Skip to main content
skill CX Codex

http-toolkit-intercept — Claude Code skill

http-toolkit-intercept captures HTTP requests and responses from any script or service — including LLM API calls, backend requests, and auth flows. Use it when you need to see what's actually sent over the wire and what comes back.

no license 124 installs ★ 129 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Factory-AI/factory-plugins --skill http-toolkit-intercept -a claude-code
Open on GitHub

What http-toolkit-intercept does

This skill integrates HTTP Toolkit into a running process to inspect all network traffic. It works with Node.js, Python, Go, Java, Ruby, .NET, Rust, curl, and other runtimes that respect proxy environment variables. The typical workflow is: start HTTP Toolkit, run your program through the proxy at http://127.0.0.1:8000 with HTTP_PROXY, HTTPS_PROXY, and NO_PROXY set, capture the program's structured logs (if it supports --output-format json or similar), export the HTTP session from Toolkit, and cross-reference the two.

On Linux headless systems, use xvfb-run --auto-servernum httptoolkit --no-sandbox to avoid X11 sandbox errors. Each runtime has its own proxy quirks: Bun ignores standard env vars and requires BUN_CONFIG_PROXY; Java needs JVM flags -Dhttp.proxyHost and -Dhttp.proxyPort at startup. TLS verification is on by default — disable it with NODE_TLS_REJECT_UNAUTHORIZED=0 or runtime-specific equivalents only for local debugging when the HTTP Toolkit CA is not in your system trust store.

What it helps with

  • inspect API calls to LLM services during integration development
  • trace request payloads and headers in complex network flows
  • debug authentication failures and auth header issues
  • verify what data leaves your application before production deployment
  • gather evidence of HTTP client behavior across different runtimes

Example prompts for the agent

  • Capture HTTP requests from a Python script calling Claude API and examine headers and body content
  • Run a Node.js app through HTTP Toolkit proxy and export logs in JSON to verify what data goes to your backend
  • Debug a Go service by routing traffic through the proxy and matching outbound requests to application logs

How to install http-toolkit-intercept

1Skills CLI (Vercel)

npx skills add Factory-AI/factory-plugins --skill http-toolkit-intercept -a claude-code

2Manually: put the files in place

~/.claude/skills/http-toolkit-intercept/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/http-toolkit-intercept/

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

Questions about http-toolkit-intercept

How do I install http-toolkit-intercept for Claude Code?

Run npx skills add Factory-AI/factory-plugins --skill http-toolkit-intercept -a claude-code, then open ~/.claude/skills/http-toolkit-intercept/SKILL.md to get started. The skill requires HTTP Toolkit installed and access to ports 45456 and 45457.

What does http-toolkit-intercept do?

It wires HTTP Toolkit into your running processes to capture and inspect all HTTP traffic—requests, responses, headers, body content, auth tokens, and retry timing. All this happens on your development machine without modifying your code.

Which runtimes are supported?

Node.js, Bun, Deno, Python, Go, Ruby, Java/JVM, .NET, PHP, Rust, shell, and curl. Each honors different proxy environment variables: most respond to HTTP_PROXY and HTTPS_PROXY, but Bun requires BUN_CONFIG_PROXY and Java requires JVM flags like -Dhttp.proxyHost=127.0.0.1 -Dhttp.proxyPort=8000.

Similar skills

All skills for Backend and APIs →

From the same set17

The whole set →
skill-creation skill-creation converts past session breakthroughs into reusable agent skills inside SKILL.md files. Helps extract repeatable patterns and refine existing instructions. CX Codex +1 142installs autoresearch The autoresearch skill runs repeated code experiments against a measurable target. Use it for tuning tests, builds, bundle size, or ML training results. CX Codex +1 137installs vulnerability-validation vulnerability-validation is a Claude Code skill that tests whether security scan findings can be exploited and filters false alarms. It runs after commit-security-scan, before findings become issues or block a PR. CX Codex +1 135installs commit-security-scan The commit-security-scan skill reviews Git changes for security flaws using threat-model context. Use it for pull requests, staged files, or branch diffs. CX Codex +1 126installs browser-navigation browser-navigation automates browser tasks: page navigation, form filling, screenshots, data extraction, and session recording. CX Codex +1 120installs droid-control droid-control is a skill for automating terminal TUIs, browsers, and desktop apps. Record demos, run tests in real environments, and capture QA proof. CX Codex +1 118installs follow-up-on-pr follow-up-on-pr takes an open pull request, rebases on the target branch, resolves reviewer comments, runs local verification, and pushes updates. CX Codex +1 117installs create-pr create-pr — a skill that creates a pull request with a Conventional Commits title, templated body, and local verification before submission. CX Codex +1 115installs

Project sponsors

Companies that keep this analytics open