Borrowing it
Nothing to install: this file belongs to longbiao7498/remote-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/longbiao7498/remote-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/longbiao7498/remote-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/longbiao7498/remote-mcp/claude-md)<a href="https://agentmods.dev/instructions/longbiao7498/remote-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/longbiao7498/remote-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 | $0.04135 | $0.04135 |
| Opus 5 | $0.02067 | $0.02067 |
| Sonnet 5 | $0.00827 | $0.00827 |
| Haiku 4.5 | $0.00413 | $0.00413 |
Grade C, and why
remote-mcp CLAUDE.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Panel metadata in `~/.local/share/remote-mcp/jobpane/<old_sid>/` from old sessions is not auto-cleaned. Manual `rm -rf` or future `JobsAdminCleanup` (not in v0.3.0). How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
中文版本：CLAUDE.zh.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
For user-facing documentation organized along the Diátaxis framework (tutorial / how-to / reference / explanation), see docs/. This file is specifically for Claude Code's perspective — it surfaces the load-bearing decisions and conventions that an agent modifying this codebase needs to know upfront.
Repository status
v0.3.0 implemented. Stages A–K complete. The authoritative designs are:
docs/superpowers/specs/2026-05-26-remote-mcp-design.md(v2, base)docs/superpowers/specs/2026-05-27-v0.2.0-non-persistent-bash.md(v0.2.0 increment)docs/superpowers/specs/2026-05-28-network-robustness-design.md(v0.2.2 increment)docs/superpowers/specs/2026-05-31-v0.3.0-job-panel.md(v0.3.0 increment — job panel)
New sessions: read the relevant spec end-to-end before proposing architecture changes. Many decisions have explicit rationales (snapshot mechanism, cwd policy, ~ two-layer semantics, unified suffix, SFTP-vs-exec split, local-first panel metadata, sid derivation, terminal-state observation skip, JobArchive-as-local-only) that shouldn't be re-litigated without checking with the user.
What's being built
remote-mcp is a local Python MCP server that exposes 17 tools to Claude Code. Thirteen operate on a remote Linux host over SSH; one (Feedback) writes to a local JSONL file; four (Jobs, JobKill, JobArchive, JobScript) manage the background task panel using local-first metadata. The seven with Claude Code native counterparts (Read/Write/Edit/MultiEdit/Bash/Glob/Grep) match their schemas and output formats. Hard constraints: remote host has SSH only (no agent install), transport is stdio MCP, SSH library is paramiko.
The authoritative designs are docs/superpowers/specs/2026-05-26-remote-mcp-design.md (v2, base) and the three incremental specs listed under Repository Status. The Chinese-language 软件设计文档.md at repo root is the prior v1 draft — kept for reference but superseded by v2.
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 · 168 lines · 4,135 tokens per session scan C dccd2e95529d
remote-mcp CLAUDE.md is an instructions file published in the GitHub repository longbiao7498/remote-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 4,135 tokens to every session, about $0.0207 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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.