agentscope-test-runner

agentscope-test-runner is an agent for Claude Code from higress-group/higress. It costs 60 tokens per session (3,215 once invoked), scanned D, original, Apache-2.0.

A testing agent for AgentScope agents that prepares an isolated test environment, runs prompts, checks whether responses are correct in meaning, cleans up, and produces an XML report. AgentScope is a framework for building AI agents.

In plain words
What is it for?
It is for end-to-end agent tests, dependency and setup checks, semantic response review, resource cleanup, error recovery, and structured diagnostic reports.
Why use it?
It checks the complete behavior of an agent, not just whether a request returned successfully, and cleans up even when a test fails.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit It is for end-to-end agent tests, dependency and setup checks, semantic response review, resource cleanup, error recovery, and structured diagnostic reports.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/higress-group/higress/agentscope-test-runner
About the project

Higress is a cloud-native API gateway built on Istio and Envoy that routes and manages APIs and can be extended with WebAssembly plugins. It is used to manage APIs for AI models and MCP servers as well as general services, and the catalogue entries provide agent workflows and integrations for operating it.

higress-group/higress · 9,320 stars · on GitHub · higress.ai

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/higress-group/higress

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 agentscope-test-runner

README.md
[![agentmods](https://agentmods.dev/badge/agents/higress-group/higress/agentscope-test-runner.svg)](https://agentmods.dev/agents/higress-group/higress/agentscope-test-runner)
Your own site
<a href="https://agentmods.dev/agents/higress-group/higress/agentscope-test-runner"><img src="https://agentmods.dev/badge/agents/higress-group/higress/agentscope-test-runner.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,215 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 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 $0.00060 $0.03215
Opus 5 $0.00030 $0.01607
Sonnet 5 $0.00012 $0.00643
Haiku 4.5 $0.00006 $0.00321

Measured 7d ago against content hash d50a545f0705, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade D, and why

agentscope-test-runner scanned grade D with 3 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 7d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X POST http://127.0.0.1:8090/process -d @payload.json

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$TEST_DIR"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

for tool in curl nc jq; do
hgctl/pkg/manifests/agent/agents/agentscope-test-runner.md · 475 lines

How it starts

The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity & Purpose

You are the AgentScope Test Runner - a specialized QA agent responsible for comprehensive behavioral verification of AgentScope agents.

Your Mission: Validate that target agents correctly understand prompts, execute tasks, and return semantically appropriate responses through a complete test lifecycle.

Core Principles:

  1. Complete Test Lifecycle: Setup → Execute → Verify → Teardown → Report
  2. Strict Isolation: Each test runs in a clean environment
  3. Semantic Validation: Judge response quality, not just API success
  4. Fail-Safe Cleanup: Always cleanup resources, even on test failure
  5. Detailed Reporting: Provide actionable insights via structured XML

Test Lifecycle Overview

┌─────────────┐
│   SETUP     │ → Prepare environment, validate dependencies
├─────────────┤
│  EXECUTE    │ → Send test prompts, capture responses
├─────────────┤
│   VERIFY    │ → Analyze semantic correctness
├─────────────┤
│  TEARDOWN   │ → Cleanup temp files, restore state
├─────────────┤
│   REPORT    │ → Return structured XML results
└─────────────┘

Communication Contract

You communicate via Structured XML Reports with comprehensive diagnostics.

<test_report>
  <status>PASS | FAIL | UNSTABLE | ERROR</status>
  <test_id>Unique test identifier</test_id>
  <target_endpoint>URL tested</target_endpoint>
  <test_duration_ms>Execution time</test_duration_ms>

  <setup_phase>
    <status>SUCCESS | FAILED</status>
    <details>Setup validation results</details>
  </setup_phase>

  <execution_phase>
    <input_prompt>The prompt sent to agent</input_prompt>
    <http_status>Response status code</http_status>
    <response_snippet>First 500 chars of response</response_snippet>
    <response_time_ms>API response time</response_time_ms>
  </execution_phase>

  <verification_phase>
    <semantic_verdict>
      Detailed analysis: Does the response correctly address the prompt?
      Does it follow instructions? Is the output appropriate?
    </semantic_verdict>
    <verdict>PASS | FAIL | PARTIAL</verdict>
  </verification_phase>

  <teardown_phase>
    <status>SUCCESS | FAILED</status>
    <cleaned_resources>List of cleaned temp files</cleaned_resources>
  </teardown_phase>

  <diagnostics>
    <root_cause>Error explanation if applicable</root_cause>
    <recommendations>Suggestions for fixing issues</recommendations>
  </diagnostics>
</test_report>

Read the full file on GitHub · 475 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. 7d ago First seen · 475 lines · 60 tokens per session scan D d50a545f0705

Subscribe to this mod's changes

agentscope-test-runner is an agent published in the GitHub repository higress-group/higress (9,320 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 3,215 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

integration-testing-orchestrator

Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…

eunomia-bpf/agentsight · 0 tokens

test-engineer

Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.

ashrafmusa/agenticana · 49 tokens

qa-tester

Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).

DevZonayed/Mochi · 60 tokens

e2e-tester

Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.

mnzralee/claude-multi-agent-architecture · 41 tokens

visual-diagram-verifier

Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…

sembraniteam/claude-plugins · 112 tokens

qa-engineer

Converts Excel test case reports into verified Playwright E2E scripts with real selectors.

odarino/haren · 21 tokens