Borrowing it
Nothing to install: this file belongs to Topman-14/mobius-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/Topman-14/mobius-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/Topman-14/mobius-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/topman-14/mobius-mcp/claude-md)<a href="https://agentmods.dev/instructions/topman-14/mobius-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/topman-14/mobius-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/topman-14/mobius-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/topman-14/mobius-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03055 | $0.03055 |
| Opus 5.5 | $0.01222 | $0.01222 |
| Sonnet 5.5 | $0.00611 | $0.00611 |
| Haiku 4.5 | $0.00305 | $0.00305 |
Grade A, and why
mobius-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 2mo 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 — 111 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 (claude.ai/code) when working with code in this repository.
Commands
Setup
npm install
Root-only. This is an npm workspaces monorepo (apps/*, packages/*) — installing inside an individual workspace folder fights the root's symlinked node_modules and is never necessary.
Build
npm run build
Builds every workspace in dependency order: packages/capture-core → apps/mcp-server / apps/npm-client / apps/browser-extension. The apps consume packages/capture-core's built dist/ output, not its TypeScript source — after editing it, rebuild before an app will see the change (or use watch mode).
Build one workspace:
npm run build -w packages/capture-core
npm run build -w apps/mcp-server
Watch mode (active development)
npm run watch
Does a one-time build of packages/capture-core, then runs three labeled watchers in parallel: [packages] (tsc -b --watch), the extension's Vite dev server + esbuild watcher for the standalone content-script/injected bundles, and apps/mcp-server's tsup --watch. Load the extension once via chrome://extensions → Developer Mode → Load unpacked → apps/browser-extension/dist; background/popup/options changes hot-reload via crxjs, but content-script.ts/injected.ts changes only take effect the next time they're injected (reload the target tab or toggle capture off/on).
If only the shared packages need rebuilding (e.g. working on apps/npm-client or apps/mcp-server without the extension watchers):
npm run watch -w packages/capture-core
Run the MCP server from source
npm run start --workspace=apps/mcp-server
Test / lint
npm run test and npm run lint exist at the root (--workspaces --if-present) and run in CI, but no workspace currently defines a test or lint script — there is no test suite or lint config in this repo yet.
Architecture
One shared package implements one pipeline: a browser client captures runtime events and streams them over a local WebSocket to a Node server, which exposes them to AI agents as MCP tools over stdio.
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.
- 2mo ago First seen · 111 lines · 3,055 tokens per session scan A 19eeb6d50f16
mobius-mcp CLAUDE.md is an instructions file published in the GitHub repository Topman-14/mobius-mcp (19 stars, last pushed 2mo ago), licensed MIT. It adds 3,055 tokens to every session, about $0.0122 per session on Opus 5.5. 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.
mobius-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mobius-mcp CLAUDE.mdTopman-14/mobius-mcp | Instructions file | 19 | 2mo ago | MIT | A | 3,055 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |