convex

convex is a skill for Claude Code, Codex from waynesutton/convexskills. It costs 31 tokens per session (479 once invoked), scanned A, original, Apache-2.0.

An index of guidance for building applications with Convex, a backend platform that provides data storage, server functions, real-time updates, and related tools.

In plain words
What is it for?
Use it to choose instructions for database schemas, queries, data changes, live updates, webhooks, file storage, scheduled jobs, AI agents, reusable components, or security checks.
Why use it?
It helps you find the specific Convex guidance needed for a task instead of searching through unrelated patterns.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the convexskills plugin — 14 skills shipped together

Good fit Use it to choose instructions for database schemas, queries, data changes, live updates, webhooks, file storage, scheduled jobs, AI agents, reusable components, or security checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/waynesutton/convexskills/convex
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.

Any agent
npx skills add waynesutton/convexskills --skill convex
Clone the repo
git clone --depth 1 https://github.com/waynesutton/convexskills

Made for: Claude Code, Codex.

Or install convexskills, the plugin that ships this one along with the rest of its 14 skills.

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 convex

README.md
[![agentmods](https://agentmods.dev/badge/skills/waynesutton/convexskills/convex/github.svg)](https://agentmods.dev/skills/waynesutton/convexskills/convex)
Your own site
<a href="https://agentmods.dev/skills/waynesutton/convexskills/convex"><img src="https://agentmods.dev/badge/skills/waynesutton/convexskills/convex/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.

agentmods 80×15 button for convex

Your own site · 80×15
<a href="https://agentmods.dev/skills/waynesutton/convexskills/convex"><img src="https://agentmods.dev/badge/skills/waynesutton/convexskills/convex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 479 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk pass 17 Feb 2026
How audits are shown
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 $0.00031 $0.00479
Opus 5 $0.00015 $0.00239
Sonnet 5 $0.00006 $0.00096
Haiku 4.5 $0.00003 $0.00048

Measured 9d ago against content hash 59f65bc1a1d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

convex 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 9d 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.

skills/convex/SKILL.md · 63 lines

What it actually says

Convex Development Skills

This is an index skill for Convex development. Use specific skills for detailed guidance:

Core Development

Skill Command Use When
Functions /convex-functions Writing queries, mutations, actions
Schema /convex-schema-validator Defining database schemas and validators
Realtime /convex-realtime Building reactive subscriptions
HTTP Actions /convex-http-actions Webhooks and HTTP endpoints

Data & Storage

Skill Command Use When
File Storage /convex-file-storage File uploads, serving, storage
Migrations /convex-migrations Schema evolution, data backfills

Advanced Patterns

Skill Command Use When
Agents /convex-agents Building AI agents with tools
Cron Jobs /convex-cron-jobs Scheduled background tasks
Components /convex-component-authoring Reusable Convex packages

Security

Skill Command Use When
Security Check /convex-security-check Quick security audit checklist
Security Audit /convex-security-audit Deep security review

Guidelines

Skill Command Use When
Best Practices /convex-best-practices General patterns and guidelines

Quick Start

For most tasks:

  1. Start with /convex-best-practices for general patterns
  2. Use /convex-functions for writing backend logic
  3. Use /convex-schema-validator for data modeling
  4. Use specific skills as needed for your use case

Documentation

Files

What ships with it

3 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.

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. 9d ago First seen · 63 lines · 31 tokens per session scan A 59f65bc1a1d8

Subscribe to this mod's changes

convex is a skill published in the GitHub repository waynesutton/convexskills (404 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 479 once invoked, about $0.0002 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

use-si-coder

Legacy one-shot full-stack auto-deploy monolith. Runs scripts/deploy.js to create a GitHub repo, push local code via SSH, set up a Dokploy project, configure self-hosted Convex (Docker Compose) + Next.js, wire Hostinger DNS, and trigger + poll the deployment — zero human steps. Superseded by the modular /sc- skills…

rahmanef63/si-coder-agent · 90 tokens

sc-n8n

Drive a user-configured self-hosted or cloud n8n instance through the official @n8n/cli. List, inspect, create, update, activate, and verify workflows; inspect executions; manage projects, tags, variables, data tables, and packages without assuming a specific server, deployment platform, or account.

rahmanef63/si-coder-agent · 70 tokens

sc-stripe

(STUB / NOT IMPLEMENTED YET) Stripe payments setup — create products/prices, webhook endpoint registration, customer portal config, restricted API keys. Pairs with sc-convex for payments table mutations and HTTP webhook routes.

rahmanef63/si-coder-agent · 52 tokens

sc-supabase

(STUB / NOT IMPLEMENTED YET) Supabase backend as an alternative to self-hosted Convex. Create project, apply migrations from supabase/migrations, deploy Edge Functions, generate types. For projects where Postgres + Row-Level-Security is a better fit than Convex's reactive query model.

rahmanef63/si-coder-agent · 67 tokens

convex

Use when building with Convex, writing Convex functions, queries, mutations, actions, HTTP endpoints, defining database schemas/validators, configuring cron jobs, file storage, realtime subscriptions, AI agents, or security audits.

J-StaR-Films-Studios/VibeCode-Protocol-Suite · 47 tokens

sc-convex

Convex self-hosted operations on Dokploy. Deploy compose template, rotate admin key, push schema, configure @convex-dev/auth (JWTPRIVATEKEY + JWKS), and probe the three backend subdomains (api-, site-, dash-).

rahmanef63/si-coder-agent · 55 tokens