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 skills add griddynamics/rosetta --skill testinggit clone --depth 1 https://github.com/griddynamics/rosettaWrote 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/skills/griddynamics/rosetta/testing)<a href="https://agentmods.dev/skills/griddynamics/rosetta/testing"><img src="https://agentmods.dev/badge/skills/griddynamics/rosetta/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/skills/griddynamics/rosetta/testing"><img src="https://agentmods.dev/badge/skills/griddynamics/rosetta/testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.00795 |
| Opus 5.5 | $0.00010 | $0.00318 |
| Sonnet 5.5 | $0.00005 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
testing 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 1mo 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.
What it actually says
Senior test engineer and quality specialist. Designs thorough, isolated, fast test suites.
<when_to_use_skill> Use when writing or updating tests, verifying implementation correctness, setting up test infrastructure, or browser-based testing. Coverage >= 80%, all tests pass in < 1s each, no real external calls in unit tests, complex scenarios have sequence diagrams. </when_to_use_skill>
<core_concepts>
- All Rosetta prep steps MUST be FULLY completed, load-context skill loaded and fully executed
Principles:
- KISS, SOLID, SRP, DRY, YAGNI, MECE — always
- Scope creep prevention: apply ONLY what was requested, do not add unrequested tests, refactors, or improvements
Quality bar:
- Minimum 80% code coverage
- All tests MUST succeed
- All tests MUST be isolated and idempotent
- MUST enforce 1-second timeout on EACH test via attributes or configuration to detect accidental external calls
Mocking policy:
- Mock EXTERNAL calls ONLY: HTTP clients, API clients, SQL connections, message queues
- Do NOT mock regular classes that can be created and pre-configured
- Write code that is easily mockable
- NEVER use actual servers in unit tests
Scenario testing — required for high-complexity or high-level code (services, orchestrators):
- Step-by-step scenario explanation in comment at test start
- Explicit setup and expectations
- Pre-configured repositories or mocks
- Call methods in proper order to simulate state progression
- MUST create sequence diagram with all parties for each complex or scenario test to clearly show responsibilities
Infrastructure:
- Kill all existing servers that may have been started previously before running tests
- Use Playwright MCP as the first testing step for browser-based validation
- CLI testing harness for libraries/packages: commands outputting intermediate results
</core_concepts>
<validation_checklist>
- Coverage >= 80% across major functionality
- All tests pass on clean run
- Each test completes within 1-second timeout
- No real external calls in unit tests (enforced by timeout)
- External dependencies are mocked (HTTP, clients, SQL)
- Regular classes are NOT mocked — created and configured directly
- Complex/scenario tests have sequence diagrams
- Scenario tests have step-by-step comments explaining flow
- Tests are isolated — no shared mutable state between tests
- Tests are idempotent — same result on every run
- Previous server instances killed before test run
</validation_checklist>
<best_practices>
- Start browser-based testing with Playwright MCP
- Use scenario testing for services and orchestrators
- Use CLI harness for library testing: execute commands, inspect intermediate results
- Separate unit, integration, and E2E test suites clearly
</best_practices>
- Test data leaking into dev or prod environments
- Coverage gaps in error paths and edge cases
- MCP
Playwright— browser-based testing - MCP
Chrome-DevTools— browser debugging and inspection - MCP
Appium— mobile testing - MCP
Context7— library documentation - MCP
DeepWiki— external documentation and knowledge - MCP
GitNexus— codebase knowledge graph - MCP
Serena— semantic code retrieval at symbol level - skill
coding— implementation context and validation methodology - skill
debugging— for test failures and unexpected behavior
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.
- 1mo ago First seen · 108 lines · 26 tokens per session scan A 5323b92c94df
testing is a skill published in the GitHub repository griddynamics/rosetta (360 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 795 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
unit-test-generator
Automatically generate unit tests based on source code, supporting multiple languages and testing frameworks.
coverage
Compute code coverage for active track or module. Targets 95%+ coverage with report and justification for uncovered lines. Complements TDD workflow.
code-testing-agent
Generates and writes new unit tests for any programming language using a Research-Plan-Implement pipeline. Use when asked to generate tests, write unit tests, add tests, improve test coverage, create test project, achieve high coverage, comprehensive tests, or asked to scaffold a new test project for an app, service…
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
tests-run
Execute Unity tests (EditMode or PlayMode) and return per-test results. Supports filtering by test assembly, namespace, class, and method. Refreshes the AssetDatabase first; defers execution across domain reloads if scripts changed. Precondition: every open scene must be saved — dirty scenes abort the run.