cli-anything-web
CommandGenerate a complete agent-native CLI for any web app by recording and analyzing network traffic via playwright-cli. Runs the full…
Record network traffic from a web app without generating a CLI. Useful for initial exploration or adding more coverage data.
> /plugin marketplace add ItamarZand88/CLI-Anything-WEB> /plugin install cli-anything-web@cli-anything-web
name: cli-anything-web:record description: Record network traffic from a web app without generating a CLI. Useful for initial exploration or adding more coverage data. argument-hint: <url> [--duration <minutes>] [--mitmproxy] allowed-tools: Bash(*), Read, Write, mcp__chrome-devtools__*
Read the methodology overview: @${CLAUDE_PLUGIN_ROOT}/HARNESS.md
Target URL: $ARGUMENTS
!`npx @playwright/cli@latest --version 2>&1 && echo "PLAYWRIGHT_OK" || echo "PLAYWRIGHT_FAIL"`
**If PLAYWRIGHT_OK** -> use playwright-cli for recording.
**If PLAYWRIGHT_FAIL** -> If playwright-cli is not available, see HARNESS.md for the MCP fallback path.
Invoke the `capture` skill for Phase 1 traffic recording. The capture skill handles everything: site assessment, setup, trace, explore, parse.
**Difference from `/cli-anything-web`:** This command records traffic ONLY — it does not generate a CLI. Use this when you want to explore a site's API surface before committing to full CLI generation, or when adding coverage data to an existing capture.
Ask the user at each major section:
This gives the user control over what gets recorded.
Traffic is saved to `<app>/traffic-capture/raw-traffic.json`. To generate a CLI from this data later, run `/cli-anything-web <url>`.
Claude Code plugin that generates production-grade Python CLIs for any web app. 20 CLIs and counting.
Generate a complete agent-native CLI for any web app by recording and analyzing network traffic via playwright-cli. Runs the full…
List all available CLI-Anything-Web CLIs (installed and generated).
Refine an existing cli-anything-web CLI by recording additional traffic and expanding command coverage. Invokes the gap-analyzer…
Run tests for a cli-anything-web CLI and update TEST.md with results.
Validate a cli-anything-web CLI against the tiered quality checklist (Tier 1 critical / Tier 2 comprehensive). Reports…
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.