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 trumb/claude-nginx-hardening --skill nginx-hardeninggit clone --depth 1 https://github.com/trumb/claude-nginx-hardeningWrote 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/trumb/claude-nginx-hardening/nginx-hardening)<a href="https://agentmods.dev/skills/trumb/claude-nginx-hardening/nginx-hardening"><img src="https://agentmods.dev/badge/skills/trumb/claude-nginx-hardening/nginx-hardening/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/trumb/claude-nginx-hardening/nginx-hardening"><img src="https://agentmods.dev/badge/skills/trumb/claude-nginx-hardening/nginx-hardening.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 | $0.00052 | $0.02969 |
| Opus 5 | $0.00026 | $0.01484 |
| Sonnet 5 | $0.00010 | $0.00594 |
| Haiku 4.5 | $0.00005 | $0.00297 |
Grade B, and why
nginx-hardening scanned grade B with 1 finding 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 11d 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.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
| 25 | SSH key/cloud creds | Credential file theft | `/.ssh/id_rsa`, `/.aws/credentials`, `/.gcp/credentials.json` | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nginx Hardening Skill — Core Reference
1. Overview
This plugin provides full-lifecycle nginx security hardening through Claude Code. It audits static configs, analyzes access logs for attack patterns, generates blocking rules, and deploys changes through a gated pipeline.
Design goals:
- Preserve availability — never propose a rule that could block legitimate traffic without explicit human approval
- Never expose raw attacker data to LLM — all log data is hex-encoded or sanitized before reaching any agent layer
- Additive-only — rules are appended, never modify or remove existing directives
- Deterministic writes — all file mutations happen through non-LLM scripts (sanitizer.py, invariant-checker.py), never by agent output
- Staged recommendation by default — findings are presented for human review; enforcement requires explicit opt-in
2. Operating Modes
| Mode | Permission | Trigger | Actions |
|---|---|---|---|
| Recommendation (default) | R0 (read config), R1 (read logs) | Any audit or analysis command | Static analysis, log parsing, finding generation, rule proposals — all read-only |
| Enforcement | W1 (stage files), W2 (write config), X1 (reload nginx) | Explicit --enforce flag or human acceptance at decision gate |
Backup, write rule, run invariant checks, nginx -t, deploy, reload |
Recommendation Mode never modifies any file. Enforcement Mode requires passing all 5 pipeline layers including human approval at Layer 4.
3. Analysis Levels
| Level | Scope | Checks | Activation |
|---|---|---|---|
| L1 — Static Config | nginx conf files | Headers (HSTS, CSP, X-Frame, X-Content-Type, Referrer-Policy, Permissions-Policy), TLS floor (protocol versions, cipher posture), unsafe directives (autoindex, server_tokens, merge_slashes off), include hierarchy (circular, missing, duplicated), duplicate/shadowed directives, location block precedence and regex ordering, wildcard server_name, access/error logging presence, rate-limiting configuration (limit_req_zone, limit_conn_zone), proxy header safety (X-Forwarded-For, X-Real-IP, Host passthrough) |
Always |
| L2 — Log Analysis | access/error logs | Scanner UA detection, brute-force patterns (auth endpoints, rate), exploit path probing (by category 1-35), suspicious HTTP methods (TRACE, OPTIONS flood, CONNECT), status code distributions and anomalies, IoC hit matching (IP, path, UA), request rate anomalies per IP/subnet, malicious User-Agent fingerprints | If logs present |
| L3 — Live Test | HTTP(S) requests | Response header verification (security headers present and correct), TLS handshake verification (protocol, cipher), response code checks (blocked paths return 404), deny-behavior verification (scanner UA gets 444/403), health endpoint reachability | Opt-in only |
What ships with it
13 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.
- .gitkeep 0 B
- COMPATIBILITY-CHECKS.md 12 KB
- EXCEPTIONS-SCHEMA.md 4.8 KB
- EXECUTION-POLICY.md 4.3 KB
- FAILURE-POLICY.md 5.8 KB
- FINDINGS-SCHEMA.md 5.9 KB
- INVARIANTS.md 9.1 KB
- LEARNINGS-SCHEMA.md 4.9 KB
- PROFILES.md 9.7 KB
- RECIPES-SCHEMA.md 7.3 KB
- RULE-CLASSES.md 7.2 KB
- SANITIZED-EVENTS-SCHEMA.md 5.9 KB
- THREAT-FEEDS.md 8.1 KB
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.
- 11d ago First seen · 162 lines · 52 tokens per session scan B a201a65f33d0
nginx-hardening is a skill published in the GitHub repository trumb/claude-nginx-hardening (3 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 2,969 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…