agentmods.dev

ClipBrain CLAUDE.md

ClipBrain CLAUDE.md is an instructions file for coding agents from agentpilled/ClipBrain. It costs 2,475 tokens per session, scanned A, original, MIT.

Project instructions for ClipBrain, a Chrome extension and local web server that save webpage content, YouTube transcripts, and Kindle highlights to a personal knowledge base.

In plain words
What is it for?
Use them when changing the browser extension, the local server, content extraction, or the command-line tool that stores captured information.
Why use it?
They give an agent the project’s architecture and rules, reducing the risk of editing the wrong component or misunderstanding how captured content flows through the system.

Instructions file

24 2mo ago A scan 2,475 tokens original MIT
View the source file agentpilled/ClipBrain
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/agentpilled/clipbrain/claude-md
Clone the repo
git clone --depth 1 https://github.com/agentpilled/ClipBrain
Per session 2,475 This file is loaded in full into every session.
When invoked 2,475 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 $0.02475 $0.02475
Opus 5 $0.01238 $0.01238
Sonnet 5 $0.00495 $0.00495
Haiku 4.5 $0.00248 $0.00248

Measured 3d ago against content hash b07f49ca72cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ClipBrain 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.

CLAUDE.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClipBrain — Chrome Extension + HTTP Server

What it does

A Chrome extension (Manifest V3) that captures web page content and sends it to a local HTTP server, which stores it in a ClipBrain knowledge base via the gbrain CLI.

This project uses the installed gbrain CLI. ./setup.sh installs it globally with Bun if it is missing.

Architecture

Chrome Extension

MV3 service workers do NOT have DOM access, so the work is split:

  • content-script.js — Injected into the active tab on demand. Has DOM access. On YouTube video pages, extracts the video ID, title, channel name, and transcript (from the page's inline captionTracks data, fetched same-origin so YouTube cookies are included). Falls back to reading the transcript panel DOM if the script extraction fails. Sends a youtube-capture message with the transcript segments already extracted. On all other pages, runs Mozilla's Readability.js to extract the article text. Sends the extracted data back to the service worker via chrome.runtime.sendMessage.
  • kindle-content-script.js — Auto-injected on read.amazon.com/notebook*. Parses Kindle highlights/notes from the Notebook page and sends them to the service worker as kindle-import messages. Shows a floating "Import to ClipBrain" button in the bottom-right corner.
  • gmail-content-script.js — Injected into Gmail after the user grants the optional mail.google.com permission from the popup. Detects open emails, extracts subject, sender, date, and clean body text (stripping Gmail UI chrome, signatures, tracking pixels). Shows a floating "Clip to ClipBrain" button when an email is open. Supports both button click and Cmd+Shift+S. Sends gmail-capture messages to the service worker. Handles threaded conversations (joins all messages). Uses gmail:// URL scheme for dedup. Slugs stored as email/{from-slug}/{subject-slug}.
  • service-worker.js — Background service worker. Listens for the capture-page keyboard command, injects the content script, receives extracted content (types captured, kindle-import, and youtube-capture), and POSTs it to the local HTTP server. YouTube captures go to /api/capture-youtube. Manages an offline queue in chrome.storage.local and flushes it via chrome.alarms.
  • toast.js — Injected into the page to show a brief success/failure notification.
  • lib/readability.js — Vendored copy of Mozilla Readability.js (from @mozilla/readability npm package).

Read the full file on GitHub · 167 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. 3d ago First seen · 167 lines · 2,475 tokens per session scan A b07f49ca72cd

Subscribe to this mod's changes

ClipBrain CLAUDE.md is an instructions file published in the GitHub repository agentpilled/ClipBrain (24 stars, last pushed 2mo ago), licensed MIT. It adds 2,475 tokens to every session, about $0.0124 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.

Browser automationMemory and context
Related

Other instructions, from other repositories

Browser4 CLAUDE.md

Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.

platonai/Browser4 · 1,205 tokens

agentic-playwright selectors.instructions.md

Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.

idavidov13/agentic-playwright · 2,174 tokens

scrapai-cli CLAUDE.md

Instructions for discourselab/scrapai-cli, covering claude.md, 1. who you are, 2. hard rules, 3. tools and 4. before you start: confirm the project.

discourselab/scrapai-cli · 8,964 tokens

chromeboost CLAUDE.md

Instructions for lordamdal/chromeboost, covering chromeboost — repo-developer guide, what chromeboost is, repository layout, development commands and tests/antibot/ (run locally; not in ci).

lordamdal/chromeboost · 3,633 tokens

skills CLAUDE.md

Instructions for aemcoder/skills, covering claude.md, repository structure, slicc browser automation conventions, stateless tab targeting (since slicc pr #188) and tab-new returns a targetid.

aemcoder/skills · 1,546 tokens

xgrower-extension CLAUDE.md

Instructions for JoyyyceD/xgrower-extension, covering x grower extension — architecture notes, architecture, key files, auth flow and quota system.

JoyyyceD/xgrower-extension · 900 tokens