What is mcp-clipstream CLAUDE.md?

Instructions for a tool that captures text, code, and commands from Claude Code sessions and shows them in a persistent terminal interface. A terminal interface is a text-based screen for viewing and interacting with programs.

Running the MCP server and its companion terminal app to capture clips and copy them to the system clipboard.

It keeps copied material in a scrollable buffer so useful session output can be collected and copied later.

How shamis6ali/mcp-clipstream configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shamis6ali/mcp-clipstream. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/shamis6ali/mcp-clipstream/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/shamis6ali/mcp-clipstream

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/shamis6ali/mcp-clipstream/claude-md/github.svg)](https://agentmods.dev/instructions/shamis6ali/mcp-clipstream/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/shamis6ali/mcp-clipstream/claude-md"><img src="https://agentmods.dev/badge/instructions/shamis6ali/mcp-clipstream/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/shamis6ali/mcp-clipstream/claude-md"><img src="https://agentmods.dev/badge/instructions/shamis6ali/mcp-clipstream/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 868 This file is loaded in full into every session.

When invoked 868 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00868	$0.00868
Opus 5	$0.00434	$0.00434
Sonnet 5	$0.00174	$0.00174
Haiku 4.5	$0.00087	$0.00087

Measured 8d ago against content hash 8b547cdc1516, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-clipstream 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 8d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-clipstream

MCP server + persistent TUI for clean clipboard capture from Claude Code sessions.

Architecture

Two processes:

MCP server (mcp-clipstream) — STDIO MCP server spawned by Claude Code. Exposes clip, clip_code, clip_cmd tools. Writes clip payloads as JSON over a Unix domain socket.
TUI (clipstream) — persistent Textual app. Listens on the Unix domain socket, buffers clips, displays a scrollable list, copies to the system clipboard on Enter.

Key files

src/mcp_clipstream/server.py — MCP server entry point (FastMCP app)
src/mcp_clipstream/tools.py — tool definitions (clip_tool)
src/mcp_clipstream/socket_writer.py — async UDS client with local spool fallback
src/mcp_clipstream/protocol.py — JSON wire protocol (ClipMessage, HeartbeatMessage, ClearMessage)
src/mcp_clipstream/config.py — ServerConfig.from_env()
src/clipstream/tui.py — Textual app (ClipstreamApp)
src/clipstream/socket_listener.py — async UDS server
src/clipstream/buffer.py — ClipBuffer (ring buffer, newest-first)
src/clipstream/clipboard.py — pbcopy / xclip / wl-copy subprocess wrapper

Conventions

Python 3.11+
Async throughout (asyncio)
Type hints on all public APIs
Ruff for lint + format
pytest + pytest-asyncio
No database — in-memory buffer; optional JSONL persistence lands in v0.3.0
Unix domain socket at /tmp/clipstream.sock (overridable via CLIPSTREAM_SOCKET)

Build order (v0.1.0 — done)

protocol.py
socket_listener.py
buffer.py
tui.py (scaffold with ListView)
clipboard.py (pbcopy only)
socket_writer.py
server.py + tools.py (single clip tool)
Entry points in pyproject.toml
Integration test
README

Next up (v0.2.0)

Add clip_code and clip_cmd tools in tools.py and expose them as separate @app.tool()s in server.py.
Render code clips with Rich syntax highlighting (rich.syntax.Syntax) inside the ClipItem preview.
/ keybinding opens a search bar; filter the ListView using ClipBuffer.search() (replace substring match with token + Levenshtein).
Session filter: s cycles through {all, current, per-session}.

Read the full file on GitHub · 66 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.

8d ago First seen · 66 lines · 868 tokens per session scan A 8b547cdc1516

Subscribe to this mod's changes

mcp-clipstream CLAUDE.md is an instructions file published in the GitHub repository shamis6ali/mcp-clipstream (1 stars, last pushed 4mo ago), licensed MIT. It adds 868 tokens to every session, about $0.0043 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.

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

mcp-clipstream: Instructions file for Claude Code