Agent skill

Auth Security

by majiayu000 in majiayu000/spellbook

OAuth 2.1 + JWT authentication security best practices. An agent skill from majiayu000/spellbook.

MITAuto-check passedBackend & APIs

Install Auth Security

skills CLI
$ npx skills add majiayu000/spellbook --skill auth-security -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install majiayu000/spellbook auth-security --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/majiayu000/spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/auth-security .claude/skills/auth-security && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
auth-security
GitHub stars
287
Token cost
~2.8k tokens
SKILL.md length
205 words
Files
5
Skills in repo
97
Repo updated
First seen
Licence
MIT

At a glance

OAuth 2.1 + JWT authentication security best practices. An agent skill from majiayu000/spellbook.

  • Implementing auth
  • SKILL.md covers Core Principles, OAuth 2.1 Key Changes, JWT Best Practices and Token Storage, plus 5 more sections
  • Runs TypeScript scripts from its folder; needs INVALID_TOKEN
  • API authorization

What it does

Auth Security is an agent skill from majiayu000/spellbook. OAuth 2.1 + JWT authentication security best practices. Use when implementing auth, API authorization, token management. Follows RFC 9700 (2025).

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files (for example `reference/attacks.md`, `reference/jwt.md` and `reference/oauth2.1.md`).

It sits in Backend & APIs, covering Authentication, OAuth and OpenID Connect and Authorization and RBAC. The repository describes itself as: Cross-runtime skills for Claude Code, Codex, and multi-agent workflows. The licence is MIT.

When your agent uses it

  • Implementing auth
  • API authorization
  • Token management

Example prompts

  • “/auth-security”

Requirements

  • Node.js
  • A credential in INVALID_TOKEN

What it can do on your machine

Read from SKILL.md and the folder at commit ed52af7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (TypeScript), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • INVALID_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Auth Security loads about 2.8k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 205 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from majiayu000/spellbook at commit ed52af7, republished under its MIT licence (© majiayu000). 205 words, ~2,771 tokens.

Download SKILL.mdSave it as .claude/skills/auth-security/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
auth-security
description
OAuth 2.1 + JWT authentication security best practices. Use when implementing auth, API authorization, token management. Follows RFC 9700 (2025).

Auth Security

Core Principles

  • OAuth 2.1 — Follow RFC 9700 (January 2025)
  • PKCE Required — All clients must use PKCE
  • Short-lived Tokens — Access tokens expire in 5-15 minutes
  • Token Rotation — Refresh tokens are single-use
  • HttpOnly Storage — Browser tokens in HttpOnly cookies
  • Explicit Algorithm — Never trust JWT header algorithm
  • No backwards compatibility — Delete deprecated auth flows

OAuth 2.1 Key Changes

Deprecated Flows (DO NOT USE)
FlowStatusReplacement
Implicit GrantRemovedAuthorization Code + PKCE
Password GrantRemovedAuthorization Code + PKCE
Auth Code without PKCERemovedMust use PKCE
Required: Authorization Code + PKCE
typescript
import crypto from 'crypto';

// 1. Generate code verifier (43-128 chars)
function generateCodeVerifier(): string {
  return crypto.randomBytes(32).toString('base64url');
}

// 2. Generate code challenge
function generateCodeChallenge(verifier: string): string {
  return crypto
    .createHash('sha256')
    .update(verifier)
    .digest('base64url');
}

// 3. Authorization request
const verifier = generateCodeVerifier();
const challenge = generateCodeChallenge(verifier);

const authUrl = new URL('https://auth.example.com/authorize');
authUrl.searchParams.set('response_type', 'code');
authUrl.searchParams.set('client_id', CLIENT_ID);
authUrl.searchParams.set('redirect_uri', REDIRECT_URI);
authUrl.searchParams.set('code_challenge', challenge);
authUrl.searchParams.set('code_challenge_method', 'S256');
authUrl.searchParams.set('scope', 'openid profile email');
authUrl.searchParams.set('state', generateState());

// 4. Token exchange (after redirect)
const tokenResponse = await fetch('https://auth.example.com/token', {
  method: 'POST',
  headers: { 'Content-Type': 'application/x-www-form-urlencoded' },
  body: new URLSearchParams({
    grant_type: 'authorization_code',
    code: authorizationCode,
    redirect_uri: REDIRECT_URI,
    client_id: CLIENT_ID,
    code_verifier: verifier, // Prove we initiated the request
  }),
});

JWT Best Practices

Algorithm Selection (2025)
PriorityAlgorithmNotes
1EdDSA (Ed25519)Most secure, quantum-resistant properties
2ES256 (ECDSA P-256)Widely supported, compact signatures
3PS256 (RSA-PSS)More secure than RS256
4RS256 (RSA PKCS#1)Best compatibility
typescript
// Recommended: ES256
import { SignJWT, jwtVerify } from 'jose';

const privateKey = await importPKCS8(PRIVATE_KEY_PEM, 'ES256');
const publicKey = await importSPKI(PUBLIC_KEY_PEM, 'ES256');

// Sign
const token = await new SignJWT({ sub: userId, scope: 'read write' })
  .setProtectedHeader({ alg: 'ES256', typ: 'JWT', kid: keyId })
  .setIssuer('https://auth.example.com')
  .setAudience('https://api.example.com')
  .setExpirationTime('15m')
  .setIssuedAt()
  .setJti(crypto.randomUUID())
  .sign(privateKey);
Token Structure
typescript
interface AccessTokenPayload {
  // Standard claims
  iss: string;  // Issuer
  sub: string;  // Subject (user ID)
  aud: string;  // Audience
  exp: number;  // Expiration (Unix timestamp)
  iat: number;  // Issued at
  jti: string;  // JWT ID (unique identifier)

  // Custom claims
  scope: string;      // Permissions
  email?: string;     // User email
  roles?: string[];   // User roles
}
Verification (Critical)
typescript
import { jwtVerify, errors } from 'jose';

async function verifyAccessToken(token: string): Promise<AccessTokenPayload> {
  try {
    const { payload } = await jwtVerify(token, publicKey, {
      // CRITICAL: Explicitly specify allowed algorithms
      algorithms: ['ES256'],

      // Validate standard claims
      issuer: 'https://auth.example.com',
      audience: 'https://api.example.com',

      // Clock tolerance for sync issues
      clockTolerance: 30,
    });

    // Additional validation
    if (!payload.scope?.includes('read')) {
      throw new Error('Insufficient scope');
    }

    return payload as AccessTokenPayload;
  } catch (err) {
    if (err instanceof errors.JWTExpired) {
      throw new AuthError('Token expired', 'TOKEN_EXPIRED');
    }
    if (err instanceof errors.JWTClaimValidationFailed) {
      throw new AuthError('Invalid token claims', 'INVALID_CLAIMS');
    }
    throw new AuthError('Invalid token', 'INVALID_TOKEN');
  }
}

Token Storage

Web Applications
typescript
// Set token in HttpOnly cookie (server-side)
function setAuthCookie(res: Response, token: string) {
  res.cookie('access_token', token, {
    httpOnly: true,     // Not accessible via JavaScript
    secure: true,       // HTTPS only
    sameSite: 'strict', // CSRF protection
    maxAge: 15 * 60 * 1000, // 15 minutes
    path: '/api',       // Only sent to API routes
  });
}

// Refresh token (longer-lived)
function setRefreshCookie(res: Response, token: string) {
  res.cookie('refresh_token', token, {
    httpOnly: true,
    secure: true,
    sameSite: 'strict',
    maxAge: 7 * 24 * 60 * 60 * 1000, // 7 days
    path: '/api/auth/refresh',  // Only for refresh endpoint
  });
}
Single Page Applications (SPA)
typescript
// Store in memory (NOT localStorage/sessionStorage)
class TokenManager {
  private accessToken: string | null = null;

  setToken(token: string) {
    this.accessToken = token;
  }

  getToken(): string | null {
    return this.accessToken;
  }

  clearToken() {
    this.accessToken = null;
  }
}

// Use with Refresh Token Rotation
// Refresh token in HttpOnly cookie
// Access token in memory
Storage Comparison
StorageXSS SafeCSRF SafePersistence
HttpOnly CookieYesNeeds SameSiteYes
MemoryYesYesNo (lost on reload)
localStorageNoYesYes
sessionStorageNoYesTab only

Refresh Token Rotation

Flow
1. Client sends refresh_token
2. Server validates refresh_token
3. Server generates NEW access_token + NEW refresh_token
4. Server INVALIDATES old refresh_token
5. Server returns new tokens
6. Client stores new tokens
Implementation
typescript
async function refreshTokens(refreshToken: string) {
  // Find token in database
  const stored = await db.refreshToken.findUnique({
    where: { token: hashToken(refreshToken) },
    include: { user: true },
  });

  if (!stored) {
    throw new AuthError('Invalid refresh token', 'INVALID_TOKEN');
  }

  // Check if already used (reuse detection)
  if (stored.usedAt) {
    // Potential token theft - revoke ALL user tokens
    await db.refreshToken.deleteMany({
      where: { userId: stored.userId },
    });

    // Alert security team
    await alertSecurityTeam({
      event: 'REFRESH_TOKEN_REUSE',
      userId: stored.userId,
      tokenId: stored.id,
    });

    throw new AuthError('Token reuse detected', 'TOKEN_REUSE');
  }

  // Check expiration
  if (stored.expiresAt < new Date()) {
    throw new AuthError('Refresh token expired', 'TOKEN_EXPIRED');
  }

  // Mark as used (but keep for reuse detection)
  await db.refreshToken.update({
    where: { id: stored.id },
    data: { usedAt: new Date() },
  });

  // Generate new tokens
  const newAccessToken = await generateAccessToken(stored.user);
  const newRefreshToken = await generateRefreshToken(stored.user);

  // Store new refresh token
  await db.refreshToken.create({
    data: {
      token: hashToken(newRefreshToken),
      userId: stored.userId,
      expiresAt: addDays(new Date(), 7),
      previousTokenId: stored.id, // Chain for audit
    },
  });

  return {
    accessToken: newAccessToken,
    refreshToken: newRefreshToken,
  };
}

Attack Prevention

Algorithm Confusion
typescript
// WRONG: Trusts header algorithm
jwt.verify(token, key); // Uses alg from header

// CORRECT: Explicit algorithm
jwt.verify(token, key, { algorithms: ['ES256'] });
CSRF Protection
typescript
// Use SameSite cookies
res.cookie('session', token, {
  sameSite: 'strict', // or 'lax' for cross-site links
});

// Or double-submit cookie pattern
const csrfToken = crypto.randomBytes(32).toString('hex');
res.cookie('csrf', csrfToken, { httpOnly: false });
// Client sends csrf token in header
XSS Protection
typescript
// Content Security Policy
res.setHeader('Content-Security-Policy', [
  "default-src 'self'",
  "script-src 'self'",
  "style-src 'self' 'unsafe-inline'",
].join('; '));

// Use HttpOnly cookies for tokens
// Never store tokens in localStorage
Token Binding (DPoP)
typescript
// Demonstration of Proof of Possession
// Bind token to client's key pair

const dpopProof = await new SignJWT({
  htm: 'POST',
  htu: 'https://api.example.com/resource',
  ath: await hashAccessToken(accessToken), // Access token hash
})
  .setProtectedHeader({ alg: 'ES256', typ: 'dpop+jwt', jwk: publicKey })
  .setJti(crypto.randomUUID())
  .setIssuedAt()
  .sign(privateKey);

// Send with request
fetch('https://api.example.com/resource', {
  headers: {
    Authorization: `DPoP ${accessToken}`,
    DPoP: dpopProof,
  },
});

Token Revocation

typescript
// Revoke all user tokens (e.g., password change, logout all)
async function revokeAllUserTokens(userId: string) {
  await db.refreshToken.deleteMany({
    where: { userId },
  });

  // If using token blacklist for access tokens
  await redis.sadd(`revoked:${userId}`, Date.now());
  await redis.expire(`revoked:${userId}`, 15 * 60); // 15 min (access token lifetime)
}

// Check blacklist during verification
async function isTokenRevoked(userId: string, iat: number): Promise<boolean> {
  const revokedAt = await redis.get(`revoked:${userId}`);
  return revokedAt && parseInt(revokedAt) > iat * 1000;
}

Checklist

markdown
## OAuth 2.1
- [ ] Using Authorization Code flow
- [ ] PKCE enabled for all clients
- [ ] No implicit or password grants
- [ ] Redirect URI exact matching

## JWT
- [ ] Using ES256 or EdDSA algorithm
- [ ] Explicit algorithm verification
- [ ] Short expiration (≤15 min)
- [ ] Unique jti for each token
- [ ] Issuer and audience validation

## Tokens
- [ ] HttpOnly cookies for web apps
- [ ] Refresh token rotation enabled
- [ ] Reuse detection implemented
- [ ] Token revocation mechanism

## Security
- [ ] HTTPS everywhere
- [ ] SameSite cookies
- [ ] CSP headers configured
- [ ] Rate limiting on auth endpoints
- [ ] Brute force protection

See Also

© majiayu000, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in skills/auth-security of majiayu000/spellbook.

  • SKILL.md
  • reference/attacks.md
  • reference/jwt.md
  • reference/oauth2.1.md
  • templates/typescript/auth.service.ts

Open the folder on GitHubat commit ed52af7

Compare with similar skills

Auth Security next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Auth Security compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Auth Security this skillmajiayu000/spellbook287—~2.8kAutomated safety check: PassMIT
Cognitoitsmostafa/aws-agent-skills1.2k1 repos~2.3kAutomated safety check: PassMIT
Auth Implementation Patternsynulihao/AgentSkillOS61710 repos~4.4kAutomated safety check: PassNone
Supercheck Security Authsupercheck-io/supercheck215—~1.2kAutomated safety check: PassAGPL-3.0
Authenticationcodewithmukesh/dotnet-claude-kit7551 repos~1.9kAutomated safety check: PassMIT
Spring Boot Security JWTgiuseppe-trisciuoglio/developer-kit356—~3.9kAutomated safety check: NotesMIT

Similar skills

  • Cognito

    itsmostafa/aws-agent-skills

    AWS Cognito user authentication and authorization service. An agent skill from itsmostafa/aws-agent-skills.

    1.2k GitHub starsUsed in 1 repo~2.3k tokens
    Backend & APIsAuto-check passed
  • Auth Implementation Patterns

    ynulihao/AgentSkillOS

    Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems.

    617 GitHub starsUsed in 10 repos~4.4k tokens
    Backend & APIsAuto-check passed
  • Supercheck Security Auth

    supercheck-io/supercheck

    Work on Supercheck authentication, RBAC, tenant isolation, sessions, API and trigger keys, invitations, project membership, project variables, OAuth, super-admin behavior, SSRF, or…

    215 GitHub stars~1.2k tokensUpdated today
    Backend & APIsAuto-check passed
  • Authentication

    codewithmukesh/dotnet-claude-kit

    Authentication and authorization for ASP.NET Core. An agent skill from codewithmukesh/dotnet-claude-kit.

    755 GitHub starsUsed in 1 repo~1.9k tokens
    Backend & APIsAuto-check passed
  • Spring Boot Security JWT

    giuseppe-trisciuoglio/developer-kit

    Provides JWT authentication and authorization patterns for Spring Boot 3.5.x covering token generation with JJWT, Bearer/cookie authentication, database/OAuth2 integration, and RBAC/permission-based…

    356 GitHub stars~3.9k tokensUpdated 29 days ago
    Backend & APIsAuto-check: notes
  • Authentication Patterns

    rohitg00/awesome-claude-code-toolkit

    Authentication and authorization patterns including OAuth2, JWT, RBAC, session management, and PKCE flows

    2.7k GitHub stars~1.4k tokensUpdated 5 mo ago
    Backend & APIsAuto-check passed

More from majiayu000/spellbook

All 97 skills in this repo
  • Skill Ecosystem Doctor

    majiayu000/spellbook

    Audits and repairs how coding-agent Skills are owned, copied and exposed across runtimes, from canonical sources to quarantine and retirement.

    287 GitHub stars~3k tokensUpdated yesterday
    Auto-check passed
  • AGENTS.md Scaffold

    majiayu000/spellbook

    Scans a repository for real evidence and proposes, or on request writes, a small stack of root and scoped AGENTS.md files with validation commands and generated-file boundaries.

    287 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Product Demo Builder

    majiayu000/spellbook

    Plans, produces or diagnoses evidence-backed product demo videos: script, capture plan, pacing checks and verified final media built on real product behavior.

    287 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed
  • Flowguard Task Guard

    majiayu000/spellbook

    Single entry point that routes long or ambiguous agent tasks, checks live state, bounds autonomous loops and leaves a resumable handoff.

    287 GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • npm Supply Chain Check

    majiayu000/spellbook

    Scans a repository, its lockfiles and node_modules for known malicious npm package versions and install-time indicators, using a read-only Python scanner.

    287 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Product Manager Toolkit

    majiayu000/spellbook

    Product management helpers: a RICE scoring script, an interview transcript analyzer and PRD templates for prioritizing features, synthesizing research and writing requirements.

    287 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Auth Security

What does Auth Security do?

OAuth 2.1 + JWT authentication security best practices. An agent skill from majiayu000/spellbook. Auth Security is an agent skill from majiayu000/spellbook.1 + JWT authentication security best practices.

When should I use Auth Security?

Auth Security fits situations like: implementing auth; API authorization; token management.

How do I install Auth Security in Claude Code?

Run `npx skills add majiayu000/spellbook --skill auth-security -a claude-code`. Or copy the skill folder (skills/auth-security in majiayu000/spellbook) into .claude/skills/auth-security in your project. Claude Code loads it when a task matches its description.

How do I install Auth Security in Codex?

Run `npx skills add majiayu000/spellbook --skill auth-security -a codex`. Or copy the skill folder (skills/auth-security in majiayu000/spellbook) into .agents/skills/auth-security in your project. Codex loads it when a task matches its description.

Can I use Auth Security in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add majiayu000/spellbook --skill auth-security -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auth-security, .gemini/skills/auth-security, .github/skills/auth-security and .opencode/skills/auth-security in your project.

What does Auth Security need to run?

Going by SKILL.md and its folder, Auth Security needs TypeScript for the scripts in its folder and credentials named INVALID_TOKEN. Our summary lists: Node.js; A credential in INVALID_TOKEN.

Does Auth Security access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Auth Security safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Auth Security use?

Auth Security is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Auth Security use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Auth Security?

Skills that share tags, products or a category with Auth Security: Cognito (itsmostafa/aws-agent-skills, 1.2k stars), Auth Implementation Patterns (ynulihao/AgentSkillOS, 617 stars), Supercheck Security Auth (supercheck-io/supercheck, 215 stars) and Authentication (codewithmukesh/dotnet-claude-kit, 755 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Auth Security?

majiayu000 (a GitHub user) maintains it in majiayu000/spellbook, which has 287 GitHub stars. The repository holds 97 skills in this directory. The repository was last updated on October 8, 2026.

Source: majiayu000/spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.