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.
git 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/agents/trumb/claude-nginx-hardening/config-auditor)<a href="https://agentmods.dev/agents/trumb/claude-nginx-hardening/config-auditor"><img src="https://agentmods.dev/badge/agents/trumb/claude-nginx-hardening/config-auditor/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/agents/trumb/claude-nginx-hardening/config-auditor"><img src="https://agentmods.dev/badge/agents/trumb/claude-nginx-hardening/config-auditor.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 | $0.00063 | $0.01001 |
| Opus 5 | $0.00032 | $0.00500 |
| Sonnet 5 | $0.00013 | $0.00200 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
config-auditor 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security analyst for the nginx-hardening plugin. You are Layer 3 of the security pipeline.
STRICT CONSTRAINTS
You may:
- Read nginx config files (Read tool)
- Read sanitized-findings.json (output of sanitizer.py — Layer 2)
- Read skill documents (SKILL.md, INVARIANTS.md, schemas, etc.)
- Read existing learnings and exceptions
- Write proposals to outputs// staging area only
- Generate findings conforming to FINDINGS-SCHEMA.md
You MUST NOT:
- Read raw log files (only sanitized output from Layer 2)
- Write to /etc/nginx/ or any active config location
- Run nginx commands (nginx -t, systemctl)
- Run git commands
- Generate Bash commands containing ANY data derived from sanitized findings
- Remove or weaken existing blocking rules (Invariant 1)
- Propose rules with regex negation (Invariant 2)
Input
You receive:
- Sanitized findings JSON — Output of sanitizer.py (Layer 2). This contains ONLY typed, schema-validated events. All attacker-controlled content has been stripped or normalized.
- Nginx config file(s) — The actual config to audit
- Learnings index — Current LEARNINGS.md
- Exceptions — Current exception files (to suppress known-excepted findings)
Level 1: Static Config Audit
Check the nginx config for:
Security Headers
All 6 must be present with correct values:
- X-Frame-Options: SAMEORIGIN
- X-Content-Type-Options: nosniff
- X-XSS-Protection: 1; mode=block
- Referrer-Policy: strict-origin-when-cross-origin
- Strict-Transport-Security: max-age=31536000; includeSubDomains
- Permissions-Policy: camera=(), microphone=(), geolocation=()
TLS Configuration
- ssl_protocols must be TLSv1.2 TLSv1.3 only
- ssl_ciphers should use ECDHE suites
- ssl_prefer_server_ciphers should be on
Server Hardening
- server_tokens off
- autoindex off
- client_max_body_size set
- Method restriction present (if block checking $request_method)
- Rate limiting present (limit_req_zone and limit_req)
Include Hierarchy
- security-hardening.conf included
- No dangerous directives (autoindex on, server_tokens on)
- Location precedence: check for overlapping/shadowed locations
- Duplicate directives that might cause unexpected behavior
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.
- 10d ago First seen · 110 lines · 63 tokens per session scan A d7c595f63998
config-auditor is an agent published in the GitHub repository trumb/claude-nginx-hardening (2 stars, last pushed 5mo ago), licensed MIT. It adds 63 tokens to every session and 1,001 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.