flins: Skill for Claude Code

.agents/skills/Convex Realtime/SKILL.md

Convex Realtime is a skill for Claude Code, Codex from powroom/flins. It costs 28 tokens per session (2,934 once invoked), scanned A, a copy of convex-realtime, MIT.

A guide for building Convex applications whose data updates automatically when the database changes.

In plain words
What is it for?
Use it for live database subscriptions, optimistic updates, caching, and loading paginated results with cursors.
Why use it?
It reduces the need to manually refresh data and explains how to handle temporary interface updates, cached results, and large lists.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is powroom/flins's own configuration. It tells Claude Code and Codex how to work on flins itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything flins configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { api } from "../convex/_generated/api";.

Reuse

Borrowing it

Nothing to install: this file belongs to powroom/flins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/powroom/flins/main/.agents/skills/Convex Realtime/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/powroom/flins

Made for: Claude Code, Codex.

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 Realtime

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/powroom/flins/convex-realtime"><img src="https://agentmods.dev/badge/skills/powroom/flins/convex-realtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,934 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.
Origin 98% copy Near-identical to another mod 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 $0.00028 $0.02934
Opus 5 $0.00014 $0.01467
Sonnet 5 $0.00006 $0.00587
Haiku 4.5 $0.00003 $0.00293

Measured 10d ago against content hash f5e742aeaf9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Convex Realtime 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 10d 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.

Origin

This is a copy

98% identical to convex-realtime — 3 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.

.agents/skills/Convex Realtime/SKILL.md · 443 lines

How it starts

The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convex Realtime

Build reactive applications with Convex's real-time subscriptions, optimistic updates, intelligent caching, and cursor-based pagination.

Documentation Sources

Before implementing, do not assume; fetch the latest documentation:

Instructions

How Convex Realtime Works

  1. Automatic Subscriptions - useQuery creates a subscription that updates automatically
  2. Smart Caching - Query results are cached and shared across components
  3. Consistency - All subscriptions see a consistent view of the database
  4. Efficient Updates - Only re-renders when relevant data changes

Basic Subscriptions

// React component with real-time data
import { useQuery } from "convex/react";
import { api } from "../convex/_generated/api";

function TaskList({ userId }: { userId: Id<"users"> }) {
  // Automatically subscribes and updates in real-time
  const tasks = useQuery(api.tasks.list, { userId });

  if (tasks === undefined) {
    return <div>Loading...</div>;
  }

  return (
    <ul>
      {tasks.map((task) => (
        <li key={task._id}>{task.title}</li>
      ))}
    </ul>
  );
}

Conditional Queries

import { useQuery } from "convex/react";
import { api } from "../convex/_generated/api";

function UserProfile({ userId }: { userId: Id<"users"> | null }) {
  // Skip query when userId is null
  const user = useQuery(
    api.users.get,
    userId ? { userId } : "skip"
  );

  if (userId === null) {
    return <div>Select a user</div>;
  }

  if (user === undefined) {
    return <div>Loading...</div>;
  }

  return <div>{user.name}</div>;
}

Mutations with Real-time Updates

import { useMutation, useQuery } from "convex/react";
import { api } from "../convex/_generated/api";

function TaskManager({ userId }: { userId: Id<"users"> }) {
  const tasks = useQuery(api.tasks.list, { userId });
  const createTask = useMutation(api.tasks.create);
  const toggleTask = useMutation(api.tasks.toggle);

  const handleCreate = async (title: string) => {
    // Mutation triggers automatic re-render when data changes
    await createTask({ title, userId });
  };

  const handleToggle = async (taskId: Id<"tasks">) => {
    await toggleTask({ taskId });
  };

  return (
    <div>
      <button onClick={() => handleCreate("New Task")}>Add Task</button>
      <ul>
        {tasks?.map((task) => (
          <li key={task._id} onClick={() => handleToggle(task._id)}>
            {task.completed ? "✓" : "○"} {task.title}
          </li>
        ))}
      </ul>
    </div>
  );
}

Read the full file on GitHub · 443 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. 10d ago First seen · 443 lines · 28 tokens per session scan A f5e742aeaf9e

Subscribe to this mod's changes

Convex Realtime is a skill published in the GitHub repository powroom/flins (39 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 2,934 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to convex-realtime, differing in 3 lines, and is treated as a copy.