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/tencentcloud/octop/skill-managernpx skills add TencentCloud/Octop --skill skill-managergit clone --depth 1 https://github.com/TencentCloud/OctopWhat 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 | $0.00114 | $0.01098 |
| Opus 5 | $0.00057 | $0.00549 |
| Sonnet 5 | $0.00023 | $0.00220 |
| Haiku 4.5 | $0.00011 | $0.00110 |
Grade C, and why
skill-manager scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- 删除前点名目标并取得明确确认。使用 `remove --yes`,不要直接 `rm -rf`。需要恢复时使用 `restore`。 How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Manager
只管理当前实例的 {{OCTOP_SKILLS}}/。当前实例工作区固定为 {{OCTOP_WORKSPACE}};上传文件通常位于其中的 inbound/。系统文件(skills、内置 skills、会话等)在 {{OCTOP_SKILLS}} 所在目录。不要用 pwd、$HOME、~/.harness-agent/workspace、记忆文件或搜索结果重新猜测工作区。不要改其他实例、全局 Skill 目录或 {{OCTOP_BUILTIN_SKILLS}}/。
操作入口
使用内置脚本完成检查、下载、安全解包、安装、列出和删除:
python "{{OCTOP_BUILTIN_SKILLS}}/skill-manager/scripts/manage_skills.py" <command>
# 列出已安装技能
... list
# 检查来源,不写入已安装 skills 目录
... inspect "<file-directory-url-or-skillhub:slug>"
# 安装;仓库或压缩包内的多个 Skill 可一次安装
... install "<source>" [--subpath "path/in/repo"] [--name "slug"]
# 仅在用户明确同意替换后覆盖
... install "<source>" --force
# SkillHub 搜索;结果可用 skillhub:<slug> 检查或安装
... skillhub-search "<query>" --limit 10
# 仅在用户明确同意删除后执行;实际移动到 skills/.trash/
... remove "<slug>" --yes
# 从回收站恢复
... restore "<trash-name>"
来源处理
- 现成 Skill、目录或 ZIP/TAR:先
inspect;检查通过且用户已要求安装时执行install。 - Git/GitHub URL:可直接处理仓库、GitHub
tree子目录和指向SKILL.md的blobURL。复杂仓库使用git+<url>和--subpath。 - SkillHub 页面 URL:
https://skillhub.cn/skills/<namespace>/<slug>可直接传给inspect或install;脚本会解析 namespace 和 slug。不要自行安装/升级 CLI,不要直接运行skillhub install。 - 普通 HTTP(S) URL:脚本处理直接文件和压缩包。若 URL 是其他介绍网页,先用现有网页工具读取并找到公开仓库、下载地址或
SKILL.md,再交给脚本。不得绕过登录、付费墙或访问控制。 - SkillHub 搜索:用户只描述能力时,先搜索并给出 1–3 个候选的 slug、名称、用途和来源,让用户选择;用户已点名具体 Skill 时,可直接检查并安装。
- 任意非 Skill 文件:普通资料不会因复制而自动成为 Skill。先读取和理解材料,再使用内置
skill-creator工作流,将可复用知识、步骤和必要资源整理为合法 Skill,写入{{OCTOP_SKILLS}}/<slug>/,然后执行inspect校验。
变更规则
- 新安装请求本身即表示同意新增;目标已存在时停止并说明冲突,只有获得明确同意才使用
--force。 - 编辑现有 Skill 前先读取其
SKILL.md和相关资源,只改该 Skill 目录;修改后重新inspect。 - 删除前点名目标并取得明确确认。使用
remove --yes,不要直接rm -rf。需要恢复时使用restore。 - 安装后报告 slug 和最终路径。新安装、更新或删除的 Skill 通常从下一次新会话开始完整生效。
安全边界
- 脚本限制下载及解包体积、文件数,拒绝路径穿越和符号链接,并通过暂存目录安装。
- 不执行、导入或 source 下载包中的代码。安装表示部署 Skill 内容,不代表第三方代码已通过安全审计。
- 不在输出中回显 URL 凭据;私有来源只使用环境中已有的 Git 或 SkillHub 凭据。
- 若当前实例没有 Shell 执行能力,仍可用文件工具处理简单文本 Skill,但必须说明 URL 下载、安全解包和 SkillHub CLI 无法完成,不能假装成功。
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.
- yesterday First seen · 63 lines · 114 tokens per session scan C 1b6cc6d30208
skill-manager is a skill published in the GitHub repository TencentCloud/Octop (1,292 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 1,098 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…