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 skills/eea/eea.agent.skills/testingnpx skills add eea/eea.agent.skills --skill testinggit clone --depth 1 https://github.com/eea/eea.agent.skillsWhat 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 | $0.00045 | $0.01530 |
| Opus 5 | $0.00023 | $0.00765 |
| Sonnet 5 | $0.00009 | $0.00306 |
| Haiku 4.5 | $0.00005 | $0.00153 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing
Use this skill when a repository needs a test workflow developers and Jenkins run identically, or when coverage needs to go up for real rather than by gaming the number.
Primary goal
Two goals, in order:
- Parity — the same test commands run identically for the developer, the agent, and Jenkins. Mostly mechanical; see "Parity contract" below, which defers detail to
docker-expertandjenkins-pipelinerather than restating it. - Quality — coverage increases come from tests that exercise real behavior, not from tests written to move a number. This is the harder, ongoing part, and where this skill should keep growing.
When to use
Use this skill when you need to:
- close a real coverage gap (e.g. moving from 60% to 80%) with tests that exercise actual behavior, not just whichever lines are easiest to hit
- audit whether existing tests are meaningful or just inflate the coverage number
- define canonical test commands for a repository and confirm Jenkins and local testing run them identically
- avoid relying on Make as the only entrypoint for running tests
Parity contract
The commands Jenkins runs must be the same commands a developer can run locally with Docker. Jenkins must never hide the real commands inside Groovy only, and Make — if the repository uses it — must never be the only usable interface; a developer without Make must still be able to run the equivalent command.
For every Jenkins quality/test stage, be able to answer:
- what exact Docker command does Jenkins run?
- what exact Docker command should a developer run locally?
- are these the same command, or an obviously equivalent wrapper?
If the answer is no, fix that before touching test content — a coverage number from a stage you can't reproduce locally isn't one you can trust.
For the Dockerfile.test contract (what the image must contain, dependency-install rules, mixed-language guidance), see docker-expert/EEA-OVERRIDES.md's "Dockerfile.test for Jenkins Pipelines" — that's the canonical source, not restated here. For the Jenkinsfile phases that build, preflight, and generate around it, see jenkins-pipeline's Required workflow.
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.
- yesterday First seen · 111 lines · 45 tokens per session scan A 483c70c48d17
testing is a skill published in the GitHub repository eea/eea.agent.skills (2 stars, last pushed 25d ago), licensed MIT. It adds 45 tokens to every session and 1,530 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.