barebrowse CLAUDE.md

barebrowse CLAUDE.md is an instructions file for coding agents from hamr0/barebrowse. It costs 534 tokens per session, scanned A, original, Apache-2.0.

Project-specific instructions for barebrowse, a JavaScript library that lets software agents browse web pages and returns a simplified accessibility-style page description.

In plain words
What is it for?
Use them when changing barebrowse to decide how to validate ideas, structure modules, choose dependencies, and follow its Node.js and JavaScript setup.
Why use it?
They keep development focused by requiring a small proof first, incremental work, few dependencies, and tests before shipping. They also set clear limits on tools, runtime, and code complexity.

Instructions file

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 instructions/hamr0/barebrowse/claude-md
Clone the repo
git clone --depth 1 https://github.com/hamr0/barebrowse

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 barebrowse CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hamr0/barebrowse/claude-md.svg)](https://agentmods.dev/instructions/hamr0/barebrowse/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hamr0/barebrowse/claude-md"><img src="https://agentmods.dev/badge/instructions/hamr0/barebrowse/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 534 This file is loaded in full into every session.
When invoked 534 The same file — it is already loaded in full.
Security scan A 0 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 $0.00534 $0.00534
Opus 5 $0.00267 $0.00267
Sonnet 5 $0.00107 $0.00107
Haiku 4.5 $0.00053 $0.00053

Measured 5d ago against content hash 98f3449c960c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

barebrowse 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 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.

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.

CLAUDE.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Rules

POC first. Always validate logic with a ~15min proof-of-concept before building. Cover happy path + common edges. POC works → design properly → build with tests. Never ship the POC.

Build incrementally. Break work into small independent modules. One piece at a time, each must work on its own before integrating.

Dependency hierarchy — follow strictly: vanilla language → standard library → external (only when stdlib can't do it in <100 lines). External deps must be maintained, lightweight, and widely adopted. Exception: always use vetted libraries for security-critical code (crypto, auth, sanitization).

Lightweight over complex. Fewer moving parts, fewer deps, less config. Simple > clever. Readable > elegant.

Open-source only. No vendor lock-in. Every line of code must have a purpose — no speculative code, no premature abstractions.

Project Specifics

  • What: Vanilla JS library — CDP-direct browsing for autonomous agents. URL in, pruned ARIA snapshot out.
  • Language: Vanilla JavaScript, ES modules, no runtime build step (JSDoc→.d.ts types generated at publish only)
  • Runtime: Node.js >= 22 (built-in node:sqlite for reading cookie DBs)
  • Protocol: CDP (Chrome DevTools Protocol) direct — no Playwright
  • Browser: Any installed Chromium-based browser (chromium, chrome, brave, edge)
  • Modules: ~16 files in src/. Two runtime deps: ws (CDP transport — Node's built-in WebSocket caps messages ~3MB and tears down the socket) and @mozilla/readability (readable() article extraction). Both vetted/lightweight per the dependency rule.
  • Tests: 160+ passing — run with node --test test/unit/*.test.js test/integration/*.test.js
  • Docs: docs/README.md (navigation guide to all documentation)

@.claude/remember/MEMORY.md

Standards guide (read when designing/building something new, not hot context): .claude/remember/AGENT_RULES.md

Read the full file on GitHub · 37 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 · 37 lines · 534 tokens per session scan A 98f3449c960c

Subscribe to this mod's changes

barebrowse CLAUDE.md is an instructions file published in the GitHub repository hamr0/barebrowse (45 stars, last pushed 4d ago), licensed Apache-2.0. It adds 534 tokens to every session, about $0.0027 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.