Borrowing it
Nothing to install: this file belongs to JasonLinjc/mcp-ssh-remote. 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/JasonLinjc/mcp-ssh-remote/main/CLAUDE.mdgit clone --depth 1 https://github.com/JasonLinjc/mcp-ssh-remoteWrote 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/jasonlinjc/mcp-ssh-remote/claude-md)<a href="https://agentmods.dev/instructions/jasonlinjc/mcp-ssh-remote/claude-md"><img src="https://agentmods.dev/badge/instructions/jasonlinjc/mcp-ssh-remote/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 | $0.01025 | $0.01025 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
mcp-ssh-remote CLAUDE.md scanned grade A 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **`ssh(remoteCmd, timeout)`** is the core transport. Wraps the command in `bash -l -c <quoted>` (login shell so conda/Slurm/modules load), runs `spawnSync('ssh', [...sshArgs(), wrappedCmd])`, returns `{stdout, stderr, How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repo.
Project overview
MCP server that wraps the system ssh binary (not a Node ssh2 implementation) so it inherits everything ~/.ssh/config supports: ProxyCommand, ProxyJump, magic-user bastions, identity files, etc. Single file: index.js. No build step, no dependencies beyond Node stdlib.
Running
# Direct
node index.js --host <hostname>
# Smoke test: pipe JSON-RPC to stdin, watch stdout
printf '%s\n%s\n%s\n' \
'{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"t","version":"1"}}}' \
'{"jsonrpc":"2.0","method":"notifications/initialized","params":{}}' \
'{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"execute_command","arguments":{"command":"hostname"}}}' \
| node index.js --host <hostname>
<hostname> must resolve via ssh <hostname> from the user's shell.
Architecture
JSON-RPC stdio server. Lines in → dispatch → lines out.
dispatch(msg)(bottom of file) routesinitialize,tools/list,tools/call.tools/call→handleToolCall(name, args).handleToolCallis the bigifchain — one branch per tool.ssh(remoteCmd, timeout)is the core transport. Wraps the command inbash -l -c <quoted>(login shell so conda/Slurm/modules load), runsspawnSync('ssh', [...sshArgs(), wrappedCmd]), returns{stdout, stderr, status, error}. One retry onETIMEDOUT.sshWithStdin(remoteCmd, stdinData, timeout)— same, but pipes large input via stdin to avoidARG_MAX. Used forwrite_file,edit_file.sshArgs()returns the ssh CLI args. Branches onNO_MULTIPLEX.
SSH multiplexing (important)
Multiplexing is off by default — NO_MULTIPLEX = process.env.MCP_SSH_MULTIPLEX !== '1'. Many jump hosts permit only one session per TCP connection (e.g. magic-user auto-forward bastions where the username encodes the target: user/target_ip/target_user). With multiplexing on, call #1 works, call #2+ hit Session open refused by peer, ssh client falls back to fresh connection per call, stderr noise leaks into every response, and under load the fresh connections flake.
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 · 68 lines · 1,025 tokens per session scan A 8683a86b3966
mcp-ssh-remote CLAUDE.md is an instructions file published in the GitHub repository JasonLinjc/mcp-ssh-remote (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,025 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.