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 OKHP3/skillz --skill published-keyboard-recovery-checkgit clone --depth 1 https://github.com/OKHP3/skillzWrote 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/okhp3/skillz/published-keyboard-recovery-check)<a href="https://agentmods.dev/skills/okhp3/skillz/published-keyboard-recovery-check"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/published-keyboard-recovery-check/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/okhp3/skillz/published-keyboard-recovery-check"><img src="https://agentmods.dev/badge/skills/okhp3/skillz/published-keyboard-recovery-check.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 | $0.00028 | $0.00454 |
| Opus 5 | $0.00014 | $0.00227 |
| Sonnet 5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
published-keyboard-recovery-check 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 11d 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
Published keyboard recovery check
Use when
Run after a Forge deploy (or on demand against the live site) to catch hosting or artifact differences that local validation cannot see -- a stale GitHub Pages artifact, a build that shipped without the failed-contract recovery path, or the keyboard-recovery behavior itself regressing once served from production.
Callable command
node .agents/skills/published-keyboard-recovery-check/run.mjs
Set FORGE_PUBLISHED_URL to point at a non-default deployment (defaults to
https://okhp3.github.io/skillz/). In a post-deploy CI job, set
EXPECTED_SOURCE_COMMIT to the commit that was just deployed (e.g.
${{ github.sha }}) so a lagging Pages artifact is reported before the
keyboard checks even run.
Inputs and outputs
The command drives a headless browser against the published site only --
plain, unauthenticated HTTPS requests, no repository access, no production
credentials. It forces a skill-detail contract load to fail and checks that
the failed-contract alert, the raw-markdown fallback link, and the focusable
panel remain keyboard reachable, exactly as validated locally by
artifacts/forge/scripts/test-review-surface-browser.mjs.
Failures are reported on two distinct channels so an operator does not confuse "the deploy did not ship" with "the deploy shipped a regression":
- Deployment failures (exit code
2,[deployment]prefix): the site or its catalog is unreachable, the published bundle never mounts, or the published catalog'ssourceCommitdoes not match the expected commit (a stale artifact). - Assertion failures (exit code
1,[assertion]prefix): the site and catalog are current, but the failed-contract alert, panel focus, or fallback-link keyboard reachability itself is broken.
Never paste credentials into the command; it does not need any.
What ships with it
1 file 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.
- 11d ago First seen · 49 lines · 28 tokens per session scan A ce83b55d3985
published-keyboard-recovery-check is a skill published in the GitHub repository OKHP3/skillz (3 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 454 once invoked, about $0.0001 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
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
devlab-web-visual-ops
A browser-based operations guide for web applications, including single-page apps, micro-frontends, and multi-page sites. It covers observing, navigating, interacting, inspecting, validating, and capturing pages with browser automation and visual fallbacks.
webapp-testing
Browser-tests a local webapp end to end — starts the app, installs Playwright if missing, writes a spec for the critical path plus edge cases, runs headless, captures screenshots, console and network logs on failure, and reports a pass/fail table with repro steps. Degrades to curl smoke tests when no browser is…
selenium-ui-test-generator
Generates Selenium WebDriver tests for React/Angular front-ends with STRICT loop prevention. Triggers on: "test UI", "generate Selenium tests", "test React app", "create E2E tests", "test front-end". WARNING: UI tests cost 3x more than unit tests -- generate selectively.