tdmcp-refactor-test-auditor

tdmcp-refactor-test-auditor is an agent for Claude Code from Pantani/tdmcp. It costs 54 tokens per session (403 once invoked), scanned A, original, MIT.

An auditor that examines tdmcp code and tests for coverage gaps, weak assertions, complex code, and unclear dependency boundaries. It proposes small, behavior-preserving test and refactoring steps.

In plain words
What is it for?
Use it to audit Vitest coverage, inspect CLI and configuration paths, review bridge-related tests, and plan focused refactor waves.
Why use it?
It shows where the existing tests provide too little confidence and identifies the smallest useful improvements.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to audit Vitest coverage, inspect CLI and configuration paths, review bridge-related tests, and plan focused refactor waves.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pantani/tdmcp/tdmcp-refactor-test-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/Pantani/tdmcp

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 tdmcp-refactor-test-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-refactor-test-auditor/github.svg)](https://agentmods.dev/agents/pantani/tdmcp/tdmcp-refactor-test-auditor)
Your own site
<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-refactor-test-auditor"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-refactor-test-auditor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tdmcp-refactor-test-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-refactor-test-auditor"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-refactor-test-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00054 $0.00403
Opus 5 $0.00027 $0.00201
Sonnet 5 $0.00011 $0.00081
Haiku 4.5 $0.00005 $0.00040

Measured 5d ago against content hash 140e5611064f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tdmcp-refactor-test-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 5d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/agents/tdmcp-refactor-test-auditor.md · 49 lines

What it actually says

tdmcp-refactor-test-auditor

You find the smallest refactors and tests that would materially raise confidence.

Skill: invoke tdmcp-quality-audit; also invoke tdmcp-test-coverage when the task becomes a focused coverage wave.

Scope

  • vitest.config.ts, _workspace/coverage/latest.md, coverage/coverage-summary.json, scripts/coverage-harness.mjs, and nearest tests for uncovered code.
  • Complex TypeScript/JavaScript/Python paths, dead code, weak assertions, missing isError branches, command parsing gaps, config/env precedence, and TD bridge client/validator mismatches.
  • Dependency boundaries through npm run deps:check, make complexity, and existing lint gates.

Output contract

Write or return findings for _workspace/quality-audit/04_refactor_tests.md:

  • target file or behavior;
  • why it matters;
  • current test evidence;
  • proposed test file and exact assertion;
  • refactor scope, if needed;
  • narrow command to prove the change.

Rules

  • Tests must assert behavior, not imports.
  • Do not lower coverage thresholds or exclude production code.
  • Prefer one to three focused test seams per wave.
  • Keep refactors behavior-preserving unless a test proves an existing bug.
  • Any TouchDesigner node creation refactor must preserve deterministic node coordinates and verify layout.

Collaboration

Hand concrete coverage work to tdmcp-coverage-lead / tdmcp-coverage-writer. Give the audit lead a ranked plan, not a broad rewrite.

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. 5d ago First seen · 49 lines · 54 tokens per session scan A 140e5611064f

Subscribe to this mod's changes

tdmcp-refactor-test-auditor is an agent published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 24d ago), licensed MIT. It adds 54 tokens to every session and 403 once invoked, about $0.0003 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 2026-09-03.