2native-ssh-mcp: Instructions file for Codex

AGENTS.md

2native-ssh-mcp AGENTS.md is an instructions file for Codex, OpenCode from daidaiJ/2native-ssh-mcp. It costs 2,884 tokens per session, scanned A, original, ISC.

A set of instructions for an AI coding agent working with 2native-ssh-mcp, a tool that runs commands and transfers files on remote computers over SSH.

In plain words
What is it for?
Use it when maintaining, testing, or handing off work on this SSH-based MCP server.
Why use it?
It gives the agent project-specific guidance, including how to handle commands safely and what has or has not been verified.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is daidaiJ/2native-ssh-mcp's own configuration. It tells Codex and OpenCode how to work on 2native-ssh-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything 2native-ssh-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to daidaiJ/2native-ssh-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.

Copy the file
curl -O https://raw.githubusercontent.com/daidaiJ/2native-ssh-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/daidaiJ/2native-ssh-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for 2native-ssh-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/daidaij/2native-ssh-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/daidaij/2native-ssh-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/daidaij/2native-ssh-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/daidaij/2native-ssh-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for 2native-ssh-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/daidaij/2native-ssh-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/daidaij/2native-ssh-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,884 This file is loaded in full into every session.
When invoked 2,884 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02884 $0.02884
Opus 5.5 $0.01154 $0.01154
Sonnet 5.5 $0.00577 $0.00577
Haiku 4.5 $0.00288 $0.00288

Measured 6d ago against content hash e983334affa7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

2native-ssh-mcp 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 6d 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.

AGENTS.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — 2native-ssh-mcp

SSH-based MCP server (Go): remote command execution + file transfer over MCP. Human-facing docs live in README.md and docs/; agent-facing API reference is docs/AGENT_GUIDE.md; the defensive playbook for agents driving this server is skills/2native-ssh-mcp-agent/SKILL.md.

🔄 Handoff 摘要

(无进行中的交接。)

escaping-optimizations — done

  • 已落地: execute-command 的三种命令形态 —— cmdString(shell)、cmdString+args[](argv,服务端逐参数引用)、scriptFile(本地脚本 SFTP 暂存到远端后执行);scriptCleanup / scriptInterpreter 接线;lint 接线(off/warn/strict,strict 报 COMMAND_LINT_FAILED);连接建立后一次的远端 base64/jq 探测(autoProbe 可关,list-servers 显示 capabilities=)
  • 可审计性(用户硬要求): 白/黑名单、破坏性分类器、审批弹窗与审计记录看的都是可读等效命令 —— argv 记 grep -rn 'foo bar' /etc 这种最小引用形式,scriptFile 记脚本正文(首行注释标注来源、暂存路径、解释器、是否清理),不做 base64 之类的包装
  • 验证证据: go test ./... 绿(含结构门禁);golangci-lint run ./... 0 issues;go test -tags integration ./internal/manager/ 全绿(Ubuntu 24.04 实测:argv 逐字节还原且对照 naive join 会拆分/展开、暂存脚本执行+清理、后台模式经清理子壳保住退出码 5、lint warn/strict、审计记录内容、能力探测与关闭);MCP stdio 端到端驱动(tools/list 参数表、argv/scriptFile/lint 调用、capabilities=base64,jq)
  • 详情指针: .handoff/escaping-optimizations.md

schema-slimming — done (v1.9.1)

  • 决策(用户,2026-10-28): 配一次就长期不变的开关留在连接配置,不上推成工具参数(策略开关尤其不该握在调用方手里);工具描述精准、长文本交给配套 skill。
  • 已落地: execute-command 去掉 lintMode / scriptCleanup / pty / keepAlive / keepAliveDuration(前三个配置层早有同名字段;保活改为新配置项 keepAliveMs,-1 = 执行完即断,$global 可设默认);session 去掉 pty(后台任务按连接的 pty 决定是否包 script);DefaultCommandTimeoutMs 30000 → 120000(实测 137 次调用里 130 次显式传 timeout,中位 90s、p75 120s,只有 3 次用得上旧默认值);四个工具描述压到 1–3 句。
  • 实测收益: tools/list 载荷 7251 B → 4716 B(−35%),参数 28 → 22,execute-command 13 → 8 个参数(3663 B → 1778 B)。
  • 验证证据: golangci-lint run ./... 0 issues;go test ./... 绿(internal/config 本机 ACL 既有红除外,CI 跑 Linux);go vet -tags integration ./... 干净;go test -tags integration ./internal/manager/ 全绿(含 TestExecDefaultNoPTY、TestBackgroundPTY 两条 PTY 用例,以及暂存脚本清理、后台退出码用例);新增 internal/config/config_keepalive_test.go 覆盖默认值/全局默认/连接覆盖/非法值。

Read the full file on GitHub · 61 lines

Changes

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.

  1. 6d ago Changed · +32 lines · +1,853 tokens per session e983334affa7
  2. 9d ago First seen · 29 lines · 1,031 tokens per session scan A 89f057e74d8c

Subscribe to this mod's changes

2native-ssh-mcp AGENTS.md is an instructions file published in the GitHub repository daidaiJ/2native-ssh-mcp (0 stars, last pushed 6d ago), licensed ISC. It adds 2,884 tokens to every session, about $0.0115 per session on Opus 5.5. 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 2026-10-28.

Related

2native-ssh-mcp AGENTS.md compared with instructions from other repositories

2native-ssh-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
2native-ssh-mcp AGENTS.mddaidaiJ/2native-ssh-mcpInstructions file06d agoISCA2,884Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode