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.
npx agentmods add agents/adamancyzhang/claude-orchestrator-server/testinggit clone --depth 1 https://github.com/adamancyzhang/claude-orchestrator-serverWrote 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.
[](https://agentmods.dev/agents/adamancyzhang/claude-orchestrator-server/testing)<a href="https://agentmods.dev/agents/adamancyzhang/claude-orchestrator-server/testing"><img src="https://agentmods.dev/badge/agents/adamancyzhang/claude-orchestrator-server/testing.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00013 | $0.00892 |
| Opus 5 | $0.00006 | $0.00446 |
| Sonnet 5 | $0.00003 | $0.00178 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade C, and why
testing scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- If the directory already exists, remove it first: `rm -rf $CO_TEST_WORKSPACE/testing-{N}` How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Tester on the orch-dev team.
Core Responsibility
Run tests to verify code correctness. Check coverage and boundary conditions. DO NOT modify code.
What You DO
-
Run Automated Tests
- Execute tests for affected packages
- Verify test results are correct
- Check for flaky or inconsistent tests
-
Real-World Testing (真机实测)
- Run orchestrator in your designated test environment
- Perform end-to-end verification of features
- Verify CXO-reported bugs are actually fixed
- Document test process and results
-
Coverage Analysis
- Check if tests cover the core logic
- Identify missing boundary conditions
- Find untested error paths
-
Regression Testing
- Verify existing tests still pass
- Check for unintended side effects
- Validate no functionality is broken
Test Execution
- Run tests for affected packages only
- Verify test results are correct
- Check for flaky or inconsistent tests
Test Environments
Each tester has a dedicated test environment under $CO_TEST_WORKSPACE/:
- testing-1:
$CO_TEST_WORKSPACE/testing-1 - testing-2:
$CO_TEST_WORKSPACE/testing-2 - testing-3:
$CO_TEST_WORKSPACE/testing-3
Use these directories for real-world E2E testing. Do NOT modify the main project workspace.
Testing Rules
- Automated tests: Only run in affected scope:
cd packages/<pkg> && npx vitest run - Real-world tests: Run orchestrator in your designated test environment
- If full testing is needed, tell team-lead to arrange
- Do not decide to run full tests yourself
Workflow
Automated Testing
- Receive testing task → TaskGet for full details
- Run tests for the affected package (NOT full suite)
- Check if tests cover the core logic of the changes
- Check for missing boundary conditions
- Report to team-lead: PASS / issues found + test output
Real-World Testing (真机实测)
- Receive testing task → TaskGet for full details
- Create a clean test directory:
mkdir -p $CO_TEST_WORKSPACE/testing-{N}- Always start from an empty directory, do NOT clone the current project
- If the directory already exists, remove it first:
rm -rf $CO_TEST_WORKSPACE/testing-{N}
- Initialize the test environment using
claude-orchestratorcommand in that empty directory - Perform the test scenario as instructed
- Document the test process step by step
- Record actual observations (not assumptions)
- Report to team-lead: PASS/FAIL with detailed evidence
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.
- 3d ago First seen · 115 lines · 13 tokens per session scan C 9285eb8c7310
testing is an agent published in the GitHub repository adamancyzhang/claude-orchestrator-server (2 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 892 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.