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 skills add DongLiStudio/personal-agent-foundation --skill server-profilegit clone --depth 1 https://github.com/DongLiStudio/personal-agent-foundationWrote 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/skills/donglistudio/personal-agent-foundation/server-profile)<a href="https://agentmods.dev/skills/donglistudio/personal-agent-foundation/server-profile"><img src="https://agentmods.dev/badge/skills/donglistudio/personal-agent-foundation/server-profile/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.
<a href="https://agentmods.dev/skills/donglistudio/personal-agent-foundation/server-profile"><img src="https://agentmods.dev/badge/skills/donglistudio/personal-agent-foundation/server-profile.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00059 | $0.01811 |
| Opus 5.5 | $0.00024 | $0.00724 |
| Sonnet 5.5 | $0.00012 | $0.00362 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade A, and why
server-profile 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
服务器连接
路由与边界
读取当前项目 AGENTS.md、README.md、STATUS.md,以及上层 GLOBAL 的 README.md、GLOBAL_CONTEXT.md、SERVER_PROFILES.md。已有 Profile 只读取对应 servers/.md;新服务器确认地址、端口、用户和用途,不推断默认主机或 root 权限。
连接授权不等于部署、重启或安全策略变更授权。不得输出私钥、密码、完整环境变量或未经筛选的日志。首次公钥安装需要可信控制台或已验证连接;没有初始权限时提供一条可复制命令,不伪称已连接。
会话复用
同一用户请求/同一回答轮次内,对同一服务器、同一主体的连续操作必须在一个持续 SSH 会话中批量完成,完成后立即退出,避免每条命令重新申请 Bitwarden 签名。建立交互会话后必须保留终端工具的可复用会话句柄(如 session_id),本轮后续命令只能通过该句柄发送,不得把每条命令重新包装成 ssh;若工具无法返回或保持句柄,立即暂停并报告。回答结束后退出;下一条用户请求必须重新连接并重新授权,即使目标和主体不变。首次独立认证、密钥轮换验收、目标/主体变化或连接断开时也必须新连接,并记录原因。保持始终提示授权、主机校验和 ForwardAgent no,不建立跨回答轮次的常驻连接。已认证会话可继续执行命令,锁定 Bitwarden 不会断开它;进程名称只用于辨认,不作为防仿冒依据。详细边界见 Agent 接入与验收。
首次接入与轮换
- 人工 SSH 默认在 Bitwarden 桌面端创建独立 Ed25519 SSH 密钥条目,启用 SSH Agent 并设置每次签名提示授权;不默认在磁盘生成、导出或恢复私钥。没有桌面端时先引导安装、启用和验证;
bwCLI 不代替桌面 SSH Agent。 - 完整读取 Agent 接入与验收,按实际 Windows/macOS 客户端和安装来源检查通道、socket 及公开指纹。Bitwarden 已开启不代表 Git、WindTerm 等全部接入;每种实际客户端单独验收。用户指定 root 时据实保留主体,不擅自另创用户。
- 核验用户提供公钥的算法、完整编码和指纹,服务端只安装公钥。若用户仍坚持文件私钥,先解释泄露风险并再次确认具体例外,优先加密口令与最小 ACL;不能因 Agent 拒签而自动生成无口令私钥。现有业务专用凭据遵循对应服务规则,不顺带撤销。
- 从用户云控制台获取主机公钥指纹。ssh-keyscan 只用于取得候选公钥,不是信任来源。候选指纹必须与可信来源一致;与另一台已登记服务器指纹相同也需核查是否操作错主机或克隆密钥。不能关闭 StrictHostKeyChecking 或直接信任未知密钥。
- 用户控制台追加公钥时使用单行 grep -qxF 公钥 authorized_keys || echo 公钥 >> authorized_keys,确保目录 700、文件 600 且属主正确;不覆盖原授权。公钥仅使用已生成并核验的完整值,不包含占位符。无需重启 sshd。
- 先用显式地址、端口、主体和已验证 known_hosts 建立新的 Agent 连接,验收时禁用文件身份、密码/交互回退及连接复用,执行 whoami、hostname;观察目标条目签名授权与最终认证。再按需维护公开别名、保留其他 Host,并用 ssh -G 核对路由。正常使用同时提供完整 IP/域名命令,不要求换机先有别名。不默认转发 Agent。
- 轮换时只有新连接成功且用户授权清理后,按完整公钥字段精确移除旧授权,逐字节验证其他行不变,再重连。不要仅按注释删除;不要顺便删除本机旧私钥。
- 关闭密码需独立授权:先核验恢复入口、有效 Include/Match 与账号条件,语法通过再 reload,新公钥连接和密码/交互负向测试分别验收。公钥成功不代表全机密码已关闭。登记前完整读取 服务器详情模板,横向核对一份现行详情,不复制其事实。私钥和口令不进入 Git,未验收字段明确待核验。
登记验收
- 详情必须包含“定位与连接”“权限与安全边界”“服务索引”“恢复说明”,服务表采用模板六列;未知字段标记待核验,不推断。
- 索引、详情、实际地址/端口/主体与 Agent 公钥身份必须一致;客户端公钥与服务器主机指纹分开记录,禁止混用。公钥选择器是公开路由,不强制永久保存,不能从服务器主机公钥推导客户端身份。
- 将长期事实与带日期的运行快照分开;未检查服务时不编造清单,旧的“待盘点”说明在实际盘点后更新。自启动配置存在不等于重启验收通过。
- 现行详情不累积变更日志:移除已撤销人工指纹、被替代状态和重复验收流水,历史交给 Git 与项目记录;保留现行自动化授权、必要回退入口和未解决风险。只删除文档噪声,不因此删除实际密钥、备份或账号。
- 写入后回读完整详情,逐项对照模板与本次证据;检查 Markdown 链接、敏感信息及 diff。Skill 语法校验不能替代输出文档验收。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 31c236257fbd
- 10d ago Changed · +6 lines · +3 tokens per session dabd69a188f1
- 1mo ago First seen · 43 lines · 56 tokens per session scan A 8af498dba71d
server-profile is a skill published in the GitHub repository DongLiStudio/personal-agent-foundation (16 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 1,811 once invoked, about $0.0002 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.
Other skills, from other repositories
harbor-daytona
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.
boost-modules
Skill "boost-modules" from av/harbor, covering harbor boost custom modules, module structure, quick reference, output methods and stream text to client.
token-usage
Nested swiss-knife reference for token usage, cost, cache, and tool-call/API-call reports. Use for model cost reports, cache rates, budget/burn analysis, and tools-per-API-call trends across LingTai logs.
composio
Build AI agents and apps with Composio - access 200+ external tools with Tool Router or direct execution.
security-arsenal
Security payloads, bypass tables, wordlists, gf pattern names, always-rejected bug list, and conditionally-valid-with-chain table. Use when you need specific payloads for XSS/SSRF/SQLi/XXE/NoSQLi/command injection/SSTI/IDOR/path-traversal/HTTP smuggling/WebSocket/MFA bypass, bypass techniques, or to check if a finding…
frontmcp-development
Use when building any FrontMCP server component other than a tool (for tools, use create-tool). Covers @Resource static resources and parameterized URI templates; @Prompt reusable prompts (RAG, multi-turn); @Provider singleton dependency-injection providers (database pools, API clients); @Agent autonomous LLM agents…