Borrowing it
Nothing to install: this file belongs to simplicianokelly52/comet_mcp. 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/simplicianokelly52/comet_mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/simplicianokelly52/comet_mcpWrote 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/simplicianokelly52/comet_mcp/claude-md)<a href="https://agentmods.dev/instructions/simplicianokelly52/comet_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/simplicianokelly52/comet_mcp/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 | $0.00962 | $0.00962 |
| Opus 5 | $0.00481 | $0.00481 |
| Sonnet 5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
comet_mcp 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
What This Is
MCP server connecting Claude Code to Perplexity's Comet browser via Chrome DevTools Protocol (CDP).
v3.0.0: Now uses a DEDICATED MCP Comet instance (port 9223) - your personal browser tabs are never touched.
Architecture
Claude Code → MCP Server (index.ts) → CometAI (comet-ai.ts) → CDP Client (cdp-client.ts) → MCP Comet Browser
↓
Port 9223 (isolated)
Data: ~/.comet-mcp
8 Tools
comet_connect- Start/connect to MCP-dedicated Comet (separate from personal browser)comet_ask- Send prompt, wait for response (15s default, use poll for longer)comet_poll- Check status of long-running taskscomet_stop- Stop current taskcomet_screenshot- Capture current pagecomet_mode- Switch Perplexity modes (search/research/labs)comet_folders- Manage research spaces (list/create/save)comet_library- Search existing research in Perplexity library
Key Implementation Details
Isolated MCP Instance (NEW in v3.0):
- Uses port 9223 (not 9222) to avoid conflicts with personal Comet
- Separate data directory:
~/.comet-mcp(macOS/Linux) or%LOCALAPPDATA%\comet-mcp(Windows) - macOS: Requires separate app bundle at
~/.comet-mcp/Comet-MCP.app(see README setup instructions) - Visual indicator: "[MCP]" in title + badge on page
- First launch prompts for Perplexity login
Response extraction (comet-ai.ts:getAgentStatus):
- Collects ALL prose elements (not just last) - fixes text truncation
- Scrolls to load lazy content before extraction
- 50KB response limit (up from 8KB)
- Filters UI text (Library, Discover, etc.) and questions
Follow-up detection (index.ts):
- Captures old prose count/text before sending
- Waits for NEW response (different text or more elements)
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 · 102 lines · 962 tokens per session scan A 2ce7dcf5e7f9
comet_mcp CLAUDE.md is an instructions file published in the GitHub repository simplicianokelly52/comet_mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 962 tokens to every session, about $0.0048 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
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.
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).
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).
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.
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.