skill-manager

A tool for managing the coding agent's installed skills, which are reusable instruction sets for specific tasks. It can inspect, install, update, list, restore, or remove skills from the current agent instance.

In plain words
What is it for?
Use it to search SkillHub, inspect a skill before installing it, install skills, update or remove them, restore removed skills, and turn documents or code into a new skill.
Why use it?
It gives one controlled way to handle skill files from local folders, archives, Git repositories, URLs, or SkillHub. This reduces the risk of putting a skill in the wrong location or replacing one without approval.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/tencentcloud/octop/skill-manager
Any agent
npx skills add TencentCloud/Octop --skill skill-manager
Clone the repo
git clone --depth 1 https://github.com/TencentCloud/Octop

Made for: Claude Code, Codex.

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,098 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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 $0.00114 $0.01098
Opus 5 $0.00057 $0.00549
Sonnet 5 $0.00023 $0.00220
Haiku 4.5 $0.00011 $0.00110

Measured yesterday against content hash 1b6cc6d30208, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/manage_skills.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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`。
src/octop/infra/agents/builtin_skills/skill-manager/SKILL.md · 63 lines

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

  1. 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
  2. Git/GitHub URL:可直接处理仓库、GitHub tree 子目录和指向 SKILL.mdblob URL。复杂仓库使用 git+<url>--subpath
  3. SkillHub 页面 URLhttps://skillhub.cn/skills/<namespace>/<slug> 可直接传给 inspectinstall;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
  4. 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。
  5. 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。
  6. 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。

Read the full file on GitHub · 63 lines

Files

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.

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. yesterday First seen · 63 lines · 114 tokens per session scan C 1b6cc6d30208

Subscribe to this mod's changes

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.

Related

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/CopilotKit · 175 tokens

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/CopilotKit · 46 tokens

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.

CopilotKit/CopilotKit · 48 tokens

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".

kirodotdev/KiroCrew · 74 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

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…

kirodotdev/KiroCrew · 154 tokens