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/jordanburke/ssh-client-mcp-server/claude-mdgit clone --depth 1 https://github.com/jordanburke/ssh-client-mcp-serverWrote 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/jordanburke/ssh-client-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/jordanburke/ssh-client-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jordanburke/ssh-client-mcp-server/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 | $0.01373 | $0.01373 |
| Opus 5 | $0.00687 | $0.00687 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
ssh-client-mcp-server 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 5d 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 — 86 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
This is a pnpm monorepo containing three packages:
| Package | npm name | Role |
|---|---|---|
packages/core |
@ssh-mcp/core (private) |
Shared SSH pool (createPool), tmux command builders (tmuxList/tmuxSend/tmuxRead/tmuxKeys), auth resolution (resolveAuth), and SSH exec helpers. Bundled into both servers; not published separately. |
packages/connector |
ssh-client-mcp-server |
Single-host MCP server — exec + tmux_* tools for one SSH host, configured via CLI flags. |
packages/orchestrator |
ssh-fleet-mcp-server |
Multi-host fleet MCP server — hosts_list + host-routed exec/tmux_* tools, driven by a TOML fleet config (--config= flag or SSH_FLEET_CONFIG env or ~/.config/ssh-fleet/fleet.toml). |
Both servers consume @ssh-mcp/core for all SSH and tmux logic. Run the full suite with pnpm -r validate.
The connector package (ssh-client-mcp-server) retains its original published identity and public API unchanged.
Development Commands
Each package delegates all tooling to ts-builds. Run from the repo root to hit all packages:
- Validate all:
pnpm -r validate- Full chain per package: format → lint → typecheck → test → build - Per-package:
cd packages/<name> && pnpm validate
Within any package:
- Build:
pnpm build- Production build via tsdown →dist/(dev builds go tolib/) - Dev:
pnpm dev- tsdown watch mode - Test:
pnpm test/pnpm test:watch/pnpm test:coverage - Lint/Format:
pnpm lint/pnpm format(both auto-fix);*:checkvariants for CI - Inspect (connector/orchestrator):
pnpm inspect- Build + launch MCP Inspector
Architecture
@ssh-mcp/core (packages/core)
Shared logic consumed by both servers. Not published; bundled by tsdown into each server's dist/.
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.
- 5d ago First seen · 86 lines · 1,373 tokens per session scan A 648002e9d14a
ssh-client-mcp-server CLAUDE.md is an instructions file published in the GitHub repository jordanburke/ssh-client-mcp-server (3 stars, last pushed 2mo ago), licensed MIT. It adds 1,373 tokens to every session, about $0.0069 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).
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.
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).