capture

capture is a skill for Claude Code, Codex from ItamarZand88/CLI-Anything-WEB. It costs 57 tokens per session (4,376 once invoked), scanned B, original, MIT.

A browser-based workflow for recording how a website works. It identifies the site’s technology, protections, login method, and API requests, then saves the observed web traffic.

In plain words
What is it for?
Exploring a target site, handling login, discovering its API surface, recording HTTP traffic, writing an assessment, and checking that the capture is complete.
Why use it?
It gives later development work a concrete map of the website’s requests and authentication behavior instead of relying on assumptions.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the cli-anything-web plugin — 6 skills, 6 commands, 4 agents, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/itamarzand88/cli-anything-web/capture
Any agent
npx skills add ItamarZand88/CLI-Anything-WEB --skill capture
Clone the repo
git clone --depth 1 https://github.com/ItamarZand88/CLI-Anything-WEB

Made for: Claude Code, Codex.

Or install cli-anything-web, the plugin that ships this one along with the rest of its 6 skills, 6 commands, 4 agents, 1 MCP server.

Wrote 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.

agentmods badge for capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/itamarzand88/cli-anything-web/capture.svg)](https://agentmods.dev/skills/itamarzand88/cli-anything-web/capture)
Your own site
<a href="https://agentmods.dev/skills/itamarzand88/cli-anything-web/capture"><img src="https://agentmods.dev/badge/skills/itamarzand88/cli-anything-web/capture.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,376 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.04376
Opus 5 $0.00028 $0.02188
Sonnet 5 $0.00011 $0.00875
Haiku 4.5 $0.00006 $0.00438

Measured 5d ago against content hash 553e2db917d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

capture scanned grade B with 2 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

3. Save auth state and tighten permissions (CLAUDE.md mandates `chmod 600`):

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. Probe the API endpoints directly with `httpx` or `curl`
cli-anything-web-plugin/skills/capture/SKILL.md · 411 lines

How it starts

The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Traffic Capture (Phase 1)

Assess the site, then capture comprehensive HTTP traffic. This skill combines site assessment with full traffic recording in a single browser session.

Copy this checklist and check off items as you complete them:

Phase 1 Progress:
- [ ] Prerequisites: playwright-cli available, checkpoint restored if one exists
- [ ] Step 1: Browser open on target URL
- [ ] Step 2: Fingerprint run + auth handled + profile classified + assessment.md written
- [ ] Step 3: Full capture — exploration targets met for the profile
- [ ] Step 4: Trace parsed, validate-capture.py PASSED (the gate)
- [ ] Step 5: Browser closed, checkpoint + phase-state marked complete

CRITICAL EXECUTION RULES

NEVER use run_in_background: true for ANY playwright-cli command. All playwright-cli commands must run in the foreground with appropriate timeouts. Background execution causes task ID tracking failures — the command completes before you can read the output. See references/playwright-cli-commands.md for the timeout table.

NEVER use eval for complex expressions. eval fails silently on ternaries, comma operators, and multi-branch logic with "not well-serializable" errors. Use run-code instead. See references/framework-detection.md for details.

ESM context — no require(). run-code uses ESM. Use await import('fs') instead of require('fs'). See references/playwright-cli-commands.md.


Prerequisites (Hard Gate)

Do NOT start unless:

  • playwright-cli is available (npx @playwright/cli@latest --version)
  • Target URL is known

Default capture method: playwright-cli tracing (standard workflow below).

Optional --mitmproxy mode

When the --mitmproxy flag was passed to /cli-anything-web (or the capture needs untruncated bodies / enhanced metadata), follow this workflow with the step substitutions in references/mitmproxy-mode.md — Steps 1, 3, and 4 differ; everything else is identical. When playwright-cli itself is unavailable (e.g., no Node), fall back to chrome-devtools-mcp via launch-chrome-debug.sh — see HARNESS.md Tool Hierarchy.

Read the full file on GitHub · 411 lines

Changes

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.

  1. 5d ago First seen · 411 lines · 57 tokens per session scan B 553e2db917d5

Subscribe to this mod's changes

capture is a skill published in the GitHub repository ItamarZand88/CLI-Anything-WEB (215 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 4,376 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

scrapling-official

Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…

D4Vinci/Scrapling · 80 tokens

playwright-test-generator

Use when someone wants to add, write, create, or scaffold new Playwright end-to-end tests for a page, flow, form, component, uncovered route, or first-project setup. The skill analyzes coverage gaps, explores live pages only on local/disposable or externally isolated approved non-production targets, proposes scenarios…

voidmatcha/e2e-skills · 140 tokens

playwright-test-generator

Use this skill to generate new Playwright end-to-end tests from scratch — for a page, a user flow, a form, or a component — taking them from zero to reviewed, passing specs. Reach for it whenever someone wants to add, write, create, or scaffold Playwright E2E coverage, fill coverage gaps for uncovered routes, or…

voidmatcha/e2e-skills · 202 tokens

qa-explore

Exploratory end-to-end QA with a team of agents that drive a real browser like human testers — they click through the whole app, create/fill/submit, screenshot and visually judge rendering + data correctness, capture trace/HAR/console/video evidence, adversarially verify each finding, learn from rejected findings, and…

victoraguilarsantamariadev/qa-explore · 158 tokens

agent-browser

Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape…

aegntic/compound-engineering · 77 tokens

ubrowser

Control a headless browser with 98% token reduction compared to Playwright MCP and Dev Browser. Uses batch execution, minimal responses, and efficient HTML formatting.

Lulzx/ubrowser · 0 tokens