agentmods.dev

access-control

access-control is a skill for Claude Code from bethanychamberlain/claude-skills-librechat. It costs 64 tokens per session (1,430 once invoked), scanned A, original, MIT.

A LibreChat access-control guide for deciding what users can see, do, and spend in the application. It covers roles, groups, and multi-tenant setups, where separate user groups share one service.

In plain words
What is it for?
Use it to enforce agent-only access, set spending limits, manage balances, configure per-course or per-group access, and implement role-based permissions.
Why use it?
It helps administrators restrict models and features, control registration, and manage spending or balances. It also provides patterns for different user groups such as students, staff, or customers.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the librechat-security plugin — 2 skills shipped together

not rated 3repo 5mo ago A scan 64 tokens original MIT

Good fit Use it to enforce agent-only access, set spending limits, manage balances, configure per-course or per-group access, and implement role-based permissions.

Compare 6 skills from other repositories ↓
View source ↗ bethanychamberlain/claude-skills-librechat
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add bethanychamberlain/claude-skills-librechat
Claude Code
/plugin install librechat-security

Made for: Claude Code.

Or install librechat-security, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

agentmods badge for access-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/bethanychamberlain/claude-skills-librechat/access-control/github.svg)](https://agentmods.dev/skills/bethanychamberlain/claude-skills-librechat/access-control)
Your own site
<a href="https://agentmods.dev/skills/bethanychamberlain/claude-skills-librechat/access-control"><img src="https://agentmods.dev/badge/skills/bethanychamberlain/claude-skills-librechat/access-control/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.

agentmods 80×15 button for access-control

Your own site · 80×15
<a href="https://agentmods.dev/skills/bethanychamberlain/claude-skills-librechat/access-control"><img src="https://agentmods.dev/badge/skills/bethanychamberlain/claude-skills-librechat/access-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,430 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00064 $0.01430
Opus 5 $0.00032 $0.00715
Sonnet 5 $0.00013 $0.00286
Haiku 4.5 $0.00006 $0.00143

Measured 10d ago against content hash b3624df86ce2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

access-control 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 10d 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.

librechat-security/skills/access-control/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LibreChat Access Control

You are an expert in LibreChat access control and user restrictions. Your goal is to help administrators control what users can see, do, and spend inside LibreChat.

Before Starting

Check for context first: If librechat-context.md exists in the current working directory, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

If librechat-context.md does not exist, ask the user:

  1. What LibreChat version are you running?
  2. How is it deployed? (Docker local / Docker remote / cloud / Kubernetes)
  3. Who are the users? (students, faculty, employees, public)
  4. What model providers are currently configured?

Then offer: "Would you like me to save this as librechat-context.md so you don't have to answer these again?"

How This Skill Works

Mode 1: Design Access Control Strategy

When the user wants to plan access restrictions but is not sure what to configure.

  1. Ask about user groups, use cases, and risk tolerance
  2. Load ${CLAUDE_PLUGIN_ROOT}/references/access-patterns.md to show available patterns
  3. Recommend a pattern and explain trade-offs
  4. Walk through implementation step by step using Mode 2

Mode 2: Implement a Specific Restriction

When the user knows what they want to restrict.

  1. Identify which restriction mechanism(s) are needed:
    • modelSpecs for controlling which models/endpoints users see
    • interface for hiding UI elements (endpoints menu, model selector, presets, parameters, agents, etc.)
    • balance for spending limits
    • registration for controlling who can sign up
    • agents endpoint config for agent capabilities and builder access
  2. Load the relevant reference doc(s) from ${CLAUDE_PLUGIN_ROOT}/references/
  3. Produce exact YAML for librechat.yaml and/or .env changes
  4. Show restart command and verification steps

Mode 3: Audit Existing Access

When the user wants to review current access settings for security gaps.

  1. Read their librechat.yaml file
  2. Check for each risk area listed in Proactive Triggers below
  3. Produce a report: what is restricted, what is open, and recommendations
  4. Offer to fix any issues found

Read the full file on GitHub · 110 lines

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. 10d ago First seen · 110 lines · 64 tokens per session scan A b3624df86ce2

Subscribe to this mod's changes

access-control is a skill published in the GitHub repository bethanychamberlain/claude-skills-librechat (3 stars, last pushed 5mo ago), licensed MIT. It adds 64 tokens to every session and 1,430 once invoked, about $0.0003 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.

Backend and APIsClaude CodeSecurityagent-skillsagentic-aianthropic-claudeclaude-aiclaude-code-plugins
Related

Other skills, from other repositories

TEMPLATE

../../../agents/personas/TEMPLATE.md.

alirezarezvani/claude-skills · 0 tokens

api-documenter

Auto-generate API documentation from code and comments. Use when API endpoints change, or user mentions API docs. Creates OpenAPI/Swagger specs from code. Triggers on API file changes, documentation requests, endpoint additions.

alirezarezvani/claude-code-tresor · 48 tokens

dev-auth

Modern web auth implementation (better-auth, Lucia, NextAuth/Auth.js, Clerk, Supabase Auth). Trigger when the user wants to add login, signup, sessions, OAuth, magic links, 2FA, or when existing auth code is detected to audit or migrate.

christopherlouet/claude-base · 58 tokens

dev-nextjs

Next.js development (App Router, Server Components, caching, streaming). Trigger when the user works with Next.js, modifies app/, pages/, next.config, or talks about RSC, Server Actions, Route Handlers, middleware.

christopherlouet/claude-base · 50 tokens

dev-api

Develop and document a REST, GraphQL, or tRPC API, including versioning strategy. Use when the user wants to create an endpoint, a route, a type-safe procedure, or structure/version an API.

christopherlouet/claude-base · 46 tokens

dev-supabase

Backend development with Supabase. Trigger when the user wants to configure auth, the database, or Supabase storage.

christopherlouet/claude-base · 28 tokens