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 EzraApple/skills-init --skill create-verificationgit clone --depth 1 https://github.com/EzraApple/skills-initWrote 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/ezraapple/skills-init/create-verification)<a href="https://agentmods.dev/skills/ezraapple/skills-init/create-verification"><img src="https://agentmods.dev/badge/skills/ezraapple/skills-init/create-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/ezraapple/skills-init/create-verification"><img src="https://agentmods.dev/badge/skills/ezraapple/skills-init/create-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00043 | $0.00387 |
| Opus 5.5 | $0.00017 | $0.00155 |
| Sonnet 5.5 | $0.00009 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
create-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 18d 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
Create verification
Write a repo-local .agents/skills/verify-<app>/SKILL.md that another agent can run to prove a real user journey. Adapt the name and location to an existing repo convention when one exists. Reuse the repository's working harness, fixtures, and checks before adding new ones.
Inspect the current entry points, startup commands, configuration, and app behavior. The recipe must identify the exact target and prove readiness, so an agent cannot accidentally test a stale server or the wrong environment. State required credentials and data as preconditions; do not embed secrets.
Make each journey reproducible:
- Start or connect to the target, verify its identity and ready state, and prepare isolated data.
- Perform a real action through the user-facing app, CLI, or API. Name the input and the expected visible result.
- Read back the resulting state or side effect through an independent surface when available. Record evidence that remains after cleanup.
- Remove only data and processes the recipe created. Track process ownership; never kill by a broad name or port match.
Use the environment the user asked to verify. For browser journeys, follow the user's preferred browser path and existing approval. Describe a blocked precondition honestly rather than replacing the real journey with a mock or a static check.
Run the written recipe, including the success and failure paths it claims to verify. Correct gaps found during that run. If access or setup prevents a path, mark it unverified and state the failed step, observed result, and what would unblock it. Keep the recipe short enough to run again; move long commands or fixture setup into a script only when that improves reliability.
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.
- 18d ago First seen · 22 lines · 43 tokens per session scan A 7bac808baad0
create-verification is a skill published in the GitHub repository EzraApple/skills-init (2 stars, last pushed 19d ago), licensed MIT. It adds 43 tokens to every session and 387 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 2026-10-16.
Other skills, from other repositories
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
running-livekit-simulations
Runs LiveKit agent simulations and acts on the results. Use when the user says "run my simulations", "regression test my agent before deploying", "run the scenarios", "use lk agent simulate", "did my agent pass", "why did this scenario fail", "run simulations in CI", "test the audio pipeline", "check turn-taking and…
test-runner
For a code change, pick the right test tier by change surface, run apc test with baseline diff, and report only NEW reds vs baseline back to the task's acceptance criterion. Separates envblocked from SUT red so a broken machine never fails the code.
qa/e2e-playwright
A method for writing Playwright end-to-end tests, which automate a browser to verify complete user journeys. It covers setup, reusable page objects, login reuse, API mocking, visual checks, multiple browsers and screen sizes, CI, and debugging.
patrol-e2e-testing
Use when writing E2E/integration tests, testing native interactions like permissions or system dialogs, capturing UI regressions, or validating cross-platform behavior (Patrol 4.x).