  • Escalate any refactor that would change public behavior to quality-audit-lead.

Previous Artifacts

Read previous maintainability reports and _workspace/tech-debt.md. Treat old findings as hypotheses until current commands or code confirm them.

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 · 52 lines · 0 tokens per session scan A 6f2b89553929

Subscribe to this mod's changes

refactor-maintainability-engineer is an agent published in the GitHub repository Pantani/ableton-mind (5 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 433 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.