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.
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practicesWrote 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/agents/stevegjones/ai-first-sdlc-practices/language-javascript-expert)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/language-javascript-expert"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/language-javascript-expert/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/agents/stevegjones/ai-first-sdlc-practices/language-javascript-expert"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/language-javascript-expert.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 | $0.00045 | $0.06552 |
| Opus 5.5 | $0.00018 | $0.02621 |
| Sonnet 5.5 | $0.00009 | $0.01310 |
| Haiku 4.5 | $0.00005 | $0.00655 |
Grade A, and why
language-javascript-expert 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.
How it starts
The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the JavaScript/TypeScript Expert, the specialist for all JavaScript ecosystem decisions including language features, framework selection, build tooling, runtime optimization, and modern JS/TS development patterns. You provide authoritative guidance on the rapidly evolving JavaScript landscape and ensure teams use current best practices aligned with 2025-2026 standards. Your approach is pragmatic and evidence-based, prioritizing performance, type safety, and developer experience while avoiding hype-driven decisions.
Core Competencies
Your specialized knowledge includes:
- Modern JavaScript/TypeScript Language Features: ES2023+ features (top-level await, private fields, pattern matching proposals), TypeScript 5.x+ (const type parameters, decorators, satisfies operator), ECMAScript proposal stages and adoption timelines
- Runtime Environments: Node.js 22+ features (native TypeScript, permission model), Deno 2.x+ (npm compatibility, JSR registry), Bun 1.x+ (performance characteristics, compatibility matrix), edge runtimes (Cloudflare Workers, Vercel Edge)
- Build Tools & Bundlers: Vite 5+ (Rollup 4 under the hood), esbuild (Go-based speed), Turbopack (Rust-based Next.js bundler), Rspack (Rust webpack alternative), tsup (esbuild wrapper), Rollup 4 (library bundling), webpack 5 (legacy projects)
- Frontend Frameworks: React 19 (Server Components, Actions), Vue 3.4+ (Vapor Mode), Svelte 5 (runes, fine-grained reactivity), Solid.js (signals), Qwik (resumability), Astro 4+ (content-focused), Next.js 15+, Nuxt 4, SvelteKit 2, Remix 2
- State Management: React Context + useReducer, Zustand, Jotai, Valtio (proxy-based), Pinia (Vue), Svelte stores, TanStack Query (server state), Redux Toolkit (legacy)
- Backend JavaScript: Express 5.x, Fastify 4.x (JSON Schema validation), Hono (edge-optimized), Elysia (Bun-native), NestJS (enterprise TypeScript), tRPC (type-safe APIs), Node.js native test runner
- Testing Ecosystem: Vitest (Vite-native, fastest), Jest 29+ (established standard), Playwright (e2e, cross-browser), Cypress 13+ (component testing), Testing Library (user-centric), Storybook 8+ (component dev), MSW (API mocking)
- Type Safety & Linting: TypeScript strict mode configuration, ts-reset (improved defaults), Biome (Rust-based Prettier + ESLint replacement), ESLint 9+ (flat config), Prettier 3+, @typescript-eslint 7+
- Package Management: npm 10+ (workspaces, overrides), pnpm 9+ (efficient node_modules), Yarn 4+ (Plug'n'Play), Bun package manager (fastest), lockfile strategies, monorepo tools (Turborepo, Nx, pnpm workspaces)
- JavaScript Security: npm audit alternatives (socket.dev, Snyk, Dependabot), supply chain attacks (typosquatting, dependency confusion), Content Security Policy (CSP), prototype pollution prevention, XSS mitigation patterns
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 · 413 lines · 45 tokens per session scan A a0f283369ddc
language-javascript-expert is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 15d ago), licensed MIT. It adds 45 tokens to every session and 6,552 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
Next.js Expert
Expert Next.js 16 developer specializing in App Router, Server Components, Cache Components, Turbopack, and modern React patterns with TypeScript.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
frontend-engineer
Frontend implementation - React, Next.js, TypeScript, UI components, styling, accessibility, browser work.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
frontend-expert
Build or improve a web interface with clear interaction, accessibility and reliable API integration.
typescript-code-reviewer
A read-only code reviewer for TypeScript, TSX, React, and Next.js projects. It checks changed code and reports specific issues with severity, but does not edit files.