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.
npx agentmods add instructions/yultyyev/better-auth-firebase-auth/agents-mdgit clone --depth 1 https://github.com/yultyyev/better-auth-firebase-authWrote 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.
[](https://agentmods.dev/instructions/yultyyev/better-auth-firebase-auth/agents-md)<a href="https://agentmods.dev/instructions/yultyyev/better-auth-firebase-auth/agents-md"><img src="https://agentmods.dev/badge/instructions/yultyyev/better-auth-firebase-auth/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02238 | $0.02238 |
| Opus 5 | $0.01119 | $0.01119 |
| Sonnet 5 | $0.00448 | $0.00448 |
| Haiku 4.5 | $0.00224 | $0.00224 |
Grade A, and why
better-auth-firebase-auth AGENTS.md 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.
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.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Assistant Guidelines
This document provides additional context for AI assistants working on this Better Auth Firebase Auth plugin project. Please read README.md first for project overview and features.
Note: All planned phases are complete. The plugin is fully implemented and ready for use.
Quick Reference
- Main Documentation: See README.md for project overview
- Contributing Guidelines: See Better Auth Contributing Guide
- Plugin Architecture: See Better Auth Plugin Guide
Current Project State
Phase 1: Project Foundation ✅ Complete Phase 2: Types and Core Structure ✅ Complete Phase 3: Server Plugin - Endpoints ✅ Complete Phase 4: Server Plugin - Hooks ✅ Complete Phase 5: Client Plugin - Methods ✅ Complete Phase 6: Tests ✅ Complete Phase 7: CI/CD and Example Project ✅ Complete
Supported Firebase Auth Providers
The plugin currently implements a subset of Firebase Authentication methods:
Implemented Providers
- Google OAuth (
/firebase-auth/sign-in-with-googleendpoint) - Email/Password (
/firebase-auth/sign-in-with-emailendpoint) - Password Reset with email verification and custom URLs
/firebase-auth/send-password-reset- Send reset email/firebase-auth/verify-password-reset-code- Verify reset code/firebase-auth/confirm-password-reset- Complete password reset
Not Implemented (but available in Firebase Auth)
Social Providers:
- Facebook, GitHub, Twitter/X, Microsoft, Apple, Yahoo, LinkedIn
Phone/SMS Authentication:
- Phone number sign-in with SMS verification
- Multi-factor authentication (MFA)
Other Methods:
- Anonymous authentication
- Custom authentication tokens
- SAML/OIDC providers
- Game Center (iOS), Play Games (Android)
Key Implementation Pattern
All authentication methods follow the same core flow:
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.
- 4d ago First seen · 242 lines · 2,238 tokens per session scan A e8a414fcbb41
better-auth-firebase-auth AGENTS.md is an instructions file published in the GitHub repository yultyyev/better-auth-firebase-auth (19 stars, last pushed 3d ago), licensed MIT. It adds 2,238 tokens to every session, about $0.0112 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.
Other instructions, from other repositories
instancez AGENTS.md
AGENTS.md instructions for instancez/instancez, covering agents.md, non-negotiables, common commands, architecture (the parts that span files) and things that look weird but are intentional.
b2b-saas-starter AGENTS.md
AGENTS.md instructions for brandhaug/b2b-saas-starter, covering b2b saas starter, intent node index, setup, dependencies and cross-cutting rules.
better-auth-firestore AGENTS.md
AGENTS.md instructions for yultyyev/better-auth-firestore, covering ai assistant guidelines, quick reference, current project state, project structure and key exports.
qauth AGENTS.md
AGENTS.md instructions for qauth-labs/qauth, covering general guidelines for working with nx, scaffolding & generators, when to use nxdocs, qauth project guide and architecture principles.
mcp-auth-adapter AGENTS.md
Instructions for velias/mcp-auth-adapter, covering agents.md, project overview, key responsibilities, tech stack and directory layout.
instancez CLAUDE.md
Claude Code instructions for instancez/instancez, a project described as: An LLM-friendly, single-binary, drop-in replacement to Supabase.