check-web

check-web is a command for Claude Code from OpenVidu/openvidu.io. It costs 15 tokens per session (566 once invoked), scanned A, original, Apache-2.0.

A command for checking website source files with the same convention checks and strict build used by continuous integration, the automated system that tests changes before merging.

In plain words
What is it for?
Use it for a quick lint check, or add `full` to also run the strict MkDocs site build.
Why use it?
It finds errors and warnings early, so website changes are less likely to fail the project's automated checks later.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/openvidu/openvidu.io/check-web
Clone the repo
git clone --depth 1 https://github.com/OpenVidu/openvidu.io

Made for: Claude Code.

Wrote 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.

agentmods badge for check-web

README.md
[![agentmods](https://agentmods.dev/badge/commands/openvidu/openvidu.io/check-web.svg)](https://agentmods.dev/commands/openvidu/openvidu.io/check-web)
Your own site
<a href="https://agentmods.dev/commands/openvidu/openvidu.io/check-web"><img src="https://agentmods.dev/badge/commands/openvidu/openvidu.io/check-web.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 566 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00566
Opus 5 $0.00008 $0.00283
Sonnet 5 $0.00003 $0.00113
Haiku 4.5 $0.00002 $0.00057

Measured 5d ago against content hash 32f7f54b2e00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check-web 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 5d 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.

.claude/commands/check-web.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate the current state of the website sources. Argument: $ARGUMENTS (empty for the fast check, full to add the strict build).

Fast check (always)

Run from the repo root:

ovweb lint

(If ovweb is not installed: pip install -e "./publish-tool[validate]" first.)

It reports [check] file:line: message — hint lines at three severities. Act on them:

  • error — CI fails on these. Fix every error in files this session touched; for errors in files you did not touch, fix them if the fix is unambiguous, otherwise list them for the user.
  • warn — convention violations that do not block CI. Fix the ones caused by this session's edits; report pre-existing ones without fixing (they may be deliberate).
  • info — janitorial; mention only if the user asked for a cleanup.

Never silence a finding by weakening the checker (publish-tool/src/ovweb/lint/) — the checker changes only when a convention itself changes, with the user's agreement. What each check enforces is documented in contributing/checks.md.

Full check (full argument)

After the fast check passes, also run what CI runs:

CI=false GOOGLE_ANALYTICS_KEY=G-XXXXXXXX mkdocs build --strict --site-dir /tmp/mkdocs-strict-validation
ovweb lint --site /tmp/mkdocs-strict-validation
  • The build must end with zero WARNINGs — any WARNING is a failure to fix.
  • Anchor INFO lines in the build log are expected noise (~110 pymdownx.tabbed false positives) — ovweb lint --site is the authoritative anchor check, since it resolves every fragment against the ids actually present in the built HTML.
  • If mkdocs is not installed locally, use the Docker image instead: docker run --rm -v ${PWD}:/docs -e GOOGLE_ANALYTICS_KEY=G-XXXXXXXX squidfunk/mkdocs-material build --strict -d /tmp/site.

If redirect rules or publish-tool/ovweb.yaml were touched this session, also run ovweb redirects check. If any page was deleted or renamed this session, also run ovweb lint --against origin/main — every removed page must be claimed by a redirect rule.

Read the full file on GitHub · 54 lines

Changes

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.

  1. 5d ago First seen · 54 lines · 15 tokens per session scan A 32f7f54b2e00

Subscribe to this mod's changes

check-web is a command published in the GitHub repository OpenVidu/openvidu.io (5 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 566 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.