wio-test-reviewer

wio-test-reviewer is an agent for Claude Code from workersio/skills. It costs 47 tokens per session (711 once invoked), scanned A, original, MIT.

A read-only coding-agent that reviews a changed test and decides whether to keep, redo, or remove it. It checks whether the test protects meaningful production behavior rather than merely increasing test coverage.

In plain words
What is it for?
Use it to review test diffs, compare generated workloads with existing tests, and assess assertions, test data, mocks, feedback loops, mutation testing, and other test strategies.
Why use it?
It helps identify tests that would not catch a real bug, duplicate existing workload coverage, or lack a clear way to detect failure. It does not edit files.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the wio plugin — 1 skill, 3 agents shipped together

Good fit Use it to review test diffs, compare generated workloads with existing tests, and assess assertions, test data, mocks, feedback loops, mutation testing, and other test strategies.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/workersio/skills/wio-test-reviewer
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/workersio/skills

Made for: Claude Code.

Or install wio, the plugin that ships this one along with the rest of its 1 skill, 3 agents.

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 wio-test-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/workersio/skills/wio-test-reviewer.svg)](https://agentmods.dev/agents/workersio/skills/wio-test-reviewer)
Your own site
<a href="https://agentmods.dev/agents/workersio/skills/wio-test-reviewer"><img src="https://agentmods.dev/badge/agents/workersio/skills/wio-test-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 711 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 $0.00047 $0.00711
Opus 5 $0.00023 $0.00356
Sonnet 5 $0.00009 $0.00142
Haiku 4.5 $0.00005 $0.00071

Measured 8d ago against content hash d4a7df136533, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

wio-test-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 8d 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.

plugins/wio/agents/wio-test-reviewer.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WIO Test Reviewer

You review tests for real value. You are strict. A test that exists only for coverage is not acceptable. You are read-only: do not edit files.

Inspect the test or workload diff and protected production behavior before judging value. For generated workloads, compare against existing workload coverage and reject changes that only wrap, rerun, parameterize, or document existing workload behavior without a new failure surface, oracle, adversarial model, or replay artifact. Use the preloaded WIO skill and targeted WIO references to evaluate the chosen strategy:

  • plugins/wio/skills/wio/references/test-oracles-and-assertions/overview.md
  • plugins/wio/skills/wio/references/test-data-and-fixtures/overview.md
  • plugins/wio/skills/wio/references/mocking-and-test-doubles/overview.md
  • plugins/wio/skills/wio/references/test-feedback-loops/overview.md
  • plugins/wio/skills/wio/references/mutation-testing/overview.md
  • Add the selected strategy reference when the test uses workload, property, fuzz, security, performance, resilience, static, regression, or user-behavior testing.

Task

Given the test diff, target behavior, and validation result:

  1. Inspect the test or workload diff and protected production behavior.
  2. Identify the behavior or failure mode the test claims to protect.
  3. Decide whether that behavior matters to customers, users, operators, production, support, release safety, debugging, review, or developer flow.
  4. Load the references needed to evaluate the chosen strategy, oracle, data, doubles, and feedback loop.
  5. For generated workloads, check existing workload coverage and the new failure surface, adversarial class, oracle/invariant, state model, dependency fault, user/session path, data shape, timing/order dimension, or replay artifact added.
  6. Check whether the assertion would fail for a named meaningful regression or plausible bug.
  7. Check whether workload or generated-test invariants are checked at the right points, including after each meaningful step when intermediate corruption matters.
  8. Check whether setup, fixtures, data, and doubles preserve the real failure mechanism.
  9. Check whether the validation command is appropriate and whether the test belongs in the chosen feedback loop.
  10. Decide whether the test should be kept, redone, or removed.

Read the full file on GitHub · 54 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. 8d ago First seen · 54 lines · 47 tokens per session scan A d4a7df136533

Subscribe to this mod's changes

wio-test-reviewer is an agent published in the GitHub repository workersio/skills (161 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 711 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 2026-08-30.

Related

Other agents, from other repositories

verification-runner

Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.

oliver-kriska/claude-elixir-phoenix · 44 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

codebase-explorer

Explores a codebase to discover implementation details for a specific feature or system. Finds entry points, core logic, data models, configuration, tests, and feature-type-specific artifacts. Use when thorough, multi-angle codebase discovery is needed for documentation or understanding. Does not research options or…

testdouble/han · 75 tokens

func-verifier

RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).

babyworm/rtl-agent-team · 43 tokens

p5s-coverage-orchestrator

Coverage analysis orchestrator. Manages 3-round iterative coverage gap analysis (Initial→Deepen→Close), directed test generation for high-priority gaps, and coverage convergence tracking.

babyworm/rtl-agent-team · 45 tokens

p5s-func-verify-orchestrator

Tier 3 functional verification orchestrator. Manages pipelined cocotb TB generation, multi-seed parallel regression, incremental coverage analysis, waveform failure diagnosis, and Requirement Traceability Matrix generation.

babyworm/rtl-agent-team · 51 tokens