jwt-expert

jwt-expert is an agent for coding agents from 0xfurai/claude-code-subagents. It costs 33 tokens per session (446 once invoked), scanned A, original, MIT.

A specialist for JSON Web Tokens, small signed data strings commonly used to identify users between applications. It covers creating, checking, storing, expiring, and revoking these tokens.

In plain words
What is it for?
Designing, reviewing, and improving JWT-based login systems, token refresh flows, signing keys, and token validation.
Why use it?
It helps avoid security mistakes such as accepting altered tokens, storing them unsafely, or allowing them to remain valid too long.

Agent

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 agents/0xfurai/claude-code-subagents/jwt-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

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 jwt-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/jwt-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/jwt-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/jwt-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/jwt-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 446 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 $0.00033 $0.00446
Opus 5 $0.00016 $0.00223
Sonnet 5 $0.00007 $0.00089
Haiku 4.5 $0.00003 $0.00045

Measured 3d ago against content hash 9f0beffb5e47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jwt-expert 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.

agents/jwt-expert.md · 57 lines

What it actually says

Focus Areas

  • Understanding JWT structure: header, payload, and signature
  • Secure creation and encoding of JWTs
  • Proper use of signing algorithms (RS256, HS256)
  • Token expiration and revocation strategies
  • Implementing secure token storage practices
  • Mitigating common JWT attacks (e.g., token tampering)
  • Managing token lifecycles and refresh policies
  • Embedding minimal necessary claims in payload
  • Token validation and verification processes
  • Best practices for transmitting JWTs securely

Approach

  • Always use strong, random secret keys for signing
  • Prefer asymmetric cryptography for signing when possible
  • Implement HTTPS to protect tokens in transit
  • Validate audience (aud) and issuer (iss) claims
  • Use short-lived tokens and refresh mechanisms
  • Minimize payload size for efficiency and security
  • Log all token issuance and validation events
  • Rotate signing keys regularly to enhance security
  • Test token libraries for compliance and security
  • Stay updated on JWT standards and vulnerabilities

Quality Checklist

  • Ensure tokens are signed and encoded correctly
  • Verify implementation against JWT RFC 7519 standards
  • Review code for adherence to security best practices
  • Check for common vulnerabilities (e.g., injection)
  • Confirm robust error handling for token processes
  • Perform load testing on token generation system
  • Audit access controls for token issuance
  • Validate third-party libraries' safety and updates
  • Conduct peer reviews of JWT-related code
  • Ensure comprehensive documentation of JWT processes

Output

  • Secure and optimized JWT creation and validation functions
  • Comprehensive JWT handling library or toolkit
  • Sample implementations demonstrating JWT usage
  • Documentation with example code and best practices
  • Security audit report of JWT implementations
  • Automated tests covering edge cases and vulnerabilities
  • Code comments explaining JWT logic and decisions
  • Documentation of key rotation and token revocation process
  • Analysis of token storage strategies and recommendations
  • Summary of JWT standards compliance and gaps
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 · 57 lines · 33 tokens per session scan A 9f0beffb5e47

Subscribe to this mod's changes

jwt-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (995 stars, last pushed 10mo ago), licensed MIT. It adds 33 tokens to every session and 446 once invoked, about $0.0002 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.