web-latest

web-latest is a skill for Claude Code from AdamBien/airails. It costs 204 tokens per session (1,122 once invoked), scanned A, original, MIT.

A setting for web experiments that lets you use newer browser features, including experimental or flag-controlled ones, without requiring fallbacks.

In plain words
What is it for?
Use it when building a proof of concept or testing recent web platform features with web-related skills.
Why use it?
It removes browser-support checks that can slow down prototypes. Accessibility, semantic HTML, and other rules still apply.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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 skills/adambien/airails/web-latest
Any agent
npx skills add AdamBien/airails --skill web-latest
Clone the repo
git clone --depth 1 https://github.com/AdamBien/airails

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 web-latest

README.md
[![agentmods](https://agentmods.dev/badge/skills/adambien/airails/web-latest.svg)](https://agentmods.dev/skills/adambien/airails/web-latest)
Your own site
<a href="https://agentmods.dev/skills/adambien/airails/web-latest"><img src="https://agentmods.dev/badge/skills/adambien/airails/web-latest.svg" alt="Measured on agentmods" height="20"></a>
Per session 204 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,122 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 5.1 $0.00204 $0.01122
Opus 5 $0.00102 $0.00561
Sonnet 5 $0.00041 $0.00224
Haiku 4.5 $0.00020 $0.00112

Measured 6d ago against content hash 05bd28cbc82c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

web-latest 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 6d 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.

web/web-latest/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use the most recent web platform features freely in $ARGUMENTS. This is a modifier skill — it changes exactly one thing about the composed stack: the browser-support policy.

Purpose & Precedence

Experiments and PoCs exist to explore what the newest browsers can do; a support policy designed for production audiences would defeat their purpose. When composed with /web-static, /web-sprinkles, or /web-components (and their shared /web-conventions), this skill overrides:

  • the Baseline Policy section of /web-conventions
  • the Baseline check of /web-static's verification loop (replaced below)
  • any @supports or existence-check requirements the stack skills impose on Newly Available features — feature detection becomes optional

Everything else in the composed skills remains binding. Explicitly not relaxed:

  • accessibility rules, including prefers-reduced-motion and prefers-color-scheme
  • semantic HTML and heading hierarchy
  • /web-static's no-JavaScript constraint
  • /web-sprinkles' enhancement contract — detection becomes optional, but a page whose content depends on an experimental API is broken, not experimental
  • /web-components' dependency and architecture rules
  • design-token discipline

A PoC that is inaccessible or unsemantic demonstrates nothing about the feature it showcases.

Relaxed Policy

  • any Baseline status is usable: Widely Available, Newly Available, Limited availability, and experimental or flag-gated features
  • no @supports wrappers required, no fallbacks required, no graceful-degradation argument needed
  • the view-transition exemptions carved out in /web-static and /web-components are subsumed by this policy — no special casing needed
  • when a feature exists in several maturity stages (e.g. a spec revision only Canary ships), prefer the newest form that runs in at least one stable or pre-release browser

Honesty Stays

The policy changes; the lookup discipline does not. A PoC is only useful if the viewer can actually run it, so:

Read the full file on GitHub · 78 lines

Files

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.

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. 6d ago First seen · 78 lines · 204 tokens per session scan A 05bd28cbc82c

Subscribe to this mod's changes

web-latest is a skill published in the GitHub repository AdamBien/airails (48 stars, last pushed 2d ago), licensed MIT. It adds 204 tokens to every session and 1,122 once invoked, about $0.0010 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 2026-08-30.

Related

Other skills, from other repositories

openkb-html-critic

Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…

VectifyAI/OpenKB · 132 tokens

eval-graphics

Turn an eval study's numbers into on-brand, publish-ready figures using the Newsjack chart room (the eval design system), then validate them with Playwright. For producing the charts in a published eval/data study.

elvisun/newsjack · 47 tokens

airflow-plugins

Builds Airflow 3.1+ plugins that embed FastAPI apps, custom UI pages, React components, middleware, macros, and operator links directly into the Airflow UI. Use when building anything custom inside Airflow 3.1+ that involves Python and a browser-facing interface - creating an Airflow plugin, adding a custom UI page or…

astronomer/agents · 147 tokens

authoring-java-sdk-tasks

Writes Airflow task logic in Java, Kotlin, or any JVM language using the Airflow Java SDK. Use when the user wants to implement Airflow tasks in Java/JVM, asks about @Builder.Dag/@Builder.Task/@Builder.XCom, the Task/BundleBuilder interfaces, reading connections/variables/XComs from Java, the JSON-to-Java type…

astronomer/agents · 152 tokens

configuring-airflow-language-sdks

Configures Airflow to run language SDK tasks (Java, Go, and future native SDKs) — register a coordinator, map a queue to it, ensure the runtime/artifact on workers, and tune coordinator options. Use when the user wants Airflow to route a queue to a native-language coordinator, asks about the [sdk]…

astronomer/agents · 155 tokens

decocms-ui

Build or style React UI with the decocms product design system (@decocms/ui). Use when creating interfaces, pages, or components in a project that should look like decocms products, when the user mentions "design system", "@decocms/ui", "decocms style", or asks to make UI consistent with Studio. Covers installation…

decocms/studio · 91 tokens