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/techtankto/techtank-site/testingnpx skills add techtankto/techtank-site --skill testinggit clone --depth 1 https://github.com/techtankto/techtank-siteWhat 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 | $0.00058 | $0.00487 |
| Opus 5 | $0.00029 | $0.00244 |
| Sonnet 5 | $0.00012 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
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 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.
What it actually says
Testing
What gets tested, at which layer, and how much of each.
The pyramid
Tests are shaped like a pyramid, narrowing as they get slower and more end-to-end:
- Unit (the base, most numerous). Pure functions, single components, isolated logic — fast, deterministic, no network/DOM/browser. Write these liberally; cheap to write, cheap to run.
- Integration (the middle, fewer). Multiple units wired together as they'd run in production — a component with its hooks, a route handler with its data layer. Covers the seams a unit test can't: whether A actually calls B correctly.
- End-to-end (the top, fewest). A real browser driving a real (or realistically mocked) app through a full user journey. Slow and expensive to write and maintain — reserved for the handful of flows whose breakage would be catastrophic (the primary conversion path, checkout, auth).
Fewer tests as you go up the pyramid, not more. An inverted pyramid (heavy e2e, thin unit) is slow, flaky, and expensive to maintain — flag it as a smell.
Rules
- Tests earn their place under the project's stated strategy. Don't add speculative coverage; each test maps to a real risk at its layer.
- The plumbing stays warm. The test runner stays wired and the test command stays green (it passes with no tests present), so a strategy can land without re-plumbing.
- Colocate tests with what they test. Unit and integration tests sit next to their source file; e2e tests live in their own top-level suite, since they don't belong to one file.
- Default to the lowest layer that catches the risk. Reach for a unit test before an integration test, and an integration test before an e2e test; climb the pyramid only when a lower layer genuinely can't catch the risk.
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 · 40 lines · 58 tokens per session scan A 72fa16ac4212
testing is a skill published in the GitHub repository techtankto/techtank-site (5 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 487 once invoked, about $0.0003 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…