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/szymdzum/browser-debugger-cli/claude-mdgit clone --depth 1 https://github.com/szymdzum/browser-debugger-cliWhat 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 | $0.01817 | $0.01817 |
| Opus 5 | $0.00908 | $0.00908 |
| Sonnet 5 | $0.00363 | $0.00363 |
| Haiku 4.5 | $0.00182 | $0.00182 |
Grade A, and why
browser-debugger-cli CLAUDE.md scanned grade A with 0 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 3d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 252 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 when working with this repository.
Agent-Friendly Discovery (START HERE)
bdg is self-documenting - use these FIRST:
bdg --help --json # All commands, flags, exit codes
bdg cdp --list # 53 CDP domains
bdg cdp Network --list # Methods in a domain
bdg cdp Network.getCookies --describe # Full method schema
bdg cdp --search cookie # Search methods
Key Principle: Discover capabilities programmatically before implementation.
Essential Patterns
CommandRunner (src/commands/shared/CommandRunner.ts)
All commands use this wrapper for consistent error handling and JSON/human output:
await runCommand(
async () => {
const response = await ipcFunction(params);
return response.status === 'error'
? { success: false, error: response.error }
: { success: true, data: response.data };
},
options,
formatFunction
);
Error Handling
Convention: process.exit and console.error belong at entrypoints only (src/index.ts, CommandRunner, signal handlers, daemon/worker bootstrap). Below that layer, choose one of two structured styles:
- Throw
CommandError— from deep helpers when the caller can't reasonably recover.CommandRunnercatches and formats. - Return
{ success, error?, exitCode?, errorContext? }— from composable operations whose callers branch on failure (e.g., CLI command action handlers,FetchResult).
Never mix: a helper shouldn't log-and-exit when its surrounding function already returns a structured shape.
import { CommandError } from '@/ui/errors/index.js';
import { EXIT_CODES } from '@/utils/exitCodes.js';
throw new CommandError(
'Session not found',
{ suggestion: 'Start a session with: bdg <url>' },
EXIT_CODES.RESOURCE_NOT_FOUND
);
Message Centralization (src/ui/messages/)
All user-facing strings must use centralized functions - no inline strings.
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.
- 3d ago First seen · 252 lines · 1,817 tokens per session scan A aaf47c3a3164
browser-debugger-cli CLAUDE.md is an instructions file published in the GitHub repository szymdzum/browser-debugger-cli (149 stars, last pushed 2mo ago), licensed MIT. It adds 1,817 tokens to every session, about $0.0091 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
cdpilot CLAUDE.md
Instructions for mehmetnadir/cdpilot, covering cdpilot, kimlik, hızlı başlangıç, dosya haritası and dikkat edilecekler.
native-devtools-mcp AGENTS.md
AGENTS.md instructions for vectora-foundry/native-devtools-mcp, covering agent context: native-devtools-mcp, 🧠 core reasoning loop, 🗺️ capabilities matrix (strategy guide), 🛠️ tool definitions & schemas and 1. vision & perception (the "eyes").
chatgpt-web-handoff CLAUDE.md
Instructions for sologuy/chatgpt-web-handoff, covering claude.md —— claude code 专用补充, 浏览器通道, 上下文纪律, 这个 chrome 是用户日常在用的 and skill 真相源在仓库.
chrome-cdp-ex CLAUDE.md
Instructions for EndeavorYen/chrome-cdp-ex, covering claude.md — chrome-cdp-ex, problem-solving principles, project overview, architecture and coding conventions.
empir3-bridge CLAUDE.md
Instructions for empir3hq/empir3-bridge, covering empir3 bridge — agent & contributor guide, what lives here, before you edit, run locally and release / publish.
browser-use CLAUDE.md
Claude Code instructions for browser-use/browser-use, covering claude.md, high-level architecture, core components, event-driven browser management and cdp integration.