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.
npx agentmods add instructions/itamarzand88/cli-anything-web/claude-mdgit clone --depth 1 https://github.com/ItamarZand88/CLI-Anything-WEBWrote 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/instructions/itamarzand88/cli-anything-web/claude-md)<a href="https://agentmods.dev/instructions/itamarzand88/cli-anything-web/claude-md"><img src="https://agentmods.dev/badge/instructions/itamarzand88/cli-anything-web/claude-md.svg" alt="Measured on agentmods" 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 | $0.03270 | $0.03270 |
| Opus 5 | $0.01635 | $0.01635 |
| Sonnet 5 | $0.00654 | $0.00654 |
| Haiku 4.5 | $0.00327 | $0.00327 |
Grade B, and why
CLI-Anything-WEB CLAUDE.md scanned grade B with 1 finding 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 6d 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.
- **Auth**: Credentials in `auth.json` with `chmod 600`, never hardcoded. Env var `CLI_WEB_<APP>_AUTH_JSON` for CI/CD. How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
CLI-Anything-Web is a Claude Code plugin that generates production-grade Python CLIs for any web application by capturing live HTTP traffic. Point at a URL → capture API traffic via playwright-cli → analyze endpoints → generate a complete CLI with auth, REPL mode, --json output, and tests.
Plugin Structure
cli-anything-web-plugin/ # The plugin itself
├── .claude-plugin/plugin.json # Plugin manifest
├── HARNESS.md # Core methodology SOP (read this first)
├── commands/ # Slash commands (/cli-anything-web, /record, /refine, etc.)
├── skills/ # 4-phase skill system (capture → methodology → testing → standards)
├── scripts/ # parse-trace.py, mitmproxy-capture.py, analyze-traffic.py (v1.3.0), site-fingerprint.js, capture-checkpoint.py, phase-state.py, repl_skin.py
│ # Pipeline automation: scaffold-cli.py, validate-checklist.py, generate-test-docs.py, smoke-test.py
└── templates/ # .tpl files used by scaffold-cli.py (exceptions, client, auth, CLI entry, setup, RPC, etc.)
Generated CLIs live in their own directories (e.g., futbin/agent-harness/) with namespace packages under cli_web/.
Pipeline Phases
The skill sequence is strictly ordered: capture → methodology → testing → standards → DONE
| Phase | Skill | What it does |
|---|---|---|
| 1 | capture | Site assessment + browser traffic recording (or public API shortcut) |
| 2 | methodology | Analyze traffic, design CLI architecture, implement code |
| 3 | testing | Write unit + E2E + subprocess tests |
| 4 | standards | Implementation review (3 agents), two-tier quality checklist, publish, smoke test, generate skill |
Site Profiles
Not all sites need the same pipeline path. Identify the profile early:
- Auth + CRUD (full pipeline): Google apps, Monday.com, Notion, Jira
- Auth + read-only: Dashboards, analytics viewers
- No-auth + CRUD: Sites with optional API key auth (Dev.to)
- No-auth + read-only: Hacker News, Wikipedia, npm — skip auth.py, skip write tests
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.
- 6d ago First seen · 172 lines · 3,270 tokens per session scan B 630a2c1bd985
CLI-Anything-WEB CLAUDE.md is an instructions file published in the GitHub repository ItamarZand88/CLI-Anything-WEB (215 stars, last pushed 4d ago), licensed MIT. It adds 3,270 tokens to every session, about $0.0163 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
e2e-skills AGENTS.md
AGENTS.md instructions for voidmatcha/e2e-skills, covering agents.md, repository overview, verification gate (must pass before commit), directory layout and conventions.
humanized-social-publisher AGENTS.md
AGENTS.md instructions for lincwang123-bot/humanized-social-publisher: This repository is designed to be configured with an AI coding agent.
python-lsp CLAUDE.md
Instructions for zircote/python-lsp, covering claude.md, project overview, setup, key files and hook system.
quarry python.instructions.md
Instructions for punt-labs/quarry, covering python review rules, construction, encapsulation, types and error handling.
quantcoder-plugin AGENTS.md
AGENTS.md instructions for nutdnuy/quantcoder-plugin, covering agent instructions - quantcoder plugin, goal, plugin surfaces, development and safety.
quantcoder-plugin CLAUDE.md
Claude Code instructions for nutdnuy/quantcoder-plugin: Follow AGENTS.md. This repo is a Claude Code plugin and Codex plugin wrapper around QuantCoder.