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.
npx skills add NovaCode37/claude-security-skills --skill jwt-inspectorgit clone --depth 1 https://github.com/NovaCode37/claude-security-skillsWrote 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.
[](https://agentmods.dev/skills/novacode37/claude-security-skills/jwt-inspector)<a href="https://agentmods.dev/skills/novacode37/claude-security-skills/jwt-inspector"><img src="https://agentmods.dev/badge/skills/novacode37/claude-security-skills/jwt-inspector/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.
<a href="https://agentmods.dev/skills/novacode37/claude-security-skills/jwt-inspector"><img src="https://agentmods.dev/badge/skills/novacode37/claude-security-skills/jwt-inspector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.00699 |
| Opus 5 | $0.00043 | $0.00349 |
| Sonnet 5 | $0.00017 | $0.00140 |
| Haiku 4.5 | $0.00009 | $0.00070 |
Grade A, and why
jwt-inspector 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JWT Inspector
Decode and audit JSON Web Tokens with no third-party dependencies. It splits the token, decodes header + payload, evaluates them against a set of security checks, and (for HMAC tokens) tries a fast offline crack of the signing secret against a wordlist.
When to use this skill
- "Decode / inspect this JWT."
- "Is this token configured securely?"
- "Does this JWT use a weak/guessable secret?"
- Auditing auth tokens during a security review.
Checks performed
- alg=none (critical) — unsigned, forgeable token.
- Symmetric alg (HS)* — HMAC verification key == signing secret; HS/RS confusion and brute-force risk.
- Missing
exp/ token never expires; excessively long lifetime. iatin the future, missingnbf, missingiss/aud/sub.- Weak HMAC secret (critical) — cracked from a built-in or supplied wordlist.
How to run it
# Decode + audit
python skills/jwt-inspector/inspector.py "<token>"
# Read token from stdin
echo "<token>" | python skills/jwt-inspector/inspector.py -
# Try cracking the HMAC secret with a custom wordlist
python skills/jwt-inspector/inspector.py "<token>" --secret-list rockyou.txt
# JSON output
python skills/jwt-inspector/inspector.py "<token>" --json
# Only fail CI on high/critical (claim-hygiene notes are LOW)
python skills/jwt-inspector/inspector.py "<token>" --min-severity high
Exit codes: 0 clean · 1 issues reported · 2 malformed input.
Every reported issue fails the build. The default reports everything down to
info (including exp-past); raise --min-severity to low/medium/high
to filter advisory notes out of both the report and the exit code.
Recommended workflow for Claude
- Run the inspector and read the decoded payload to understand the token.
- Report findings ordered by severity; explain the impact of each.
- If a secret was cracked, stress that the key is compromised — rotate it and move to an asymmetric algorithm (RS256/ES256) where feasible.
- Never treat a decoded payload as trusted: decoding ≠ verifying. Remind the user that signature verification with the correct key is what matters.
What ships with it
2 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.
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.
- yesterday Changed · +5 lines 5f125eafe5d8
- 11d ago First seen · 68 lines · 85 tokens per session scan A 1419db2746f5
jwt-inspector is a skill published in the GitHub repository NovaCode37/claude-security-skills (11 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 699 once invoked, about $0.0004 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.
Other skills, from other repositories
owasp-security
Use when reviewing code for security vulnerabilities, implementing authentication/authorization, handling user input, or discussing web application security. Covers OWASP Top 10:2025, ASVS 5.0, LLM Top 10 (2025), and Agentic AI security (2026).
report-writing
Bug bounty report writing for H1/Bugcrowd/Intigriti/Immunefi — report templates, human tone guidelines, impact-first writing, CVSS 3.1 scoring, title formula, impact statement formula, severity decision guide, downgrade counters, pre-submit checklist. Use after validating a finding and before submitting. Never use…
triage-validation
Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain table, CVSS 3.1 quick reference, severity decision guide, report title formula, 60-second pre-submit checklist. Use BEFORE writing any report. One wrong answer…
web2-recon
Web2 recon pipeline — subdomain enumeration (subfinder, Chaos API, assetfinder), live host discovery (dnsx, httpx), URL crawling (katana, waybackurls, gau), directory fuzzing (ffuf), JS analysis (LinkFinder, SecretFinder), continuous monitoring (new subdomain alerts, JS change detection, GitHub commit watch). Use when…
security-arsenal
Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. Use when you need specific payloads for XSS/SSRF/SQLi/XXE/IDOR/path-traversal, bypass techniques, or to check if a finding is submittable. Also use when asked about what NOT to submit.
web2-vuln-classes
Complete reference for 18 web2 bug classes with root causes, detection patterns, bypass tables, exploit techniques, and real paid examples. Covers IDOR, auth bypass, XSS, SSRF (11 IP bypass techniques), SQLi, business logic, race conditions, OAuth/OIDC, file upload (10 bypass techniques), GraphQL, LLM/AI (ASI01-ASI10…