Borrowing it
Nothing to install: this file belongs to cmeans/mcp-clipboard. 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/cmeans/mcp-clipboard/main/CLAUDE.mdgit clone --depth 1 https://github.com/cmeans/mcp-clipboardWrote 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/cmeans/mcp-clipboard/claude-md)<a href="https://agentmods.dev/instructions/cmeans/mcp-clipboard/claude-md"><img src="https://agentmods.dev/badge/instructions/cmeans/mcp-clipboard/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/cmeans/mcp-clipboard/claude-md"><img src="https://agentmods.dev/badge/instructions/cmeans/mcp-clipboard/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 | $0.01875 | $0.01875 |
| Opus 5 | $0.00937 | $0.00937 |
| Sonnet 5 | $0.00375 | $0.00375 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
mcp-clipboard 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 9d 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
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
mcp-clipboard is an MCP (Model Context Protocol) server that reads and writes the system clipboard — tables, plain text, code, JSON, URLs, images, and more. Preserves structure when possible (e.g. spreadsheet row/column layout from HTML) and returns non-tabular content with smart formatting. Images on the clipboard are returned as viewable content; audio and video are detected and reported but not returned.
Commands
# Install dependencies
uv sync
# Run all tests (mocked, no clipboard needed)
uv run pytest
# Run a single test file
uv run pytest tests/test_parser.py
# Run a single test function
uv run pytest tests/test_parser.py::test_parse_google_sheets_html
# Run integration tests (requires real clipboard daemon)
uv run pytest -m integration
# Run the MCP server (stdio mode)
uv run mcp-clipboard
# Run with debug logging
uv run mcp-clipboard --debug
# or: MCP_CLIPBOARD_DEBUG=1 uv run mcp-clipboard
# Test interactively with MCP Inspector
uv run mcp dev src/mcp_clipboard/server.py
# Build wheel (to verify packaging)
uv build --wheel
# Publish to PyPI (do NOT publish directly — push a tag to trigger GitHub Actions)
git tag v0.1.x && git push origin v0.1.x # triggers .github/workflows/publish.yml
git tag test-v0.1.x && git push origin test-v0.1.x # triggers test-publish.yml (TestPyPI)
Architecture
Three-layer design with clean separation:
- server.py — MCP server (
FastMCP, namemcp_clipboard) exposing 7 tools:clipboard_paste(output_format, include_schema, selection)— Primary tool. Handles any clipboard content: tables → markdown/json/csv; non-tabular → smart formatting (JSON, code, URL, text). Images are returned as base64-encoded image content. Audio/video are detected and reported.selectiondefaults to"clipboard"; pass"primary"on X11/Wayland to read the middle-click/select-text-to-paste buffer.clipboard_copy(content)— Writes text to the system clipboard.clipboard_copy_markdown(text)— Renders markdown to HTML and places both formats on the clipboard so paste targets pick the right one. macOS/Windows write both atomically via multi-format clipboard APIs; Wayland/X11 are single-MIME and write onlytext/html.clipboard_copy_image(image_data, mime_type)— Writes a PNG or JPEG image to the system clipboard from base64-encoded bytes. Pass-through, no re-encoding. Magic bytes are validated against the declared MIME.clipboard_read_raw(mime_type, selection)— Returns raw clipboard content for a given MIME type (truncated at 50KB). Rejects binary MIME types. Acceptsselection="primary"on X11/Wayland.clipboard_list_formats(selection)— Lists available MIME types on clipboard. Acceptsselection="primary"on X11/Wayland.clipboard_version()— Returns the running mcp-clipboard package version as{"name": "mcp-clipboard", "version": "<x.y.z>"}. Diagnostic surface for hosts that don't expose the standard MCPserverInfoblock to the model, and for test harnesses that need to record which build served a given run.
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.
- 9d ago First seen · 102 lines · 1,875 tokens per session scan A 8bad6ed5a2e1
mcp-clipboard CLAUDE.md is an instructions file published in the GitHub repository cmeans/mcp-clipboard (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,875 tokens to every session, about $0.0094 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.