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 skills/uvwt/agentdock/skill-installationnpx skills add uvwt/agentdock --skill skill-installationgit clone --depth 1 https://github.com/uvwt/agentdockWhat 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 | $0.00043 | $0.02860 |
| Opus 5 | $0.00022 | $0.01430 |
| Sonnet 5 | $0.00009 | $0.00572 |
| Haiku 4.5 | $0.00004 | $0.00286 |
Grade A, and why
skill-installation 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 2d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Installation
用于把本地或外部 Skill 安全地纳入当前 AgentDock,并验证当前激活版本确实可用。Skill 只提供审查和安装流程;真实读取、校验、配置、安装、命令执行和回滚由工具完成。
何时使用
使用本 Skill 处理:
- 安装本地或第三方 Skill;
- 审查未知 Skill 的代码、权限和数据行为;
- 配置已安装 Skill 的环境变量;
- 更新并激活新版本;
- 验证 Skill 是否已进入索引并可读取;
- 对当前激活版本运行只读状态检查;
- 回滚到上一已安装版本。
不要使用本 Skill 创建新 Skill、重写核心设计、替作者决定业务边界,或大范围修改第三方包。需要修改源码、补测试、升级文档或重新设计时,切换到 skill-authoring。
完整安全审查规范见 skill://skill-installation/references/skill-security-review.md。
核心原则
- 先审查,后安装;不能把
skill_package validate当作完整安全审计。 - 来源、摘要、版本、风险和缺失配置必须可追溯。
- 默认只读检查;写入、删除、上传、权限变化和依赖安装必须显式识别。
- 不替用户生成、猜测或迁移真实秘密。
- 环境变量只通过 AgentDock 的 Skill 独立环境管理能力配置。
- 安装成功不等于可用;必须验证当前激活版本、索引、正文、引用和只读状态。
- 回滚只切换已安装版本,不删除私有状态,也不覆盖共享环境配置。
标准流程
1. 识别来源
先记录:
- 来源类型:本地目录、本地压缩包或 HTTPS 下载地址;
- 来源位置和发布者;
- 目标 Skill 名称和版本;
- 用户期望安装、更新、验证还是回滚;
- 是否提供预期 SHA-256 摘要;
- 是否为首次接触的第三方包。
远程来源优先要求可信发布页和可验证摘要。URL 认证信息、查询参数和片段不得写入报告或日志。
2. 在安装前获取静态内容
在隔离的临时审查位置查看包,不直接从未知目录运行脚本。至少读取:
- 根目录文件清单;
SKILL.md;references/;- 所有脚本和测试;
- 依赖清单和锁文件;
- 包内二进制、压缩包或生成文件;
- 隐藏文件;
- 符号链接和特殊文件。
只读检查不应加载包内环境文件、不应执行安装钩子,也不应运行未知脚本。
3. 检查结构和 Frontmatter
确认:
- 包根目录存在
SKILL.md; - Frontmatter 只依赖当前正式字段
name、description、version; name稳定且与安装目标一致;description能明确触发场景;version是语义化版本;- 正文非空;
- 包内引用路径存在且不越界;
- 没有符号链接逃逸、父目录穿越或绝对路径写入。
发现 agentdock.yaml、旧式统一执行协议或旧 Skill Runtime 设计时,至少标记为 blocked,不得直接安装。
4. 执行安全审查
逐项检查:
- 网络访问目标、协议和上传内容;
- Shell 命令和子进程;
- 文件系统读取、写入、覆盖和删除;
- 权限、启动项、计划任务和持久化变化;
- 凭据、Cookie、浏览器数据、SSH 配置和主目录敏感文件读取;
- 外部依赖安装;
- 下载后执行、动态代码加载和混淆代码;
- 二进制文件和无法审查的构件;
- 运行状态和秘密是否被打包;
- 日志、错误和返回值是否可能泄露秘密;
- 破坏性动作是否要求用户确认。
风险分类:
| 等级 | 含义 | 默认处理 |
|---|---|---|
low |
纯文档或行为明确、只读、无敏感访问 | 可继续校验 |
medium |
有明确网络、写入或普通依赖,但范围可解释 | 展示风险后继续 |
high |
涉及敏感凭据、广泛文件访问、上传、删除或持久化 | 未经明确确认不安装 |
blocked |
存在不可接受或无法解释的危险行为 | 停止安装 |
必须阻止:
- 包内真实密钥、Cookie、私钥或认证缓存;
- 自动读取浏览器全部 Cookie;
- 自动读取用户主目录敏感文件;
- 隐蔽下载并执行;
- 修改系统权限或持久化配置而未明确说明;
- 未经确认删除或覆盖数据;
- 未说明的外部上传;
- 路径穿越或符号链接逃逸;
- 无法审查且会被执行的二进制;
agentdock.yaml旧清单。
What ships with it
1 file 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.
- 2d ago First seen · 297 lines · 43 tokens per session scan A 41560731a67d
skill-installation is a skill published in the GitHub repository uvwt/agentdock (440 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,860 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
debugging-output-and-previewing-html-using-ray
Use when user says "send to Ray," "show in Ray," "debug in Ray," "log to Ray," "display in Ray," or wants to visualize data, debug output, or show diagrams in the Ray desktop application.
changelog-entry
Add a new entry to CHANGELOG.yml under the current unreleased version (or create the version block if needed), then regenerate documentation. Use when the user says things like "add a changelog entry", "log this fix in the changelog", or "/changelog-entry".
project-snmp-profiles-authoring
Use when editing Netdata SNMP profile YAMLs, topology SNMP profiles, ddsnmp profile parsing, or profile-format documentation. Requires checking source MIB field accessibility, especially MAX-ACCESS not-accessible INDEX objects, before adding or changing profile symbols.
fix-issues
Fix a batch of open GitHub issues end to end - one git worktree and one agent per issue (feature-dev for implementation, review-pr for review), individual PRs into develop, a release PR to main with a final multi-agent integration review, and optional tag/release/issue-comment publishing. Use when the user asks to…
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
kurtosis-ethereum
Run Ethereum multi-client devnets using Kurtosis and the ethpandaops/ethereum-package. Use for spinning up local devnets, syncing public testnets, validating cross-client interop, testing fork transitions, shadowforks, running assertoor checks, debugging CL/EL client interactions, or verifying new feature…