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/appwrite/claude-plugin/typescriptnpx skills add appwrite/claude-plugin --skill typescriptgit clone --depth 1 https://github.com/appwrite/claude-pluginWhat 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 | $0.00079 | $0.05348 |
| Opus 5 | $0.00039 | $0.02674 |
| Sonnet 5 | $0.00016 | $0.01070 |
| Haiku 4.5 | $0.00008 | $0.00535 |
Grade C, and why
typescript scanned grade C with 1 finding 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
// Extract credentials from the redirect URL This is a copy
78% identical to appwrite-dotnet — 731 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 707 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Appwrite TypeScript SDK
Installation
# Web
npm install appwrite
# React Native
npm install react-native-appwrite
# Node.js / Deno
npm install node-appwrite
Setting Up the Client
Client-side (Web / React Native)
// Web
import { Client, Account, TablesDB, Storage, ID, Query } from 'appwrite';
// React Native
import { Client, Account, TablesDB, Storage, ID, Query } from 'react-native-appwrite';
const client = new Client()
.setEndpoint('https://<REGION>.cloud.appwrite.io/v1')
.setProject('[PROJECT_ID]');
Server-side (Node.js / Deno)
import { Client, Users, TablesDB, Storage, Functions, ID, Query } from 'node-appwrite';
const client = new Client()
.setEndpoint('https://<REGION>.cloud.appwrite.io/v1')
.setProject(process.env.APPWRITE_PROJECT_ID)
.setKey(process.env.APPWRITE_API_KEY);
Code Examples
Authentication (client-side)
const account = new Account(client);
// Email signup
await account.create({
userId: ID.unique(),
email: '[email protected]',
password: 'password123',
name: 'User Name'
});
// Email login
const session = await account.createEmailPasswordSession({
email: '[email protected]',
password: 'password123'
});
// OAuth login (Web)
account.createOAuth2Session({
provider: OAuthProvider.Github,
success: 'https://example.com/success',
failure: 'https://example.com/fail',
scopes: ['repo', 'user'] // optional — provider-specific scopes
});
// Get current user
const user = await account.get();
// Logout
await account.deleteSession({ sessionId: 'current' });
OAuth 2 Login (React Native)
Important:
createOAuth2Session()does not work on React Native. You must usecreateOAuth2Token()with deep linking instead.
Setup
Install the required dependencies:
npx expo install react-native-appwrite react-native-url-polyfill
npm install expo-auth-session expo-web-browser expo-linking
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 · 707 lines · 79 tokens per session scan C f77b5c3598f5
typescript is a skill published in the GitHub repository appwrite/claude-plugin (10 stars, last pushed 13d ago), licensed BSD-3-Clause. It adds 79 tokens to every session and 5,348 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). It is 78% identical to appwrite-dotnet, differing in 731 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…