caddy-security is a security application and set of plugins for Caddy v2, a web server, that handles user authentication and controls access to HTTP requests. It supports methods including local, LDAP, OpenID Connect, OAuth 2.0, SAML, JWT, and PASETO, and is used to protect web services behind Caddy.
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 greenpau/caddy-security --skill skill-authoringgit clone --depth 1 https://github.com/greenpau/caddy-securityWrote 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/greenpau/caddy-security/skill-authoring)<a href="https://agentmods.dev/skills/greenpau/caddy-security/skill-authoring"><img src="https://agentmods.dev/badge/skills/greenpau/caddy-security/skill-authoring/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/greenpau/caddy-security/skill-authoring"><img src="https://agentmods.dev/badge/skills/greenpau/caddy-security/skill-authoring.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00045 | $0.01842 |
| Opus 5.5 | $0.00018 | $0.00737 |
| Sonnet 5.5 | $0.00009 | $0.00368 |
| Haiku 4.5 | $0.00005 | $0.00184 |
Grade A, and why
skill-authoring 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 today.
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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring
Inherit the default authoring workflow
Use the installed $skill-creator skill to apply the default authoring workflow. Read it completely and apply its initialization, naming, frontmatter, progressive-disclosure, metadata, validation, and testing guidance.
Apply this skill after $skill-creator. Where the two differ, retain the default requirements and add the repository hierarchy and engineering-contract requirements below.
Apply repository guidance
Read the caddy-security supplement for repository scope, documentation ownership, parser/source grounding, examples, and local validation. The requirements in this skill and its hierarchy contract take precedence over the supplement wherever they differ.
Build a routed skill hierarchy
Store every discoverable skill as a direct child of .codex/skills/<skill-name>/; do not nest discoverable skill directories inside one another.
Express hierarchy as actionable routing at any depth:
AGENTS.md --Use A to do X--> skill A --Use B to do Y--> skill B --> ...
Write each repo-local route in this form:
Use [skill-name](relative/path/to/SKILL.md) to perform a specific task.
Make the action specific enough that an agent can decide whether to load the linked skill. Put routes to broad skills in AGENTS.md. Put routes to narrower skills in the broad skill that delegates the work. A leaf skill needs no hierarchy boilerplate.
Do not add structural ancestry sections or require a downstream skill to link back to its router. The forward Use ... to ... statements define the hierarchy.
Read the skill routing contract when creating, moving, routing, or auditing a skill.
Treat cross-skill references that do not tell the agent to use a skill for a task as supporting links, not hierarchy routes.
Author project engineering contracts
Capture durable behavior and workflows needed to develop, review, operate, and verify caddy-security. Treat the Go source, tests, and skills as cooperating project authorities; update the owning skill when implementation work changes its contract.
What ships with it
4 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.
- today First seen · 169 lines · 45 tokens per session scan A f49609144353
skill-authoring is a skill published in the GitHub repository greenpau/caddy-security (2,263 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 1,842 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-25.
Other skills, from other repositories
auth-patterns
Use when implementing authentication (JWT, sessions, OAuth), authorization (RBAC, ABAC), password hashing, MFA, or security best practices for backend services.
auth0-docs
Auth0 — identity platform: auth flows, Universal Login, SSO, identity providers, MFA, RBAC, Actions, tokens.
JWT Security Testing
Comprehensive JWT token security testing including signature verification, expiration checks, algorithm confusion attacks, and claim validation.
security-review
Security Code Review: Reviews code for security vulnerabilities including authentication (OAuth2, JWT), authorization (RBAC, roles), API security, data protection, payment security, and common attack vectors. Use whenever the user wants a security review, penetration test analysis, threat model, or mentions OAuth2…
testing-api-authentication-weaknesses
Tests API authentication mechanisms for weaknesses including broken token validation, missing authentication on endpoints, weak password policies, credential stuffing susceptibility, token leakage in URLs or logs, and session management flaws. The tester evaluates JWT implementation, API key handling, OAuth flows, and…
implementing-jwt-signing-and-verification
JSON Web Tokens (JWT) defined in RFC 7519 are compact, URL-safe tokens used for authentication and authorization in web applications. This skill covers implementing secure JWT signing with HMAC-SHA256.