Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/yawlabs/ssh-mcp/claude-mdgit clone --depth 1 https://github.com/YawLabs/ssh-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/yawlabs/ssh-mcp/claude-md)<a href="https://agentmods.dev/instructions/yawlabs/ssh-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yawlabs/ssh-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 | $0.01789 | $0.01789 |
| Opus 5 | $0.00894 | $0.00894 |
| Sonnet 5 | $0.00358 | $0.00358 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade C, and why
ssh-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 yesterday.
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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- Skip condition 1 — NOT a key file (`looksLikePrivateKey`, ssh.ts). A candidate carrying no private-key marker at all is skipped ALWAYS, agent or not: an empty file, a stray text file, or the classic `IdentityFile ~/.ss Copies of this mod
1 near-identical copy found in the catalogue:
- ssh-mcp CLAUDE.md — 100% identical, 29 lines differ
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ssh-mcp
MCP server that makes SSH work for AI tools. 21 tools across 4 categories: SSH environment management, diagnostics, remote operations, and higher-level ops.
Architecture
src/index.ts— CLI entry point. Starts MCP server with stdio transport. Drains pool on shutdown.src/server.ts— Creates McpServer, registers tools, re-exports all public APIs.src/tools.ts— 21 MCP tools across environment management, diagnostics, remote operations, and higher-level ops.src/ssh.ts— SSH connection primitives (connect, connectRaw, connectWithProxy, resolveConfig, exec, SFTP ops). resolveConfig usesssh -Gfor SSH config awareness. Supports ProxyJump for bastion hosts. Auto-diagnoses on connection failure.src/pool.ts— ConnectionPool class. Reuses SSH connections across tool calls with idle TTL, keepalive, and dead connection detection.src/ops.ts— Higher-level operations (multiExec, find, tail, serviceStatus). These wrap common ssh_exec patterns agents build manually.src/diagnose.ts— SSH environment diagnostics (agent, keys, known_hosts, config, connectivity). Handles both Unix and Windows OpenSSH agents. Owns the sharedisValidHostname/runArgshelpers and thesshprobe both connectivity checks run.src/env.ts— SSH environment management (ensureAgent, listSshKeys, loadKey, configLookup, fixKnownHosts, checkGitSsh, testConnection). Handles Windows OpenSSH agent service.src/policy.ts— Optional command allow/deny policy for the exec tools, configured viaSSH_MCP_COMMAND_WHITELIST/SSH_MCP_COMMAND_BLACKLIST.src/ssh-config.ts— Pure parser forssh -Goutput, shared byresolveConfig(ssh.ts) andconfigLookup(env.ts).bin/ssh-mcp.mjs— Runtime launcher. Prefers anoambinary (>= 0.9.0), falls back to running the server in-process. Owns signal forwarding and escalation.
Build
- Bundler: tsup with two entry configs (CLI with shebang, library with types).
- Linter: Biome (not ESLint).
- Tests: Vitest. Integration tests require Docker (
npm run test:integration). - TypeScript: Strict mode, ES2022 target, ESM.
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.
- yesterday Changed · +13 lines · +1,081 tokens per session scan A → C d2352959ec03
- 5d ago First seen · 46 lines · 708 tokens per session scan A 1806e018579d
ssh-mcp CLAUDE.md is an instructions file published in the GitHub repository YawLabs/ssh-mcp (4 stars, last pushed 4d ago), licensed MIT. It adds 1,789 tokens to every session, about $0.0089 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
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 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.