nextclaw: Skill for Claude Code

.agents/wiki/skills/operations/private-remote-host-access-recovery/SKILL.md

private-remote-host-access-recovery is a skill for Claude Code, Codex from Peiiii/nextclaw. It costs 63 tokens per session (1,743 once invoked), scanned A, original, MIT.

A procedure for restoring authorised SSH access to a private VPS or remote Linux machine when the normal entry point is unknown or fails before login. SSH is the encrypted command-line protocol commonly used to connect to remote machines.

In plain words
What is it for?
Diagnosing SSH connection failures, checking a host through an existing management console, establishing a verified fallback connection, and documenting rollback and host-identity checks.
Why use it?
It separates network, SSH, identity, and authentication failures so you do not repeatedly change credentials for a problem that happens before credentials are used. It also records a reusable connection without exposing passwords, tokens, or private keys.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Peiiii/nextclaw's own configuration. It tells Claude Code and Codex how to work on nextclaw 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 nextclaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Peiiii/nextclaw. 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/Peiiii/nextclaw/master/.agents/wiki/skills/operations/private-remote-host-access-recovery/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Peiiii/nextclaw

Made for: Claude Code, Codex.

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 private-remote-host-access-recovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/peiiii/nextclaw/private-remote-host-access-recovery/github.svg)](https://agentmods.dev/skills/peiiii/nextclaw/private-remote-host-access-recovery)
Your own site
<a href="https://agentmods.dev/skills/peiiii/nextclaw/private-remote-host-access-recovery"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/private-remote-host-access-recovery/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 private-remote-host-access-recovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/peiiii/nextclaw/private-remote-host-access-recovery"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/private-remote-host-access-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,743 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00063 $0.01743
Opus 5.5 $0.00025 $0.00697
Sonnet 5.5 $0.00013 $0.00349
Haiku 4.5 $0.00006 $0.00174

Measured 1mo ago against content hash 331bc20ba137, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

private-remote-host-access-recovery 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 1mo 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/wiki/skills/operations/private-remote-host-access-recovery/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

私有远程主机 SSH 访问恢复

Owner 与完成条件

本 Skill 负责把“已获授权但当前无法稳定 SSH 登录”的私有主机恢复为可重复使用、可验证且不泄露凭据的命令行入口。它不拥有业务部署、NextClaw remote 产品链路、云网络长期架构或系统安全加固;恢复 SSH 后,把后续工作交还原任务 owner。

仅在下列情况加载:

  • .local/remote-environments.private.md 中已有匹配主机,或用户明确给出并授权该主机;
  • SSH 地址、端口或认证方式不清楚;
  • TCP 已连通但在 SSH banner / key exchange / authentication 之前被关闭;
  • 需要借助已登录的云控制台建立备用入口。

完成必须同时满足:

  1. 一条不含密码、token 或私钥内容的本机 SSH 命令或别名可重复连接;
  2. 已在新连接中核验主机身份、登录用户和最小远程命令;
  3. 备用服务、监听端口、原服务影响和回滚点均有证据;
  4. 仅把验证后的连接事实更新到私有环境清单,公共 Skill 中不出现实例身份或凭据。

先定位失败阶段

先读取私有环境清单的匹配条目,再用一次有界诊断区分失败层级:

ssh -vvv -o ConnectionAttempts=1 -o ConnectTimeout=10 <user>@<host>
nc -vz -w 5 <host> 22

按最早失败点判断:

证据 阶段 下一步
timeout / no route 路由、安全组或防火墙 核对公网地址、云安全组和主机防火墙
connection refused 目标端口无监听或主动拒绝 从云控制台检查 sshd 与监听地址
收到 SSH banner 后进入 host-key 或认证 SSH 链路已经打通 处理主机指纹、用户或认证方式,不改传输层
kex_exchange_identification、连接在远端 banner 前关闭 TCP 22 路径可能被中间网络干预 先证明主机内 sshd 正常,再评估备用传输
host key changed 主机身份不一致 停止连接,从可信控制面重新核验指纹,禁止直接删除检查

“网页能打开”和“SSH 22 可用”是两条不同链路。认证前失败时不要反复更换密码;密码尚未参与握手。

从可信控制面证明主机侧 SSH

优先使用用户已经登录的云控制台、串口终端、Cloud Assistant 或现有管理入口执行只读检查:

sshd -t
systemctl status sshd --no-pager
ss -ltnp
ssh -o BatchMode=yes -o ConnectTimeout=5 localhost true

不同发行版的 unit 可能叫 ssh。本机回环连接能够进入认证、sshd -t 通过且 22 正确监听,只能证明主机侧服务正常;外部仍在 banner 前关闭时,继续调查云安全组、云防火墙、来源网络或中间链路。

不得为了“试试看”重启健康的 sshd、开放宽泛端口或覆盖现有防火墙规则。主机有共存服务时,先查端口 owner 和完整配置。

TLS 封装 SSH 备用入口

当且仅当以下条件同时成立时,可把 SSH 封装进一个独立 TLS 监听:

  • 已证明 127.0.0.1:22 上的 SSH 正常;
  • 直连 22 的外部路径在认证前被干预,且短期无法从网络控制面修复;
  • 用户授权范围包含恢复远程命令行入口;
  • 目标 TLS 端口未被 HTTPS、Nginx、Caddy、负载均衡或其它服务占用;
  • 已准备配置备份、明确 systemd unit 和回滚命令。

先确认端口和服务 owner:

ss -ltnp
systemctl list-units --type=service --state=running
nginx -T

可用 stunnel 建立单用途链路,核心拓扑为:

client ssh -> TLS listener:<tls-port> -> 127.0.0.1:22 -> sshd

服务端配置只表达传输关系,不保存 SSH 密码:

[ssh]
accept = 0.0.0.0:<tls-port>
connect = 127.0.0.1:22
cert = <certificate-path>
key = <private-key-path>

Read the full file on GitHub · 137 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. 1mo ago First seen · 137 lines · 63 tokens per session scan A 331bc20ba137

Subscribe to this mod's changes

private-remote-host-access-recovery is a skill published in the GitHub repository Peiiii/nextclaw (263 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 1,743 once invoked, about $0.0003 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 2026-09-14.

Related

private-remote-host-access-recovery compared with skills from other repositories

private-remote-host-access-recovery next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
private-remote-host-access-recoveryPeiiii/nextclawSkill263yesterdayMITA63Claude Code, Codex
openclaw-bun-upgradevincentkoc/dotskillsSkill111yesterdayMITA40Codex
add-vercelnanocoai/nanoclawSkill31kyesterdayMITB54Claude Code
ha-skill-creatorshiwenwen/hope-agentSkill1.9kyesterdayMITA106Claude Code
ha-browsershiwenwen/hope-agentSkill1.9kyesterdayMITA140Claude Code
ha-skill-installershiwenwen/hope-agentSkill1.9kyesterdayMITA82Claude Code, Codex
ha-data-storesshiwenwen/hope-agentSkill1.9kyesterdayMITA115Claude Code, Codex