Borrowing it
Nothing to install: this file belongs to glatinone/BraveMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/glatinone/BraveMCP/master/CLAUDE.mdgit clone --depth 1 https://github.com/glatinone/BraveMCPWrote 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/glatinone/bravemcp/claude-md)<a href="https://agentmods.dev/instructions/glatinone/bravemcp/claude-md"><img src="https://agentmods.dev/badge/instructions/glatinone/bravemcp/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 | $0.00572 | $0.00572 |
| Opus 5 | $0.00286 | $0.00286 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
BraveMCP 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 7d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — BraveMCP Orchestration Instructions
Project Overview
BraveMCP is a local-first browser memory system that captures browsing history, bookmarks, text highlights, and manual notes, storing them in SQLite/ChromaDB. It exposes this database as a searchable "second brain" to Claude Desktop via the Model Context Protocol (MCP).
Build & Run Commands
MCP Server (/mcp-server)
- Install dependencies:
npm install - Run development server (live TS execution):
npm run dev - Type-check:
npm run typecheck - Lint:
npm run lint - Build TypeScript files:
npm run build - Start built server:
npm run start
Claude Desktop Integration
To connect this local MCP server to Claude Desktop, add the following configuration to your claude_desktop_config.json (typically located at %APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"brave-memory": {
"command": "node",
"args": [
"/absolute/path/to/BraveMCP/mcp-server/dist/index.js"
]
}
}
}
⚠️ Critical Architecture Note: Page Capture Flow
The capture_current_page MCP tool cannot trigger browser actions directly (because MCP runs over stdio in Claude Desktop, whereas the extension runs in the browser sandbox and can only make outbound POST requests to the HTTP bridge).
This is handled by design using the following flow:
- User Action: User clicks "Capture Content" in the extension popup. This triggers
content.jsto extract text from the DOM, which is thenPOSTed to/api/captureand saved to SQLite (along with AI-generated summaries and embeddings). - Claude Lookup: When Claude calls
capture_current_page()(without arguments), the MCP server checks SQLite for any previously captured page matching the current active tab's URL and returns it. - Claude Save: If Claude calls
capture_current_page(url, title, content, summary)with arguments, the MCP server saves it directly to the database.
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.
- 7d ago First seen · 56 lines · 572 tokens per session scan A 9ef64cfbccba
BraveMCP CLAUDE.md is an instructions file published in the GitHub repository glatinone/BraveMCP (1 stars, last pushed yesterday), licensed MIT. It adds 572 tokens to every session, about $0.0029 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.