vauthenticator AGENTS.md

Project instructions for VAuthenticator, a repository containing an OAuth2 and OpenID Connect authorization server, a React admin interface, and Kubernetes deployment charts.

In plain words
What is it for?
Use it when changing authentication-server code, the management interface, Helm deployment assets, or their project-specific documentation.
Why use it?
It clarifies the boundaries between the three projects and identifies generated files that must not be edited directly.

Instructions file for CodexOpenCode

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 instructions/mrflick72/vauthenticator/agents-md
Clone the repo
git clone --depth 1 https://github.com/mrFlick72/vauthenticator

Made for: Codex, OpenCode.

Per session 197 This file is loaded in full into every session.
When invoked 197 The same file — it is already loaded in full.
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 $0.00197 $0.00197
Opus 5 $0.00098 $0.00098
Sonnet 5 $0.00039 $0.00039
Haiku 4.5 $0.00020 $0.00020

Measured yesterday against content hash c4e30440acc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vauthenticator 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 yesterday.

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.

AGENTS.md · 18 lines

What it actually says

This repository is a monorepo with 3 projects:

  • auth-server -> Kotlin OAuth2/OIDC Authorization Server
  • management-ui -> React/TypeScript admin UI
  • helm-charts -> Helm chart deployment assets

Always use the closest AGENTS.md file. Root instructions apply only when a subtree does not have its own guide or when the work is explicitly cross-project.

Project boundaries:

  • auth-server: backend authorization server, local auth-server assets, and auth-server docs
  • management-ui: standalone React admin UI, nginx local serving config, and UI docs
  • helm-charts: Kubernetes/Helm packaging and chart documentation

Never mix changes across projects unless explicitly requested. If a contract must change across projects, state that coupling clearly and update the related docs in the same change.

Do not edit generated outputs by hand, including auth-server/target, management-ui/dist, auth-server/dist, dependency directories, or packaged Helm chart archives.

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. yesterday First seen · 18 lines · 197 tokens per session scan A c4e30440acc0

Subscribe to this mod's changes

vauthenticator AGENTS.md is an instructions file published in the GitHub repository mrFlick72/vauthenticator (22 stars, last pushed 2d ago), licensed Apache-2.0. It adds 197 tokens to every session, about $0.0010 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.