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/hellonice/ssh-mcp-jumpserver/agents-mdgit clone --depth 1 https://github.com/helloNice/ssh-mcp-jumpserverWhat 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 | $0.00578 | $0.00578 |
| Opus 5 | $0.00289 | $0.00289 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
ssh-mcp-jumpserver AGENTS.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 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.
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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This is a TypeScript MCP server for SSH access and JumpServer host discovery. Source code lives in src/: index.ts is the CLI entry point, server.ts registers MCP tools, and feature modules are grouped under config/, jumpserver/, security/, ssh/, and utils/. Example client and SSH configuration files are in examples/. Generated build output goes to dist/ and should not be edited directly.
Build, Test, and Development Commands
npm ci: install dependencies exactly frompackage-lock.json.npm run build: compile TypeScript withtsc; this is the CI validation command.npm run dev -- --project-root .: run the server fromsrc/index.tswithtsxfor local development.npm start: run the compiled server fromdist/index.js.npm run inspect: launch the MCP inspector against the TypeScript entry point.
There is currently no dedicated test script. Use npm run build as the minimum verification step.
Coding Style & Naming Conventions
Use TypeScript ES modules and keep imports explicit with .js extensions where required by Node16 module resolution. The project uses strict TypeScript settings, ES2022 targets, and declaration/source map output. Follow the existing style: two-space indentation in JSON, concise TypeScript functions, camelCase for variables/functions, PascalCase for types/interfaces, and directory-level index.ts exports for module boundaries.
Keep files encoded as UTF-8 without BOM and use CRLF line endings.
Testing Guidelines
No test framework is configured yet. For behavior changes, add focused tests only after introducing a test runner, and document the new command in package.json and this guide. Until then, verify with npm run build and, for MCP behavior, exercise the relevant tool through npm run inspect or a local MCP client.
Commit & Pull Request Guidelines
Recent commits use Conventional Commit-style prefixes such as feat: and chore(deps):. Keep commit messages short, imperative, and scoped to one change.
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 First seen · 36 lines · 578 tokens per session scan A f3d08303972d
ssh-mcp-jumpserver AGENTS.md is an instructions file published in the GitHub repository helloNice/ssh-mcp-jumpserver (0 stars, last pushed 26d ago), licensed MIT. It adds 578 tokens to every session, about $0.0029 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
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.
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).
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.