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 codecast-sh/codecast --skill cast-verifygit clone --depth 1 https://github.com/codecast-sh/codecastWrote 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/codecast-sh/codecast/cast-verify)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-verify"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-verify/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/codecast-sh/codecast/cast-verify"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-verify.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 | $0.00079 | $0.00471 |
| Opus 5.5 | $0.00032 | $0.00188 |
| Sonnet 5.5 | $0.00016 | $0.00094 |
| Haiku 4.5 | $0.00008 | $0.00047 |
Grade A, and why
cast-verify 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
Asserting success is worth nothing; evidence is what a reviewer can check without rerunning. The rule is: show it, then say it.
Checks
Run what the repository defines: typecheck, tests for the packages touched, lint. Fix what fails. Keep the exact command and the last lines of its output; they go in the evidence.
Exercise the change
Pick the surface that matches the change:
- Web:
cast browser open <url>in the human's Chrome, drive the flow withcast browser do, and capturecast browser shot --share --alt "<what it shows>"at the moments that prove the behaviour. A flow that a reader should watch:cast browsersteps with shots before and after. - CLI or API: run the real command against real data and keep the output.
- Backend: an end to end test or a request against the deployed function.
- Mobile: the simulator, with a screenshot via
cast image.
Test the failure path too when the change has one. A screenshot of the happy path alone proves half the claim.
Attach
cast task comment <id> -t review - <<'EVIDENCE'
Verified: <one line per claim, each with the command or the image link>
Not verified: <what remains and why>
EVIDENCE
Put the same images inline in the reply as  so the thread
shows them. When the change is on a pull request, the same block goes in the
PR description.
Then
Mark the task done only for the claims that have evidence: cast task done <id> -m "<what was verified and how>". Anything without evidence stays open
and is named in the reply as not verified.
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 · 49 lines · 79 tokens per session scan A e03ca536c88c
cast-verify is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 471 once invoked, about $0.0003 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 2026-09-15.
Other skills, from other repositories
e2e-check
Run E2E tests or interactive browser verification. Triggers on: 'run e2e', 'e2e test', 'browser test', 'check in browser', 'verify UI', 'interactive test'.
pn-testing-strategy
Testing strategy and pyramid. Unit/integration/E2E ratio, Vitest vs Playwright vs MSW, contract testing, and test-environment setup. Use when defining or reviewing a project's testing approach.
pn-smoke-tests
Run smoke or E2E tests, debug failures, and verify fixes. Use for end-to-end verification before or after changes.
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.
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.…
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…