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 agentmods add skills/adambien/airails/javascript-conventionsnpx skills add AdamBien/airails --skill javascript-conventionsgit clone --depth 1 https://github.com/AdamBien/airailsWhat 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 | $0.00200 | $0.04326 |
| Opus 5 | $0.00100 | $0.02163 |
| Sonnet 5 | $0.00040 | $0.00865 |
| Haiku 4.5 | $0.00020 | $0.00433 |
Grade A, and why
javascript-conventions 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply all rules below strictly to any JavaScript you write, generate, or review.
Scope
- Language-level rules for JavaScript only — modules, syntax, functions, data, asynchrony, errors, JSDoc types, naming, comments.
- HTML, CSS, accessibility, and design tokens are not in this skill — see
web-conventions. - Architecture, state management, routing, dependency and build policy, project layout, dev server, and verification loops are not in this skill — see
web-components(SPAs) andweb-sprinkles(static sites with bounded enhancements);web-staticforbids JavaScript entirely. - When a composed skill specifies a rule, the composed skill wins; this skill is the fallback baseline.
Language Level
- target the newest ECMAScript syntax and standard-library APIs the Baseline policy permits — the decision is per feature, never per year: there is no "ES2020 target" to configure, only a feature's Baseline status
- no build step to reach a language feature — no transpiler (Babel, SWC, esbuild), no polyfill bundle; if a feature needs compiling, its Baseline status already says not to use it
- no TypeScript, no JSX — plain ES modules with JSDoc type annotations
- modules are strict mode already — never write
'use strict'
Baseline Lookup for JavaScript
The web-conventions Baseline policy governs JavaScript exactly as it governs CSS:
- Widely Available — use freely
- Newly Available — requires feature detection with a graceful fallback
- Limited availability — must not be used
CSS detects with @supports; JavaScript's equivalent is an existence check before first use:
const groupBy = Object.groupBy ?? ((items, key) => items.reduce(intoGroups(key), {}));
if (!document.startViewTransition) return render(url);
if (!('URLPattern' in globalThis)) return matchWithRegExp(url);
- look up the feature id in
web-conventions/references/baseline-snapshot.md— never from model memory; widely-known features can still be Limited (top-level await is, in the 2026-07-08 snapshot) - a feature missing from the snapshot or newer than its header date is uncertain — verify against webstatus.dev before recommending it, or treat it as Limited
- core syntax may have no feature id at all — optional chaining (
?.) returns 404 from the API (verified 2026-08-04), meaning untracked, not Limited; judge such syntax on its own rather than by lookup - when recommending a newer API, cite its status so the reader can judge support
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.
- 2d ago First seen · 236 lines · 200 tokens per session scan A 8bbedadce253
javascript-conventions is a skill published in the GitHub repository AdamBien/airails (47 stars, last pushed 12d ago), licensed MIT. It adds 200 tokens to every session and 4,326 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.
Other skills, from other repositories
sandbox-next
Use when building or changing Cloudflare Sandbox apps on @cloudflare/sandbox@next (Sandbox SDK 1.0 preview)—code execution, AI runners, interpreters, CI-like jobs, terminals, files, mounts, tunnels, preview URLs, lifecycle, or errors. Not for the default stable package (use sandbox-stable) or for porting stable to…
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…
80-livekit-agents-majiayu000-claude-skill-registr
Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.
turnstile-spin
Set up Cloudflare Turnstile end-to-end in a project. Scan the codebase, create the widget via the Cloudflare API, embed it where user requests need bot verification (form submissions, SPA actions, API endpoints, download links, comment or vote submissions, etc.), wire canonical server-side siteverify in the customer's…
dag-factory
Authors Apache Airflow DAGs declaratively from dag-factory YAML configs. Use when building DAGs declaratively from YAML via dag-factory; creating/editing dag-factory templates/YAML configs,reating/editing dag-factory YAML configs, defaults, dynamic tasks, datasets, or callbacks; or validating dag-factory…
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.