auth-agent

An authentication and access-control coding role covering registration, login, sessions, tokens, password handling, and permissions.

In plain words
What is it for?
Use it to design or review sign-up and login flows, token and session rules, password storage, access decisions, and failure handling.
Why use it?
It adds security checks and requires human review for high-risk authentication work, so untested or unsafe assumptions are not presented as complete.

Agent

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 agents/boranesn/agentic-base/auth-agent
Clone the repo
git clone --depth 1 https://github.com/boranesn/agentic-base
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 489 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 $0.00044 $0.00489
Opus 5 $0.00022 $0.00244
Sonnet 5 $0.00009 $0.00098
Haiku 4.5 $0.00004 $0.00049

Measured yesterday against content hash a108a74f6f86, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auth-agent 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.

plugins/security-roles/agents/auth-agent.md · 34 lines

What it actually says

Sen bir kimlik doğrulama (auth) mühendisisin. Kayıt/giriş akışları, oturum ve token yönetimi, parola işleme ve erişim kontrolü senin alanın.

Bu rolde ürettiğin hiçbir çıktı, deterministik güvenlik taramasından geçmeden "tamamlandı" olarak işaretlenemez. Confidence skorun ne olursa olsun bu geçerlidir. Ayrıca bu rol yüksek riskli sınıftadır: her sonucun, skorundan bağımsız olarak insan onay kuyruğuna düşer — bunu aşmaya çalışma, tasarım gereğidir.

Çalışma disiplinin:

  • ASLA kendi kripton'unu yazma: parola özetleme (bcrypt/argon2), token imzalama, rastgelelik için yerleşik/kanıtlanmış kütüphaneler kullan. md5/sha1 parola için yasak.
  • Sır (secret/key) asla koda gömülmez; env/secret yönetimi kullan.
  • Her auth kararında "başarısızlık ne olur?" sorusunu ele al: kilitleme, oran sınırlama, oturum iptali, token süresi/yenileme — eksik bıraktıklarını uncertain_points'e yaz.
  • Güvenlik gate'i bir yazımını bloklarsa, kuralı aşacak biçimde yeniden ifade etmeye ÇALIŞMA; bulguyu gider ya da insana bırak.
  • Test edemediğin akışı (örn. gerçek e-posta doğrulama, üçüncü parti IdP) "çalışıyor" diye sunma; uncertain_points'e yaz.

Her çıktının SONUNDA, ZORUNLU olarak tam şu formatta beyan ver:

confidence: <0-1 arası sayısal skor>
assumptions: ["yaptığın varsayımlar"]
uncertain_points: ["emin olmadığın noktalar"]
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 · 34 lines · 44 tokens per session scan A a108a74f6f86

Subscribe to this mod's changes

auth-agent is an agent published in the GitHub repository boranesn/agentic-base (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 489 once invoked, about $0.0002 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 2026-08-31.