convex-components

convex-components is a skill for Claude Code from PolarCoding85/convex-agent-skillz. It costs 42 tokens per session (1,294 once invoked), scanned A, original, MIT.

A reference for reusable Convex components, which are packages with their own database tables and functions that can be added to a Convex app. It explains how to install, configure, access, and use them safely in transactions.

In plain words
What is it for?
Use it when adding or configuring Convex Rate Limiter, Aggregate, Workpool, Workflow, or other components, including apps that need queued work, rate limits, totals, or durable multi-step processes.
Why use it?
It removes the need to learn each component’s setup and transaction behavior from scratch.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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.

agentmods
npx agentmods add skills/polarcoding85/convex-agent-skillz/convex-components-skill
Any agent
npx skills add PolarCoding85/convex-agent-skillz --skill convex-components-skill
Clone the repo
git clone --depth 1 https://github.com/PolarCoding85/convex-agent-skillz

Made for: Claude Code.

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-components

README.md
[![agentmods](https://agentmods.dev/badge/skills/polarcoding85/convex-agent-skillz/convex-components-skill.svg)](https://agentmods.dev/skills/polarcoding85/convex-agent-skillz/convex-components-skill)
Your own site
<a href="https://agentmods.dev/skills/polarcoding85/convex-agent-skillz/convex-components-skill"><img src="https://agentmods.dev/badge/skills/polarcoding85/convex-agent-skillz/convex-components-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00042 $0.01294
Opus 5 $0.00021 $0.00647
Sonnet 5 $0.00008 $0.00259
Haiku 4.5 $0.00004 $0.00129

Measured 6d ago against content hash 8c164169c6cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

convex-components 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 6d 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.

.claude/skills/convex-components-skill/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convex Components

Components are sandboxed packages with their own database tables, functions, and isolated execution.

Universal Installation Pattern

All components follow the same installation pattern:

npm install @convex-dev/<component-name>
// convex/convex.config.ts
import { defineApp } from 'convex/server';
import componentName from '@convex-dev/<component-name>/convex.config';

const app = defineApp();
app.use(componentName);

// Multiple instances with different names
app.use(componentName, { name: 'instance2' });

export default app;

Run npx convex dev to generate code.

Accessing Components

import { components } from './_generated/api';

// Default instance
const instance = new ComponentClass(components.componentName, {
  /* config */
});

// Named instance
const instance2 = new ComponentClass(components.instance2, {
  /* config */
});

Transaction Semantics

Component mutations participate in the parent transaction:

export const doWork = mutation({
  handler: async (ctx) => {
    await ctx.db.insert('myTable', { data: 'value' });
    await component.doSomething(ctx); // Same transaction

    // If mutation throws, BOTH writes roll back
  }
});

Component exceptions can be caught:

try {
  await rateLimiter.limit(ctx, 'myLimit', { throws: true });
} catch (e) {
  // Only component's writes roll back
  // Parent mutation can continue
}

Available Components

Durable Functions

  • Workflow - Long-running, durable code flows with retries
  • Workpool - Queue actions with parallelism limits
  • Action Retrier - Retry failed actions with backoff

Backend Utilities

Read the full file on GitHub · 177 lines

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. 6d ago First seen · 177 lines · 42 tokens per session scan A 8c164169c6cc

Subscribe to this mod's changes

convex-components is a skill published in the GitHub repository PolarCoding85/convex-agent-skillz (17 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 1,294 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.