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/nevaberry/nevaberry-plugins/caddy-knowledge-patchnpx skills add Nevaberry/nevaberry-plugins --skill caddy-knowledge-patchgit clone --depth 1 https://github.com/Nevaberry/nevaberry-pluginsWhat 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 | $0.00009 | $0.02173 |
| Opus 5 | $0.00005 | $0.01086 |
| Sonnet 5 | $0.00002 | $0.00435 |
| Haiku 4.5 | $0.00001 | $0.00217 |
Grade A, and why
caddy-knowledge-patch 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Caddy Knowledge Patch
Use this patch when writing or reviewing Caddyfile or JSON configuration, upgrading Caddy, building custom binaries, or operating Caddy's HTTP, proxy, certificate, and telemetry features.
Reference index
| Reference | Topics |
|---|---|
| HTTP and Caddyfile | Imports, matchers, placeholders, headers, bodies, encoding, file serving, authentication, and security behavior |
| Reverse proxy | HTTPS upstreams, health checks, retries, load balancing, transports, FastCGI, trusted proxies, and forwarding |
| Automatic HTTPS and ECH | Activation, redirects, ACME, issuers, On-Demand TLS, shared storage, local HTTPS, ECH, and wildcard selection |
| TLS and PKI | Handshake policies, certificate selection, client authentication, trust pools, internal PKI, renewal, CA pools, and diagnostics |
| Server operations | Global server options, listeners, protocols, timeouts, socket activation, admin API, shutdown, storage, and runtime limits |
| Observability and extensions | Logs, metrics, tracing, CLI changes, build requirements, embedding, and module APIs |
Upgrade hazards and breaking behavior
Remove obsolete TLS storage rate limits
Caddy 2.9.0 removes the deprecated TLS JSON fields rate_limit and burst. Delete them before loading an older configuration in 2.9 or newer.
Update wildcard automation policy
Caddy 2.10.0 automatically prefers a managed wildcard certificate for covered subdomains and removes the experimental global auto_https prefer_wildcard option introduced in 2.9. To force a separate certificate for the literal site name, configure the site with:
foo.example.com {
tls force_automate
}
Account for HTTPS upstream Host rewriting
Since 2.11.1, an HTTPS reverse_proxy sets Host to {upstream_hostport} automatically. Remove redundant header_up Host {upstream_hostport} lines. Explicitly override Host if the upstream intentionally needs a different value.
What ships with it
7 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.
- 2d ago First seen · 206 lines · 9 tokens per session scan A 807de9dea122
caddy-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (24 stars, last pushed 6d ago), licensed MIT. It adds 9 tokens to every session and 2,173 once invoked, about $0.0000 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
api-workers
Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.
infrastructure-planning
Plan and document the required software, infrastructure, and logistics for a Paperclip company — domains, GitHub, Docker Hub, Kubernetes, Slack, Google Workspace, Stripe, shipping providers, and CI/CD pipelines. Use when setting up infrastructure for a new company or auditing what an existing company needs.
kubernetes
Kubernetes and GKE operations: kubectl, manifests, deployments, services, workload identity, autopilot, config connector, private clusters, and troubleshooting.
istio
Istio service mesh: traffic management, gateways, virtual services, destination rules, mTLS, authorization policies, EnvoyFilters, and observability.
terraform
Terraform infrastructure-as-code for provisioning cloud and Kubernetes resources: modules, state and backends, providers, and plan/apply workflows.
auth
Authentication/authorization infra with Keycloak and OAuth2-proxy. Use for identity providers, SSO, OIDC/SAML, realm/client config, user federation, and OAuth2-proxy sidecar or ingress auth on Kubernetes.