Borrowing it
Nothing to install: this file belongs to adamancyzhang/claude-orchestrator-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adamancyzhang/claude-orchestrator-server/master/.claude/agents/testing.mdgit 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 5.1 | $0.00013 | $0.00892 |
| Opus 5.5 | $0.00005 | $0.00357 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 7d ago), licensed MIT. It adds 13 tokens to every session and 892 once invoked, about $0.0001 per session on Opus 5.5. 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
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
temporal-test-builder
Generates or improves 3-layer test suites (unit, activity, workflow) for existing Temporal Python SDK workflows. Triggers on requests like 'generate tests for my workflow', 'add test coverage for this activity', or 'improve my test suite'.
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.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…