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 tensorshift/claude-nginx-skill --skill nginxgit clone --depth 1 https://github.com/tensorshift/claude-nginx-skillWrote 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/tensorshift/claude-nginx-skill/nginx)<a href="https://agentmods.dev/skills/tensorshift/claude-nginx-skill/nginx"><img src="https://agentmods.dev/badge/skills/tensorshift/claude-nginx-skill/nginx/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/tensorshift/claude-nginx-skill/nginx"><img src="https://agentmods.dev/badge/skills/tensorshift/claude-nginx-skill/nginx.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 | $0.00208 | $0.01793 |
| Opus 5 | $0.00104 | $0.00897 |
| Sonnet 5 | $0.00042 | $0.00359 |
| Haiku 4.5 | $0.00021 | $0.00179 |
Grade A, and why
nginx 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 9d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nginx
Deep, practical guidance for writing, configuring, reviewing, and debugging
nginx — a full-spectrum nginx assistant, not just an incident-response tool. Use
it for routine setup (new vhost, reverse proxy, TLS, caching, security) just as
much as for hard problems. On top of standard best practices it encodes
hard-won operational lessons (mobile/MTU black holes, DPI filtering, add_header
inheritance traps, HTTP/2 syntax drift across versions) so answers are correct
and version-aware instead of generic snippets.
What this skill helps with
Authoring & setup (the everyday case):
- Stand up a new site / virtual host from scratch (HTTP→HTTPS, certs, HTTP/2).
- Reverse proxy to an app: correct headers, WebSockets, timeouts, keep-alive.
- Frontends (SPA / Next.js / React), object storage (S3/MinIO), APIs.
- Load balancing and
upstreampools. - Caching (static + proxy cache), gzip/brotli compression.
- TLS/SSL setup and tuning, HTTP/3, OCSP stapling, redirects.
- Security hardening: headers, rate limiting, real-IP behind a CDN, allow/deny.
Review & refactor:
- Audit an existing
.confagainst the checklist below; clean up cruft.
Debug (when something's wrong):
- "Won't load", slow on mobile, VPN asymmetry, 502/504/413, redirect loops, cert/SNI errors — diagnosed from logs, not guesswork.
How to use this skill
- Identify the task type and jump to the matching reference. For setup/ authoring, produce a complete, correct config from the patterns in the references (adapted to the user's stack), then validate it. For debugging, diagnose from logs first, then make the minimal correct change — don't paste a generic config at a problem you haven't localized.
- Always preserve a path to rollback. Before editing a production
.conf, note the original. Never touchssl_certificate*lines unless explicitly asked. - Validate before declaring done. Every change must pass
nginx -t. Tell the user to runnginx -t && systemctl reload nginx(reload, not restart — reload is zero-downtime). - Be version-aware. Several directives changed syntax across nginx
releases (see Anti-patterns → "HTTP/2 syntax"). When unsure, ask for
nginx -vor use the backward-compatible form.
What ships with it
8 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.
- 9d ago First seen · 130 lines · 208 tokens per session scan A 7693095233e4
nginx is a skill published in the GitHub repository tensorshift/claude-nginx-skill (3 stars, last pushed 3mo ago), licensed MIT. It adds 208 tokens to every session and 1,793 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
aws-essentials
AWS core services guide covering Lambda, S3, RDS, IAM, SQS/SNS, DynamoDB, CloudFront with security and cost optimization patterns.
docker-kubernetes
Production Docker and Kubernetes patterns including multi-stage builds, minimal base images, non-root users, layer caching, docker-compose for development, K8s Deployments, Services, Ingress, ConfigMaps, Secrets, health checks, resource limits, HPA autoscaling, security contexts, and Helm chart basics. Use when…
vercel-deploy
Deploy to Vercel with edge functions, ISR, middleware, and proper caching. Use when deploying Next.js apps, configuring preview environments, or optimizing Vercel builds.
cost-optimization
Cloud cost optimization with concrete examples for right-sizing containers, CDN caching, database query costs, serverless tuning, spot instances, reserved capacity, and build time reduction.
terraform-iac
Terraform infrastructure as code with state management, modules, workspaces, lifecycle rules, and CI/CD patterns.
cloudflare-tunnel-routes
Give any local port (Gradio, Streamlit, FastAPI, webhook receiver, dev server, Docker container) a permanent HTTPS URL on a domain the user owns - in one command, no deployment. Use when the user says "my Gradio share link keeps changing", "replace share=True with a permanent URL", "stable URL for localhost:7860"…