litestar-security

litestar-security is a skill for Claude Code from litestar-org/litestar-skills. It costs 67 tokens per session (2,874 once invoked), scanned A, original, MIT.

A declarative authentication and authorization framework for Litestar, a Python web framework. Authentication checks who is calling; authorization checks what that caller may do.

In plain words
What is it for?
Configuring accounts, sessions, MFA, passkeys, OAuth/OIDC, API keys, JWTs, route authentication, permission guards, and current-user access in Litestar.
Why use it?
It helps developers keep identity checks and permission rules separate, avoiding incorrect use of Litestar’s security settings.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the litestar plugin — 31 skills, 1 agent, 1 hook shipped together

Good fit Configuring accounts, sessions, MFA, passkeys, OAuth/OIDC, API keys, JWTs, route authentication, permission guards, and current-user access in Litestar.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/litestar-org/litestar-skills/litestar-security
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.

Any agent
npx skills add litestar-org/litestar-skills --skill litestar-security
Clone the repo
git clone --depth 1 https://github.com/litestar-org/litestar-skills

Made for: Claude Code.

Or install litestar, the plugin that ships this one along with the rest of its 31 skills, 1 agent, 1 hook.

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 litestar-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/litestar-org/litestar-skills/litestar-security/github.svg)](https://agentmods.dev/skills/litestar-org/litestar-skills/litestar-security)
Your own site
<a href="https://agentmods.dev/skills/litestar-org/litestar-skills/litestar-security"><img src="https://agentmods.dev/badge/skills/litestar-org/litestar-skills/litestar-security/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 litestar-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/litestar-org/litestar-skills/litestar-security"><img src="https://agentmods.dev/badge/skills/litestar-org/litestar-skills/litestar-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,874 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00067 $0.02874
Opus 5 $0.00034 $0.01437
Sonnet 5 $0.00013 $0.00575
Haiku 4.5 $0.00007 $0.00287

Measured 11d ago against content hash 7a68d5ca96c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

litestar-security 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 11d 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.

plugins/litestar/skills/litestar-security/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Litestar Security

litestar-security 0.6.0 is a declarative authentication and authorization framework for Litestar. It provides credential slots and mechanisms, unified session management, local accounts, MFA, WebAuthn passkeys, OAuth/OIDC, API keys, workload JWTs, and browser hardening.

Two separate axes, wired through two separate Litestar keywords:

  • Authenticationwho is calling — is a policy on auth= (or opt={"auth": ...}).
  • Authorizationwhat they may do — is a predicate in Litestar's native guards=[...].

Do not conflate them: the policy helpers (public, required, any_of, all_of, at_least, optional, exclude, mechanism) take mechanism names, while the guard combinators (requires_any_of, requires_all_of, requires_at_least, requires_one_of) take predicates.

Code Style Rules

  • Declare authentication with auth=. Put policy on the route, or on a router/controller/app through opt={"auth": ...}. The nearest native owner wins.
  • Keep authorization in guards=[...]. Litestar's security= parameter is reserved for the OpenAPI requirements projected from auth.
  • Inject the user with CurrentUser[T]. Use NamedDependency[CurrentUser[UserType]]; it rejects anonymous and userless service principals. principal and security_context stay typed on public routes too.
  • Authorize from the snapshot. Guards read the AuthorizationSnapshot produced by the configured authorization_resolver. Never query the database inside a guard.
  • Compose predicates with requires_*. Use requires_any_of, requires_all_of, requires_at_least, requires_one_of for predicate composition.
  • Exclude other plugins' routes by path. Static assets and dashboards carry no auth and compile to implicit required(), so they answer 401 until listed in SecurityConfig(exclude=[...]). Inspect routes with litestar security routes.
  • Secure WebSockets with connect tokens. Browsers cannot set handshake headers; mint a short-lived token over authenticated HTTP via WebSocketConnectTokenService or WebSocketConnectTokenIssuer.
  • Load protector keys from a secret store. MFA and OAuth protectors need application-owned 32-byte AES-256-GCM keys, never source literals.

Read the full file on GitHub · 301 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 301 lines · 67 tokens per session scan A 7a68d5ca96c0

Subscribe to this mod's changes

litestar-security is a skill published in the GitHub repository litestar-org/litestar-skills (14 stars, last pushed 22d ago), licensed MIT. It adds 67 tokens to every session and 2,874 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 2026-08-30.

Related

Other skills, from other repositories

add-server-logic

Creates, edits, and manages Power Pages Server Logic files — server-side JavaScript that runs securely on the Power Pages runtime. Orchestrates the full lifecycle: gathering requirements, fetching documentation, implementing code, configuring site settings, and deploying. Use when the user wants to add server-side…

microsoft/power-platform-skills · 83 tokens

add-cloud-flow

Integrates Power Automate cloud flows into a Power Pages site. Lists available flows, suggests relevant ones based on intent, identifies scenarios and web roles, creates metadata files, and generates client-side code to call flows. Handles both new flow registration and adding already-registered flows to additional…

microsoft/power-platform-skills · 91 tokens

integrate-backend

Analyzes the user's business problem and recommends the right backend integration approach — Web API, AI Web API (generative summaries / grounded search), Server Logic, Cloud Flows, or a combination — for a Power Pages site, then routes to the appropriate specialized skill. Use when the user wants to add backend…

microsoft/power-platform-skills · 86 tokens

integrate-webapi

Integrates Power Pages Web API into a site's frontend code with proper permissions and deployment. Orchestrates the full integration lifecycle: code integration, table permissions setup, and deployment for Dataverse CRUD operations. Use when the user wants to add Web API calls, connect to Dataverse, or add data…

microsoft/power-platform-skills · 69 tokens

migrate-webapi-selectall

Reviews and migrates deprecated wildcard () values in Power Pages Web API fields site settings to least-privilege explicit Dataverse columns. Use whenever a user mentions Web API wildcard or select-all remediation, fields settings containing , data-exposure review, wildcard deprecation readiness, or Web API failures…

microsoft/power-platform-skills · 139 tokens

add-sharepoint

Adds SharePoint Online connector to a Power Apps code app. Use when reading lists, managing documents, or integrating with SharePoint sites. Can also create new SharePoint lists.

microsoft/power-platform-skills · 39 tokens