Skip to main content
affpapa.org
RU EN
skill CX Codex

crabtrap-llm-proxy — Claude Code skill: what it does, how to install

Guides setup of CrabTrap forward proxy to intercept agent HTTP requests, evaluating outbound traffic against static rules and an LLM judge before reaching remote APIs.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add reason-machines/trending-skills --skill crabtrap-llm-proxy -a claude-code
Open on GitHub

What crabtrap-llm-proxy does

CrabTrap runs as an outbound HTTP/HTTPS gateway on port 8080 between autonomous agents and outside web services. It first applies deterministic checks against target URLs using prefix, exact, or glob patterns. When no static rule matches, the request routes to a language model like gpt-4o for security evaluation. Blocked calls immediately return status 403.

Deployment requires Docker Compose with PostgreSQL 16 and CrabTrap images, along with an API key for OpenAI or Anthropic. Inspecting HTTPS traffic fails completely without the custom ca.crt authority file mounted or trusted by the client. An administrative control plane runs separately on port 8081 for user and rule management.

What it helps with

  • stop unauthorized SSRF requests to internal subnets
  • filter outbound API calls using path prefixes and wildcards
  • evaluate questionable request payloads with an LLM judge
  • record audit traces and proxy decisions inside PostgreSQL

Example prompts for the agent

  • Set up CrabTrap with docker compose and show how to create an agent proxy token.
  • Create a static rule in CrabTrap that blocks all DELETE calls to GitHub repositories.
  • Configure CrabTrap to evaluate outbound requests with an LLM security policy.

How to install crabtrap-llm-proxy

1Skills CLI (Vercel)

npx skills add reason-machines/trending-skills --skill crabtrap-llm-proxy -a claude-code

2Manually: put the files in place

~/.claude/skills/crabtrap-llm-proxy/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/crabtrap-llm-proxy/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about crabtrap-llm-proxy

How do I install crabtrap-llm-proxy in Claude Code?

Run npx skills add reason-machines/trending-skills --skill crabtrap-llm-proxy -a claude-code. The skill file installs to ~/.claude/skills/crabtrap-llm-proxy/SKILL.md.

What does crabtrap-llm-proxy do?

It configures a forward proxy that intercepts outbound HTTP traffic from AI agents. Requests face static URL checks and an LLM judge, and all verdicts go to a PostgreSQL audit log.

What dependencies are needed to run CrabTrap?

You need Docker Compose running CrabTrap and PostgreSQL 16, plus an API key for OpenAI or Anthropic. Intercepting HTTPS also requires trusting the generated ca.crt file.

Similar skills

All skills for Security →
git-guardrails-claude-code Matt Pocock This skill adds a Claude Code hook that stops risky Git commands before they run. Use it when an agent must not push or discard working-tree changes. 499,069installs ponytail-review DietrichGebert ponytail-review reviews a change beyond the diff, checking connected code, bugs, risks, load, tests, speed, and unnecessary code. Use it for PRs and commits. CX Codex +1 57,000installs ponytail-audit DietrichGebert It audits a repository and ranks bugs, risks, and redundant code in a one-shot report. Use it when you need a review without code changes. CX Codex +1 45,400installs security-audit cloudflare Reviews codebases and APIs for vulnerabilities using safe sandboxing. Fits pre-release security reviews, pen-test triage, and architecture checks. CX Codex +1 54,800installs security-and-hardening addyosmani Guides threat modeling and security checks for code that handles user input, authentication, sessions, or external services. Use it when building a feature that accepts untrusted data or reviewing code before release. CX Codex +1 70,200installs supabase official supabase Guides the agent through database configuration and strict RLS policies in Supabase. CX Codex GP ChatGPT 8installs

From the same set199

masterhttprelayvpn-proxy A skill that walks your agent through running a local HTTP/SOCKS5 proxy, with traffic tunnelled through Google Apps Script and dressed up as Google requests. CX Codex +1 365installs tilekernels-gpu-kernels This skill guides agents through TileKernels GPU kernels for MoE, quantization and other LLM operations. Use it when writing or checking TileLang code. CX Codex +1 363installs masterhttprelayvpn-rust Helps configure and run mhrv-rs, routing HTTP and SOCKS5 traffic through Google Apps Script with TLS SNI spoofing under www.google.com. CX Codex +1 361installs aris-autonomous-ml-research A Markdown skill that links ML idea discovery, experiments, paper writing, review, and rebuttal. It fits workflows where one model checks another. CX Codex +1 360installs freellmapi-proxy This skill sets up a self-hosted Anthropic-compatible proxy that puts free-tier keys from many providers behind one endpoint. CX Codex +1 351installs ppt-image-first-workflow Takes a vague deck request through style previews and a locked plan to a PPTX where every slide is one full-page image made with GPT Image 2. CX Codex +1 325installs pi-computer-use Controls macOS desktop applications through Accessibility API targets instead of raw coordinates. Useful for GUI automation workflows. CX Codex +1 315installs gpt-image-2-skill A skill and CLI for creating and editing images with OpenAI gpt-image-2. Use it for reference-based edits, masks, and batches of variants. CX Codex +1 315installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor