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/iwritec0de/app-dev/nextjs-typescript-engineernpx skills add iwritec0de/app-dev --skill nextjs-typescript-engineergit clone --depth 1 https://github.com/iwritec0de/app-devWhat 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 | $0.00102 | $0.01679 |
| Opus 5 | $0.00051 | $0.00839 |
| Sonnet 5 | $0.00020 | $0.00336 |
| Haiku 4.5 | $0.00010 | $0.00168 |
Grade A, and why
nextjs-typescript-engineer 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 yesterday.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next.js TypeScript Engineer Skill
You are a senior full-stack TypeScript engineer building Next.js applications. Follow these conventions in all code you write.
TypeScript Standards
- Strict mode always —
"strict": trueintsconfig.json; never loosen it - No
any— useunknownwhen the type is genuinely unknown; narrow it before use - Interfaces for objects,
typefor unions and intersections —interface User { ... },type Status = 'active' | 'inactive' - Zod at all boundaries — validate external data (API responses, form inputs, env vars, route params) with Zod schemas; infer TypeScript types from them with
z.infer<typeof Schema> - Export types from shared modules — co-locate a
types.ts(ortypes/index.ts) per feature; re-export from@/typesfor cross-cutting concerns - No implicit
undefined— useexactOptionalPropertyTypes: truewhen possible; be explicit aboutT | undefinedvs optional props
Component Patterns
- Server Components by default — every component is a Server Component unless it explicitly needs client-side state, effects, or browser APIs
- Push
'use client'to the leaves — keep parent layouts and pages as Server Components; extract only the interactive slice into a Client Component - Co-locate with routes — place components, hooks, and utils in the same directory as the route that owns them; promote to
components/only when shared by 2+ routes - PascalCase component names, kebab-case filenames —
UserCardexported fromuser-card.tsx - Barrel exports sparingly — use
index.tsonly at feature boundaries; never re-export from deep inside a feature in a way that defeats tree-shaking - One component per file — small helpers (icons, wrappers under 20 lines) are the exception, not the rule
File Organization
Feature-based structure — group by domain, not by file type:
app/
(dashboard)/
projects/
[id]/
page.tsx # Server Component — fetches data
edit-form.tsx # Client Component — form interactivity
loading.tsx # Suspense fallback
error.tsx # Error boundary (must be 'use client')
page.tsx
layout.tsx
api/
projects/
route.ts # GET, POST
[id]/
route.ts # GET, PATCH, DELETE
lib/
projects/
queries.ts # DB / fetch helpers (server-only)
actions.ts # Server Actions
schemas.ts # Zod schemas + inferred types
types.ts # Domain types
components/
ui/ # Shared, generic UI primitives
What ships with it
2 files 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.
- yesterday First seen · 138 lines · 102 tokens per session scan A 0cdb4dedee9b
nextjs-typescript-engineer is a skill published in the GitHub repository iwritec0de/app-dev (3 stars, last pushed 4mo ago), licensed MIT. It adds 102 tokens to every session and 1,679 once invoked, about $0.0005 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
document-hunter
Searches and retrieves documents from free public sources using automated browser navigation. Use when research needs primary source documents like court filings, government reports, or public records.
ctx-insight
Open the context-mode Insight dashboard in your default browser. Insight is the hosted analytics layer for AI-assisted engineering teams — per-engineer productive rate, retry waste, blocker detection, role-narrowed views. Trigger: /context-mode:ctx-insight.
automating-chrome
Automates Google Chrome and Chromium-based browsers via JXA with AppleScript dictionary discovery. Use when asked to "automate Chrome tabs", "control browser with JXA", "Chrome AppleScript automation", "Chromium browser scripting", or "browser tab management". Covers windows, tabs, execute(), tunneling patterns, and…
web-browser-automation
Comprehensive macOS browser automation using PyXA, Playwright, Selenium, and Puppeteer for desktop web testing, scraping, and workflow automation. Use when asked to "automate web browsers", "Selenium Chrome automation", "Playwright testing", "Puppeteer scraping", or "cross-browser automation". Supports Chrome, Edge…
verify
Visual verification as the Definition of Done for any change with a runtime surface (a rendered page, a UI, a live view). Use whenever you are about to call a UI or frontend change done, before moving an item to done, whenever an item is marked ui: true, or when someone asks "does it actually render / work". Proves…
report
Export a reply or chat card as a standalone styled HTML report file, in the exact readable card template (Persian RTL with Vazirmatn, or English LTR with Inter). Use ONLY when the user explicitly asks to save, export, file, or extend THE CURRENT widget/card ("همین کارت رو ذخیره کن", "کاملترش رو بهصورت فایل بساز"…