robel-auth

robel-auth is a skill for Claude Code, Codex, Cursor from waynesutton/markdown-site. It costs 52 tokens per session (4,519 once invoked), scanned A, original, MIT.

A maintenance guide for Robelest Convex Auth, an authentication system used with Convex applications. It requires checking the latest upstream documentation and code before changing authentication.

In plain words
What is it for?
Use it when adding, updating, migrating, or debugging Robelest Convex Auth in an app.
Why use it?
It helps prevent auth changes from relying on outdated instructions or differences between development and release versions. It also provides a process for migrations and troubleshooting.

Skill for Claude CodeCodexCursor

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/waynesutton/markdown-site/robel-auth
Any agent
npx skills add waynesutton/markdown-site --skill robel-auth
Clone the repo
git clone --depth 1 https://github.com/waynesutton/markdown-site

Made for: Claude Code, Codex, Cursor.

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 robel-auth

README.md
[![agentmods](https://agentmods.dev/badge/skills/waynesutton/markdown-site/robel-auth.svg)](https://agentmods.dev/skills/waynesutton/markdown-site/robel-auth)
Your own site
<a href="https://agentmods.dev/skills/waynesutton/markdown-site/robel-auth"><img src="https://agentmods.dev/badge/skills/waynesutton/markdown-site/robel-auth.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,519 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 $0.00052 $0.04519
Opus 5 $0.00026 $0.02259
Sonnet 5 $0.00010 $0.00904
Haiku 4.5 $0.00005 $0.00452

Measured 4d ago against content hash a35e3e4ed1b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

robel-auth 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check-upstream.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.cursor/skills/robel-auth/SKILL.md · 464 lines

How it starts

The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Robel auth skill

Use this skill when a user asks to implement, update, or debug auth based on robelest/convex-auth.

This skill is designed to be copied into other repos.

Non negotiable upstream check before any auth change

Run this every time before proposing code or commands.

Preferred command:

bash .cursor/skills/robel-auth/scripts/check-upstream.sh

Manual checklist if script is unavailable:

  1. Read official docs: https://auth.estifanos.com/getting-started/installation/
  2. Read latest main README: https://raw.githubusercontent.com/robelest/convex-auth/main/README.md
  3. Read latest release README: https://raw.githubusercontent.com/robelest/convex-auth/release/README.md
  4. Check branch level differences: https://github.com/robelest/convex-auth/compare/release...main
  5. Read current self hosting docs if portal or static hosting is involved:
    • https://raw.githubusercontent.com/get-convex/self-hosting/main/INTEGRATION.md
    • https://github.com/get-convex/self-hosting

If main and release conflict, prefer the branch requested by the user. If unspecified, use release for stability and explain that choice.

Important assumptions for this skill

  • Treat the official docs site (auth.estifanos.com) and GitHub as sources of truth every time.
  • Do not assume npm package availability.
  • Validate package availability at execution time.
  • If npm is unavailable, use a GitHub source install pinned to a branch or commit.
  • Keep all Convex code type safe and validator complete.

Published package reality check (critical)

The docs site (auth.estifanos.com) and main branch sometimes describe APIs ahead of the latest preview release on npm. Before writing imports, always inspect what the installed version actually exports:

ls node_modules/@robelest/convex-auth/dist/providers/
cat node_modules/@robelest/convex-auth/dist/providers/index.js
cat node_modules/@robelest/convex-auth/dist/component/index.d.ts

As of 0.0.4-preview.30

Read the full file on GitHub · 464 lines

Files

What ships with it

1 file 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. 4d ago First seen · 464 lines · 52 tokens per session scan A a35e3e4ed1b2

Subscribe to this mod's changes

robel-auth is a skill published in the GitHub repository waynesutton/markdown-site (630 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 4,519 once invoked, about $0.0003 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

shieldcn-badges

Create polished shieldcn README badges, badge groups, charts, headers, sponsors grids, and full README hero sections. Use when a user wants shadcn/ui-styled badges, Shields.io replacement, npm/GitHub/CI/status badges, download charts, README header banners, contributor/sponsor images, or README Studio guidance.…

jal-co/shieldcn · 145 tokens

infisical-sync-skill

Expert knowledge for the Infisical Sync Hand — Infisical API reference, vault operations, error patterns, security guidance.

RightNow-AI/openfang · 31 tokens

soul-grader

Use when grading, reviewing, rewriting, or approving a Hermes Agent SOUL.md. Uses the SOUL.md field-guide research artifacts as the only normative source for what makes a good SOUL.md.

cobibean/soul-grader-skill · 45 tokens

anakinscraper

Scrape any website into clean markdown or structured JSON. Anti-detect browser, smart proxy rotation, AI-powered data extraction.

Anakin-Inc/anakin · 30 tokens

mb-ads

Create and review ads, and prepare provider-safe launch plans/checks. Flexible entry points: full pipeline (copy + images), copy only, images only, creative variations (hook library), video scripts, long-form video ads/VSL-style paid creative, video repurpose, compliance review, launch-plan, instrumentation, check, or…

noontide-co/mainbranch · 136 tokens

mb-setup

Bootstrap a new business folder with Main Branch structure, or migrate an existing single-offer folder to multi-offer. Use when: (1) New user needs Claude Code environment configured (2) User says "set up", "get started", "initialize", "bootstrap", "create my repo", "new business" (3) User is new to Main Branch and…

noontide-co/mainbranch · 142 tokens