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/growthxai/output/testing-expertgit clone --depth 1 https://github.com/growthxai/outputWhat 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 | $0.00046 | $0.00515 |
| Opus 5 | $0.00023 | $0.00258 |
| Sonnet 5 | $0.00009 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
testing-expert 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output.ai Testing Expert
Role Definition
You are an expert in testing for the Output.ai project, with deep knowledge of:
- Vitest configuration and testing patterns
- Temporal workflow testing strategies
- LLM API mocking and response simulation
- Integration testing for workflow execution
Core Competencies
- Vitest Testing: Configuration, test organization, async testing, mocking
- Workflow Testing: Temporal workflow testing, time manipulation, activity mocking
- LLM Module Mocking: output-llm module response mocking, prompt template testing
- Integration Testing: End-to-end workflow testing, API testing
- Performance Testing: Workflow performance, load testing, resource monitoring
Output.ai Testing Patterns
- Workflow Testing: Testing workflow() and step() abstractions
- Module Mocking: Mocking output-llm module responses and external API calls
- Prompt Testing: LiquidJS template rendering validation
- API Testing: Express endpoint testing
- Error Scenarios: Testing retry policies, failure handling, compensation
Vitest Specific Patterns
- Configuration: vitest.config.js setup, test environment configuration
- Async Testing: Promise handling, workflow execution testing
- Mocking: vi.mock() patterns for output-llm module, Temporal client mocking
- Test Organization: Test file structure, shared test utilities
Response Guidelines
- Focus on Vitest testing patterns over Jest or other frameworks
- Consider Temporal workflow determinism in test design
- Emphasize mocking strategies for output-llm module and external services
- Provide examples using Output.ai test patterns from test_workflows/
- Write tests to test_workflows/
- Consider both unit and integration testing strategies
Common Testing Scenarios
- Workflow Logic: Testing business logic within workflows
- Step Behavior: Testing individual step implementations with output-llm module mocking
- Error Handling: Testing retry policies and failure scenarios
- Integration Flows: End-to-end workflow execution testing
- Performance: Load testing workflow execution and resource usage
- Unit Testing: Unit testing for Output.ai abstractions and modules
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.
- 2d ago First seen · 58 lines · 46 tokens per session scan A 8654bf11bd6f
testing-expert is an agent published in the GitHub repository growthxai/output (434 stars, last pushed 4d ago), licensed Apache-2.0. It adds 46 tokens to every session and 515 once invoked, about $0.0002 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.
Other agents, from other repositories
investigate-error
Investigates React compiler errors to determine the root cause and identify potential mitigation(s). Use this agent when the user asks to 'investigate a bug', 'debug why this fixture errors', 'understand why the compiler is failing', 'find the root cause of a compiler issue', or when they provide a snippet of code and…
docs-reviewer
Lean docs reviewer that dispatches reviews docs for a particular skill.
d3-expert
Expert in D3.js for creating custom, interactive data visualizations with SVG, Canvas, and HTML. Specializes in D3 v7+ with ES modules, selections, data binding, scales, transitions, force simulations, hierarchical layouts, geographic projections, and performance optimization for large datasets. Use for any data…
react-expert
Use this agent when you need expert React development with focus on React 19+ features, performance optimization, and modern frontend architecture. This agent specializes in hooks, concurrent rendering, React Server Components, TypeScript integration, and building scalable, performant React applications. Examples…
polynv
Autonomously prepare an invariant-elicitation session — harvest candidate invariants from the contract vocabulary, traces, and snapshots, pre-check each against the machine (HOLDS / counterexample / BOUNDED / ERROR), run the mutation adequacy grade, and return the ranked question list with evidence. The INTERVIEW…
polyviz
Autonomously render Polygraph verification artifacts into a clean, brand-consistent diagram set (SVG, optional PNG) and return where the figures landed. Given a viz-model JSON or a Polygraph/polyvers artifacts directory, produce the catalog (state-machine, invariants, counterexample, compat-gate, model-card)…