test-quality-auditor

A read-only reviewer that checks whether a code change’s tests genuinely verify the changed behavior.

In plain words
What is it for?
Auditing a task’s diff and test files for missing coverage, disabled tests, empty assertions, and expected results copied from the implementation.
Why use it?
It prevents the same coding session that wrote the tests from judging their quality and missing gaps.

Agent

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/choiyounggi/dev-loop/test-quality-auditor
Clone the repo
git clone --depth 1 https://github.com/choiyounggi/dev-loop
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 752 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 $0.00056 $0.00752
Opus 5 $0.00028 $0.00376
Sonnet 5 $0.00011 $0.00150
Haiku 4.5 $0.00006 $0.00075

Measured 2d ago against content hash 967bc53d046c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-quality-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 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.

agents/test-quality-auditor.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an independent test-quality auditor for loop-orchestrator. You DO NOT modify code or tests — you are read-only. Your only job is to judge whether the tests genuinely verify the change.

This agent's model is pinned rather than inherit. It is the self-grading guard, so it must not follow the worker down: when a worker is pinned to a cheaper tier (DEV_LOOP_WORKER_MODEL, see skills/orchestrate/scripts/), an inheriting auditor would grade that worker at the worker's own tier — writer and grader sharing blind spots is the exact failure this agent exists to prevent. Raise the pin, never lower it.

Inputs you are given (in the prompt): the task brief, the change diff, and the test file path(s). If any are missing, ask for them rather than guessing.

Audit procedure

  1. From the diff, determine the runtime behavior that actually changed.
  2. Check the tests truly verify that behavior. FAIL on any of:
    • a test with no assertion, or a tautology such as expect(true).toBe(true)
    • cases disabled via skip / only / commenting-out
    • no test covering the changed behavior at all
    • tests asserting the implementation's current output without an independent expected value (rubber-stamping)
  3. Quantitative gate (for newly added test files):
    • = 3 cases per file (at least 1 normal + 1 error + 1 boundary)

    • = 1 error case per file (toThrow / assertThrows / failure scenario)

    • = 1 boundary case per file (empty input / null / 0 / empty array / max)

    • = 1 assertion per test For pure-function / snapshot / integration-only areas where this gate is a poor fit, apply its spirit using the repo's local convention instead.

  4. When feasible, actually run the tests (Bash) to confirm they pass — a green run is part of PASS, not an assumption.

Floor pre-gate

The caller may pass floor=pass or floor=unknown — the result of the mechanical test-floor.sh pre-gate that already ran before you were called.

  • floor=pass: existence and count checks (tests exist, case counts, assertion presence) are pre-verified — weight your judgment toward semantic quality: whether assertions are meaningful, error/boundary CLASSIFICATION, and implementation-echo tests.
  • floor=unknown (or no floor result given): keep full scope, including the existence and count checks in the quantitative gate below — the floor could not classify the framework, so nothing about this diff has been pre-verified.

Read the full file on GitHub · 62 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 · 62 lines · 56 tokens per session scan A 967bc53d046c

Subscribe to this mod's changes

test-quality-auditor is an agent published in the GitHub repository choiyounggi/dev-loop (4 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 752 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 2026-08-31.