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 thienanblog/awesome-ai-agent-skills --skill testing-verificationgit clone --depth 1 https://github.com/thienanblog/awesome-ai-agent-skillsWrote 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/thienanblog/awesome-ai-agent-skills/testing-verification)<a href="https://agentmods.dev/skills/thienanblog/awesome-ai-agent-skills/testing-verification"><img src="https://agentmods.dev/badge/skills/thienanblog/awesome-ai-agent-skills/testing-verification/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/thienanblog/awesome-ai-agent-skills/testing-verification"><img src="https://agentmods.dev/badge/skills/thienanblog/awesome-ai-agent-skills/testing-verification.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 | $0.00041 | $0.00466 |
| Opus 5.5 | $0.00016 | $0.00186 |
| Sonnet 5.5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
testing-verification 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 27d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Verification
Verify observable behavior at the narrowest reliable level, using project conventions and the failure cost to choose coverage.
Delegation
Run in the main conversation by default. Delegation can increase usage: obtain explicit approval for the proposed agent count and scope before using subagents. Reuse that approval within its bounds; ask again before expanding the approved count or scope.
Select evidence
Inspect relevant contracts, nearby tests, fixtures, commands, and CI definitions. Choose checks that can fail for the behavior in question, including important negative paths. Use test-strategy.md when the test level or coverage tradeoff is unclear.
Prefer existing test infrastructure and stable fixtures. Test public behavior rather than incidental implementation details; avoid hidden network dependencies, production data, and timing-based assertions. Add automation when it protects meaningful behavior, without writing tests that simply mirror trivial edits.
Browser work
Use the browser surface the host and project policy designate for interactive, exploratory, screenshot, and visual comparison work. If that surface fails, troubleshoot it before falling back to another, and say which surface produced the evidence. When the user named a specific surface, get their direction before substituting a different one.
Source-controlled Playwright E2E provides repeatable regression coverage. Keep it distinct from a manual Browser pass. Read ui-visual-verification.md when comparison conditions or visual ambiguity matter.
Run and finish
Run focused checks and required repository gates. Investigate failures before broadening, and rerun only affected checks after a fix. Reuse passing results for unchanged responsibilities and equivalent conditions. A commit, PR, merge, or handoff alone does not justify repeating a suite.
Follow explicit testing budgets. Propose a broader suite only when it could resolve a material gap; ask when project policy or unapproved cost requires it. Finish once the evidence is sufficient.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 27d ago Changed · -2 lines ebd85d3ab82f
- 1mo ago Changed · -20 lines · -36 tokens per session 3bc8c40448b5
- 1mo ago First seen · 55 lines · 77 tokens per session scan A f92cc0590ea7
testing-verification is a skill published in the GitHub repository thienanblog/awesome-ai-agent-skills (70 stars, last pushed 27d ago), licensed Apache-2.0. It adds 41 tokens to every session and 466 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.