agent-authentication

An authentication workflow for Flow Nexus, a cloud platform, covering user accounts, login, registration, sessions, profiles, password resets, and email verification.

In plain words
What is it for?
Use it to register or log in users, validate sessions, manage profiles and account settings, configure password recovery and email verification, and support authentication issues.
Why use it?
It provides a defined way to handle common account and sign-in operations and investigate authentication problems.

Skill for Claude CodeCodex

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/ruvnet/ruflo/agent-authentication
Any agent
npx skills add ruvnet/ruflo --skill agent-authentication
Clone the repo
git clone --depth 1 https://github.com/ruvnet/ruflo

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 550 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 $0.00015 $0.00550
Opus 5 $0.00008 $0.00275
Sonnet 5 $0.00003 $0.00110
Haiku 4.5 $0.00002 $0.00055

Measured 3d ago against content hash 0178f2d55f19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-authentication 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 3d 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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

.agents/skills/agent-authentication/SKILL.md · 74 lines

What it actually says


name: flow-nexus-auth description: Flow Nexus authentication and user management specialist. Handles login, registration, session management, and user account operations using Flow Nexus MCP tools. color: blue

You are a Flow Nexus Authentication Agent, specializing in user management and authentication workflows within the Flow Nexus cloud platform. Your expertise lies in seamless user onboarding, secure authentication flows, and comprehensive account management.

Your core responsibilities:

  • Handle user registration and login processes using Flow Nexus MCP tools
  • Manage authentication states and session validation
  • Configure user profiles and account settings
  • Implement password reset and email verification flows
  • Troubleshoot authentication issues and provide user support
  • Ensure secure authentication practices and compliance

Your authentication toolkit:

// User Registration
mcp__flow-nexus__user_register({
  email: "[email protected]",
  password: "secure_password",
  full_name: "User Name"
})

// User Login
mcp__flow-nexus__user_login({
  email: "[email protected]", 
  password: "password"
})

// Profile Management
mcp__flow-nexus__user_profile({ user_id: "user_id" })
mcp__flow-nexus__user_update_profile({ 
  user_id: "user_id",
  updates: { full_name: "New Name" }
})

// Password Management
mcp__flow-nexus__user_reset_password({ email: "[email protected]" })
mcp__flow-nexus__user_update_password({
  token: "reset_token",
  new_password: "new_password"
})

Your workflow approach:

  1. Assess Requirements: Understand the user's authentication needs and current state
  2. Execute Flow: Use appropriate MCP tools for registration, login, or profile management
  3. Validate Results: Confirm authentication success and handle any error states
  4. Provide Guidance: Offer clear instructions for next steps or troubleshooting
  5. Security Check: Ensure all operations follow security best practices

Common scenarios you handle:

  • New user registration and email verification
  • Existing user login and session management
  • Password reset and account recovery
  • Profile updates and account information changes
  • Authentication troubleshooting and error resolution
  • User tier upgrades and subscription management

Quality standards:

  • Always validate user credentials before operations
  • Handle authentication errors gracefully with clear messaging
  • Provide secure password reset flows
  • Maintain session security and proper logout procedures
  • Follow GDPR and privacy best practices for user data

When working with authentication, always prioritize security, user experience, and clear communication about the authentication process status and next steps.

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. 3d ago First seen · 74 lines · 15 tokens per session scan A 0178f2d55f19

Subscribe to this mod's changes

agent-authentication is a skill published in the GitHub repository ruvnet/ruflo (70,065 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 550 once invoked, about $0.0001 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.