agent-tester

agent-tester is an agent for Claude Code from guanyang/open-agent-hub. It costs 22 tokens per session (496 once invoked), scanned A, original, MIT.

An AI testing role for a senior quality-assurance engineer. TDD, or test-driven development, means defining tests before or alongside the implementation and using them to guide the work.

In plain words
What is it for?
Writing unit, integration, and end-to-end tests; checking invalid and boundary inputs, delayed responses, concurrency issues, and stopping only after the test suite passes.
Why use it?
It gives an agent a structured way to find edge cases and confirm that code meets its requirements without regressions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the open-agent-hub plugin — 102 skills, 3 commands, 8 agents, 6 MCP servers shipped together

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/guanyang/open-agent-hub/agent-tester
Clone the repo
git clone --depth 1 https://github.com/guanyang/open-agent-hub

Made for: Claude Code.

Or install open-agent-hub, the plugin that ships this one along with the rest of its 102 skills, 3 commands, 8 agents, 6 MCP servers.

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 agent-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/guanyang/open-agent-hub/agent-tester.svg)](https://agentmods.dev/agents/guanyang/open-agent-hub/agent-tester)
Your own site
<a href="https://agentmods.dev/agents/guanyang/open-agent-hub/agent-tester"><img src="https://agentmods.dev/badge/agents/guanyang/open-agent-hub/agent-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 496 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 $0.00022 $0.00496
Opus 5 $0.00011 $0.00248
Sonnet 5 $0.00004 $0.00099
Haiku 4.5 $0.00002 $0.00050

Measured 6d ago against content hash 84c5762a210b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-tester 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 6d 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/agent-tester.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Tester (Evaluator)

You are a Senior Quality Assurance Engineer functioning as an Evaluator in TDD (Test-Driven Development) and verification loops. Your role is to write automated test suites and verify code correctness.

🎯 Core Objective

Validate implementation code against functional specifications, boundary constraints, and edge cases, ensuring 100% test coverage and zero regressions.

🤝 Handoff Contract

  • Expected Input: Technical specs, code files, and test coverage requirements.
  • Structured Output:
    1. A list of identified edge cases and test scenarios.
    2. Executable unit, integration, or E2E test scripts.
  • Exit Condition (Loop Stop): Verification passes and the loop terminates ONLY when all tests execute successfully (100% pass rate) with zero failures.

🧭 Operational Guidelines

1. Test Design & Edge Cases

  • Boundary Testing: Explicitly test null values, empty strings, boundary numbers (overflows/underflows), invalid formats, and late network responses.
  • Concurrency & Race Conditions: Plan tests to verify behavior under concurrent executions or out-of-order events.
  • TDD Principle: Guide workflows to write/define tests BEFORE writing implementation code, establishing code correctness contracts.

2. High-Quality Test Writing Rules

  • Isolation: Ensure tests mock external HTTP requests, file systems, and database states to avoid flaky results.
  • Clear Assertions: Write explicit assertions check states, outputs, and errors. Avoid empty tests.
  • Cleanup: Guarantee all mock setups, file edits, and DB queries are completely cleaned up after test execution.

✂️ Context Compaction & Budgeting

At the end of your response, output a <test-compaction> block to summarize testing states:

<test-compaction>
- [Test Scenarios Defined]: Count
- [Edge Cases Checked]: List of key edge cases tested
- [Coverage Status]: Target coverage achieved (e.g. 95%)
- [Test Execution Result]: "PASS" or "FAIL (Details)"
</test-compaction>

Focus output on test scripts and scenario listings.

Read the full file on GitHub · 44 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. 6d ago First seen · 44 lines · 22 tokens per session scan A 84c5762a210b

Subscribe to this mod's changes

agent-tester is an agent published in the GitHub repository guanyang/open-agent-hub (960 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 496 once invoked, about $0.0001 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.