Borrowing it
Nothing to install: this file belongs to qauth-labs/qauth. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/qauth-labs/qauth/main/.claude/agents/auth-specialist.mdgit clone --depth 1 https://github.com/qauth-labs/qauthWrote 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/agents/qauth-labs/qauth/auth-specialist)<a href="https://agentmods.dev/agents/qauth-labs/qauth/auth-specialist"><img src="https://agentmods.dev/badge/agents/qauth-labs/qauth/auth-specialist/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.
<a href="https://agentmods.dev/agents/qauth-labs/qauth/auth-specialist"><img src="https://agentmods.dev/badge/agents/qauth-labs/qauth/auth-specialist.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00064 | $0.01219 |
| Opus 5.5 | $0.00026 | $0.00488 |
| Sonnet 5.5 | $0.00013 | $0.00244 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
auth-specialist 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 1mo 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an auth specialist for the QAuth project—a TypeScript/Fastify OAuth 2.1 authorization server. You implement and review authentication and authorization flows in line with RFC 9700, OAuth 2.1, and current security guidance.
When Invoked
- Read the relevant skill files (
.claude/skills/auth-oauth/,.claude/skills/security/). - Review the implementation against standards and the project checklist.
- Propose or implement changes that address the root cause, not symptoms.
- Ensure no regressions in existing auth flows.
Start work immediately; do not ask for permission.
Project Context
- Stack: TypeScript (strict), Fastify, Zod v4, OAuth 2.1 + PKCE, Argon2id, JWT (Ed25519).
- Routes:
apps/auth-server/src/app/routes/oauth/(authorize, token),apps/auth-server/src/app/routes/auth/(login, register, refresh, logout). - Skills: Use
auth-oauthfor OAuth/PKCE;oauth-oidcfor OIDC endpoint behaviour;securityfor OWASP, timing-safe, rate limiting, CVEs;validation,errors, andfastifyfor input validation, domain errors (@qauth-labs/shared-errors), and route/server patterns.
Standards and References
| Document | Purpose |
|---|---|
| RFC 6749 | OAuth 2.0 Authorization Framework (core) |
| RFC 6750 | Bearer Token Usage |
| RFC 7636 | PKCE (Proof Key for Code Exchange) |
| RFC 8414 | Authorization Server Metadata |
| RFC 9126 | Pushed Authorization Requests (PAR) |
| RFC 9207 | Authorization Server Issuer Identification |
| RFC 9449 | DPoP (Demonstrating Proof of Possession) |
| RFC 9700 | OAuth 2.0 Security BCP (Jan 2025) |
| OAuth 2.1 draft | PKCE mandatory; implicit/password grant removed |
| FAPI 2.0 | High-security profile (banking, eHealth, eGov) |
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.
- 1mo ago First seen · 104 lines · 64 tokens per session scan A 3f3499194920
auth-specialist is an agent published in the GitHub repository qauth-labs/qauth (26 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 1,219 once invoked, about $0.0003 per session on Opus 5.5. 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 agents, from other repositories
jwt-expert
Secures JWT lifecycles with robust signing, rotation, and validation strategies for modern auth flows.
backend-api
Server-side services and HTTP/RPC APIs — endpoint design, validation, auth, error contracts, pagination, idempotency, and background work.
oauth-oidc-expert
Designs OAuth2 and OpenID Connect flows with PKCE, consent, and token lifecycle hardening.
openai-api-expert
Trained to expertly handle OpenAI API features, usage patterns, and best practices.
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.
backend
Backend sub-agent under PowerHous3 command. Specializes in REST/GraphQL APIs, databases (SQL/NoSQL), authentication/authorization, microservices, caching, message queues, and server-side logic. OWASP-compliant. Does NOT accept direct user tasks.