flins: Skill for Claude Code

.agents/skills/Convex Security Audit/SKILL.md

Convex Security Audit is a skill for Claude Code, Codex from powroom/flins. It costs 27 tokens per session (3,674 once invoked), scanned A, a copy of convex-security-audit, MIT.

A security review guide for Convex applications, where Convex is a backend service for storing data and running server-side functions.

In plain words
What is it for?
Use it to review authorization, data visibility, external API calls, rate limits, and sensitive Convex functions.
Why use it?
It helps find mistakes that could let the wrong user access data, call protected operations, abuse an endpoint, or trigger sensitive actions.

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 →

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 Security Audit/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 Security Audit

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/powroom/flins/convex-security-audit"><img src="https://agentmods.dev/badge/skills/powroom/flins/convex-security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,674 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% 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 $0.00027 $0.03674
Opus 5 $0.00014 $0.01837
Sonnet 5 $0.00005 $0.00735
Haiku 4.5 $0.00003 $0.00367

Measured 10d ago against content hash 73c90c2153d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Convex Security Audit scanned grade A 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 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.

Sends data to an external URLlowData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

const response = await fetch("https://api.example.com/query", { method: "POST",

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Origin

This is a copy

100% identical to convex-security-audit — 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 Security Audit/SKILL.md · 539 lines

How it starts

The opening of the file, as written. The whole thing — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convex Security Audit

Comprehensive security review patterns for Convex applications including authorization logic, data access boundaries, action isolation, rate limiting, and protecting sensitive operations.

Documentation Sources

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

Instructions

Security Audit Areas

  1. Authorization Logic - Who can do what
  2. Data Access Boundaries - What data users can see
  3. Action Isolation - Protecting external API calls
  4. Rate Limiting - Preventing abuse
  5. Sensitive Operations - Protecting critical functions

Authorization Logic Audit

Role-Based Access Control (RBAC)
// convex/lib/auth.ts
import { QueryCtx, MutationCtx } from "./_generated/server";
import { ConvexError } from "convex/values";
import { Doc } from "./_generated/dataModel";

type UserRole = "user" | "moderator" | "admin" | "superadmin";

const roleHierarchy: Record<UserRole, number> = {
  user: 0,
  moderator: 1,
  admin: 2,
  superadmin: 3,
};

export async function getUser(ctx: QueryCtx | MutationCtx): Promise<Doc<"users"> | null> {
  const identity = await ctx.auth.getUserIdentity();
  if (!identity) return null;
  
  return await ctx.db
    .query("users")
    .withIndex("by_tokenIdentifier", (q) => 
      q.eq("tokenIdentifier", identity.tokenIdentifier)
    )
    .unique();
}

export async function requireRole(
  ctx: QueryCtx | MutationCtx, 
  minRole: UserRole
): Promise<Doc<"users">> {
  const user = await getUser(ctx);
  
  if (!user) {
    throw new ConvexError({
      code: "UNAUTHENTICATED",
      message: "Authentication required",
    });
  }
  
  const userRoleLevel = roleHierarchy[user.role as UserRole] ?? 0;
  const requiredLevel = roleHierarchy[minRole];
  
  if (userRoleLevel < requiredLevel) {
    throw new ConvexError({
      code: "FORBIDDEN",
      message: `Role '${minRole}' or higher required`,
    });
  }
  
  return user;
}

// Permission-based check
type Permission = "read:users" | "write:users" | "delete:users" | "admin:system";

const rolePermissions: Record<UserRole, Permission[]> = {
  user: ["read:users"],
  moderator: ["read:users", "write:users"],
  admin: ["read:users", "write:users", "delete:users"],
  superadmin: ["read:users", "write:users", "delete:users", "admin:system"],
};

export async function requirePermission(
  ctx: QueryCtx | MutationCtx,
  permission: Permission
): Promise<Doc<"users">> {
  const user = await getUser(ctx);
  
  if (!user) {
    throw new ConvexError({ code: "UNAUTHENTICATED", message: "Authentication required" });
  }
  
  const userRole = user.role as UserRole;
  const permissions = rolePermissions[userRole] ?? [];
  
  if (!permissions.includes(permission)) {
    throw new ConvexError({
      code: "FORBIDDEN",
      message: `Permission '${permission}' required`,
    });
  }
  
  return user;
}

Read the full file on GitHub · 539 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 · 539 lines · 27 tokens per session scan A 73c90c2153d3

Subscribe to this mod's changes

Convex Security Audit is a skill published in the GitHub repository powroom/flins (39 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 3,674 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (sends data to an external url). It is 100% identical to convex-security-audit, differing in 3 lines, and is treated as a copy.

Related

Other skills, from other repositories

convex-security-audit

Deep security review patterns for authorization logic, data access boundaries, action isolation, rate limiting, and protecting sensitive operations.

waynesutton/convexskills · 28 tokens

convex-security-audit

Deep security review patterns for authorization logic, data access boundaries, action isolation, rate limiting, and protecting sensitive operations.

igor9silva/meseeks · 28 tokens

convex-security-audit

Deep security review patterns for authorization logic, data access boundaries, action isolation, rate limiting, and protecting sensitive operations.

J-StaR-Films-Studios/VibeCode-Protocol-Suite · 28 tokens

importing-a-codebase

Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).

JetBrains/thinkrail · 69 tokens

starting-a-new-project

Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.

JetBrains/thinkrail · 61 tokens

todos

This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…

JetBrains/thinkrail · 127 tokens