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 agentmods add skills/paralleldrive/aidd/aidd-jwt-securitynpx skills add paralleldrive/aidd --skill aidd-jwt-securitygit clone --depth 1 https://github.com/paralleldrive/aiddWrote 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/paralleldrive/aidd/aidd-jwt-security)<a href="https://agentmods.dev/skills/paralleldrive/aidd/aidd-jwt-security"><img src="https://agentmods.dev/badge/skills/paralleldrive/aidd/aidd-jwt-security.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00031 | $0.00812 |
| Opus 5 | $0.00015 | $0.00406 |
| Sonnet 5 | $0.00006 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
aidd-jwt-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 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.
What it actually says
JWT Security Review
AVOID JWT if you can. Prefer opaque tokens with server-side sessions.
Patterns {
Session State
any(refresh token rotation, refresh reuse detection, jti denylist, jti revocation, token bound to session, token bound to device, logout invalidates token server-side) => Critical: Prefer opaque tokens with server-side sessions. You're tracking state anyway.
Storage & Transport
(token in localStorage or sessionStorage) => Critical: XSS vulnerable. Use httpOnly Secure SameSite=Strict cookies. (token in URL or query params) => Critical: Leaks via logs, Referer, browser history, analytics. (token logged or sent to analytics) => Critical: Scrub tokens from all logging pipelines. (SameSite=None or missing CSRF protection) => Critical: CSRF exposure. Use SameSite=Strict or add CSRF tokens.
Algorithm & Signature
(JWT 'none' algorithm) => Critical: Signature bypass. Reject unsigned tokens. (JWT verification disabled) => Critical: Always verify signatures. (jwt.decode without verify) => Critical: Use jwt.verify(). (alg from token used to select verification) => Critical: Alg confusion. Strict allowlist + key type must match algorithm. (HS256 or symmetric algorithm) => Critical: Use asymmetric algorithms (RS256/ES256).
Verification Failure Handling
(verification failure allows anonymous access) => Critical: Fail closed. Invalid token = no access. (verification failure allows partial or degraded access) => Critical: Fail closed. Invalid token = no access.
Token Purpose
(ID token used as access token) => Critical: Wrong token type. Use access tokens (typ: at+jwt) for API auth. (typ header not validated) => Critical: Reject tokens without expected typ. Prevents token confusion.
Key Handling
(kid used to fetch key from untrusted source) => Critical: SSRF/key injection. Allowlist kid values. (JWKS URL derived from iss without strict allowlist) => Critical: Attacker-controlled keys. Pin JWKS URLs. (JWKS endpoint not pinned or cached) => Warn: Cache JWKS with TTL. Validate kid against known set. (multi-issuer: verification keys shared across issuers) => Critical: Issuer key isolation required. One keyset per issuer.
Claims Validation
(iss not validated) => Critical: Confused deputy. Verify issuer matches expected value. (aud not validated) => Critical: Token reuse across services. Verify audience includes this service. (exp not validated) => Critical: Always check exp claim. (nbf present and not validated) => Critical: If present, must validate. Reject on failure. (iat present and not validated) => Critical: If present, must validate. Reject on failure. (nbf and iat not checked when absent) => Warn: Consider requiring nbf/iat. Validate with ≤60s clock skew.
Authorization
(roles or scopes trusted without server check) => Critical: Claims are assertions, not policy. Server must enforce.
Cookie Hardening
(cookie missing __Host- prefix) => Warn: Use __Host- to enforce Secure, Path=/, no Domain. (cookie Domain set to parent domain) => Warn: Subdomain hijacking. Omit Domain or use __Host-.
Lifetime
(access token lifetime >= 1 day) => Critical: Max 15 min for stateless JWT. (access token lifetime > 15 min and < 1 day) => Warn: Shorter is better. 15 min max recommended. }
What ships with it
1 file 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.
- 3d ago First seen · 62 lines · 31 tokens per session scan A f12abc620193
aidd-jwt-security is a skill published in the GitHub repository paralleldrive/aidd (380 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 812 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.
Other skills, from other repositories
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
adk-unit-design
Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to docs/design/{topic}/{unit}/index.md. It describes the code as implemented, not a proposed design, and its reader is a developer about…
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
channels-setup
Use when a developer wants to build their first CopilotKit Channels agent and get it answering in Slack or Microsoft Teams — "set up a channel", "connect my agent to Slack", "get my agent into Teams", or starting from nothing and wanting a working channel end to end. Covers the whole path: inspecting or scaffolding…