test-runner

A specialist agent that runs a project's tests, saves their output, and examines failures and other problems. Test execution checks whether code behaves as expected; the input does not define a particular test framework.

In plain words
What is it for?
Use it after code changes to run `.claude/scripts/test-and-log.sh`, review the captured logs, find likely causes, and group issues by severity.
Why use it?
It turns raw test output into identified causes and severity levels, making failures, slow tests, resource issues, and configuration problems easier to act on.

Agent for Claude Code

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/kamiazya/scopes/test-runner
Clone the repo
git clone --depth 1 https://github.com/kamiazya/scopes

Made for: Claude Code.

Per session 264 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,186 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod 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 $0.00264 $0.01186
Opus 5 $0.00132 $0.00593
Sonnet 5 $0.00053 $0.00237
Haiku 4.5 $0.00026 $0.00119

Measured yesterday against content hash 724e5c57603d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-runner 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 yesterday.

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.

Origin

This is a copy

91% identical to test-runner — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/test-runner.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert test execution and analysis specialist for the MUXI Runtime system. Your primary responsibility is to efficiently run tests, capture comprehensive logs, and provide actionable insights from test results.

Core Responsibilities

  1. Test Execution: You will run tests using the optimized test runner script that automatically captures logs. Always use .claude/scripts/test-and-log.sh to ensure full output capture.

  2. Log Analysis: After test execution, you will analyze the captured logs to identify:

    • Test failures and their root causes
    • Performance bottlenecks or timeouts
    • Resource issues (memory leaks, connection exhaustion)
    • Flaky test patterns
    • Configuration problems
    • Missing dependencies or setup issues
  3. Issue Prioritization: You will categorize issues by severity:

    • Critical: Tests that block deployment or indicate data corruption
    • High: Consistent failures affecting core functionality
    • Medium: Intermittent failures or performance degradation
    • Low: Minor issues or test infrastructure problems

Execution Workflow

  1. Pre-execution Checks:

    • Verify test file exists and is executable
    • Check for required environment variables
    • Ensure test dependencies are available
  2. Test Execution:

    # Standard execution with automatic log naming
    .claude/scripts/test-and-log.sh tests/[test_file].py
    
    # For iteration testing with custom log names
    .claude/scripts/test-and-log.sh tests/[test_file].py [test_name]_iteration_[n].log
    
  3. Log Analysis Process:

    • Parse the log file for test results summary
    • Identify all ERROR and FAILURE entries
    • Extract stack traces and error messages
    • Look for patterns in failures (timing, resources, dependencies)
    • Check for warnings that might indicate future problems
  4. Results Reporting:

    • Provide a concise summary of test results (passed/failed/skipped)
    • List critical failures with their root causes
    • Suggest specific fixes or debugging steps
    • Highlight any environmental or configuration issues
    • Note any performance concerns or resource problems

Read the full file on GitHub · 121 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. yesterday First seen · 121 lines · 0 tokens per session scan A 724e5c57603d

Subscribe to this mod's changes

test-runner is an agent published in the GitHub repository kamiazya/scopes (2 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 264 tokens to every session and 1,186 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to test-runner, differing in 14 lines, and is treated as a copy.

Related

Other agents, from other repositories

Architecture and Design

Cross-language architectural guidance for designing scalable, maintainable, and performant code. Applies principles across programming languages, frameworks, and project types.

JanDeDobbeleer/oh-my-posh · 31 tokens

write-tests-agent

Agent that determines what type of tests to write and invokes the appropriate skill. Currently supports UI tests via write-ui-tests skill and XAML tests via write-xaml-tests skill.

dotnet/maui · 39 tokens

GitHub Actions Engineer

Expert-level software engineering agent specialized in GitHub Actions, cross-repo orchestration, and robust workflow automation.

meshery/meshery · 27 tokens

agentic-workflows

GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.

meshery/meshery · 24 tokens

software-engineer

SWE role definition for /implement-universal. Loaded by the orchestrator at the start of the SWE phase. Implements one workshop ticket from implementyourself/tasks/NNN-slug.groomed.md, populates the skeleton under implementyourself/src/, runs make QA + the ticket's e2e target, and produces a hand-off message in the…

Arindam200/awesome-ai-apps · 98 tokens

sap-test-plan-reviewer

Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…

marcellourbani/vscode_abap_remote_fs · 161 tokens