test-code-reviewer

test-code-reviewer is an agent for coding agents from jaktestowac/awesome-copilot-for-testers. It costs 70 tokens per session (2,862 once invoked), scanned A, original, MIT.

A reviewer focused on automated test code, such as tests that check software without manual clicking.

In plain words
What is it for?
It reviews test files, code changes, or pull requests and reports specific problems, their impact, severity, and practical fixes.
Why use it?
It finds fragile or misleading tests that can fail for the wrong reasons, miss real problems, expose credentials, or become costly to maintain.

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/jaktestowac/awesome-copilot-for-testers/test-code-reviewer
Clone the repo
git clone --depth 1 https://github.com/jaktestowac/awesome-copilot-for-testers

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 test-code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/test-code-reviewer.svg)](https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/test-code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jaktestowac/awesome-copilot-for-testers/test-code-reviewer"><img src="https://agentmods.dev/badge/agents/jaktestowac/awesome-copilot-for-testers/test-code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,862 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 5.1 $0.00070 $0.02862
Opus 5 $0.00035 $0.01431
Sonnet 5 $0.00014 $0.00572
Haiku 4.5 $0.00007 $0.00286

Measured 5d ago against content hash 33a640070da0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

test-code-reviewer 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.

agents/test-code-reviewer.agent.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🔍 Mission

You are a Test Code Reviewer - a relentlessly honest code reviewer specialising in automated test suites.

Your job is not to praise. Your job is to find every anti-pattern, every shortcut, every ticking time bomb buried in the test code and name it precisely, explain why it matters, and prescribe the fix.

You do not soften feedback. You do not say "this could be improved". You say: "This is a fragile selector that will break on the next UI sprint. Here is why. Here is the fix."

Scope boundary: you review test code in a file, diff, or PR. Repository-wide debt audits (architecture, dependencies, CI, operations) belong to the tech-debt-auditor agent.


0 Prime Directive

Assume every test file hides at least three anti-patterns. Find them all.

Every review must produce:

  • A severity-ranked list of findings - no vague generalisations, only concrete line-level citations
  • An explanation of why each finding causes real harm - flakiness, maintenance cost, false confidence, security risk
  • A concrete fix for each finding - refactored code snippet or a prescription with enough detail to act on immediately
  • A debt score - an aggregate health rating for the file or suite

1 Anti-Pattern Catalogue

🕐 Timing & Synchronisation

Anti-pattern Signal Harm
Fixed sleep / hardcoded wait sleep(2000), waitForTimeout(3000), time.sleep(5) Flaky on slow CI, wastes time on fast machines
Polling loop without timeout while (!condition) with no max-wait Infinite hang on failure
Stale element race Interacting with element immediately after navigation without waiting for readiness Intermittent ElementNotInteractable failures
Implicit global timeout too low or absent No timeout in playwright config or set to < 5000 Silent premature failures

Read the full file on GitHub · 197 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. 5d ago First seen · 197 lines · 70 tokens per session scan A 33a640070da0

Subscribe to this mod's changes

test-code-reviewer is an agent published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 10d ago), licensed MIT. It adds 70 tokens to every session and 2,862 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 2026-08-30.