MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
A skill your agent uses when 需要检查、规划、审批、验证或回滚 GitNexus、Serena、Context7、MCP 等宿主工具能力。
MITAuto-check passed
Install Host Tool Setup
$ npx skills add protect-my-hair/nucleus-marketplace --skill host-tool-setup -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace host-tool-setup --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/nucleus/skills/host-tool-setup .claude/skills/host-tool-setup && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "host-tool-setup" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/host-tool-setup into .claude/skills/host-tool-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-tool-setup", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/host-tool-setupType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add protect-my-hair/nucleus-marketplace --skill host-tool-setup -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace host-tool-setup --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/nucleus/skills/host-tool-setup .agents/skills/host-tool-setup && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "host-tool-setup" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/host-tool-setup into .agents/skills/host-tool-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-tool-setup", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add protect-my-hair/nucleus-marketplace --skill host-tool-setup -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace host-tool-setup --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/nucleus/skills/host-tool-setup .cursor/skills/host-tool-setup && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "host-tool-setup" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/host-tool-setup into .cursor/skills/host-tool-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-tool-setup", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/protect-my-hair/nucleus-marketplace.git --path plugins/nucleus/skills/host-tool-setup--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add protect-my-hair/nucleus-marketplace --skill host-tool-setup -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace host-tool-setup --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/nucleus/skills/host-tool-setup .gemini/skills/host-tool-setup && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "host-tool-setup" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/host-tool-setup into .gemini/skills/host-tool-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-tool-setup", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install protect-my-hair/nucleus-marketplace host-tool-setupInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add protect-my-hair/nucleus-marketplace --skill host-tool-setup -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/nucleus/skills/host-tool-setup .github/skills/host-tool-setup && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "host-tool-setup" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/host-tool-setup into .github/skills/host-tool-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-tool-setup", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add protect-my-hair/nucleus-marketplace --skill host-tool-setup -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install protect-my-hair/nucleus-marketplace host-tool-setup --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/nucleus/skills/host-tool-setup .opencode/skills/host-tool-setup && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "host-tool-setup" agent skill from https://github.com/protect-my-hair/nucleus-marketplace/tree/main/plugins/nucleus/skills/host-tool-setup into .opencode/skills/host-tool-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-tool-setup", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
host-tool-setup- GitHub stars
- 164
- Token cost
- ~932 tokens
- SKILL.md length
- 238 words
- Files
- 12 (incl. scripts, references, assets)
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when 需要检查、规划、审批、验证或回滚 GitNexus、Serena、Context7、MCP 等宿主工具能力。
- Works in 9 steps: 运行 inspect，只读检查 PATH、Codex / Claude Code… → 运行 plan，生成… → 读取… → …
- 需要检查、规划、审批、验证或回滚 GitNexus、Serena、Context7、MCP 等宿主工具能力
- SKILL.md covers 使用原则, 最短操作顺序, 子命令 and 审批范围, plus 2 more sections
- Runs Python scripts from its folder; calls python3
What it does
Host Tool Setup is an agent skill from protect-my-hair/nucleus-marketplace. Use when 需要检查、规划、审批、验证或回滚 GitNexus、Serena、Context7、MCP 等宿主工具能力。
Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/codex-hooks.json` and `assets/codex-session-start-hook.py`).
It works with Model Context Protocol. The repository describes itself as: Nucleus — Claude Code / Codex 工作流插件，确保 AI 编码产出结构可信、边界可审计、过程可追溯. The licence is MIT.
When your agent uses it
- 需要检查、规划、审批、验证或回滚 GitNexus、Serena、Context7、MCP 等宿主工具能力
Example prompts
- “/host-tool-setup”
Requirements
- Python 3
Workflow steps
9 steps, taken from the first numbered list in SKILL.md.
- 运行 inspect，只读检查 PATH、Codex / Claude Code 配置标记和目标仓库证据目录。
- 运行 plan，生成 .nucleus/runs//host-tool-setup/host-tool-plan.json 和 host-tool-plan.md。
- 读取 references/host-tool-install-session.md 和 references/tool-installation.md，根据 inspect 结果判断 GitNexus、Serena、Context7 需要哪种安装或配置引导。
- 如需执行审批后动作，先运行 approval --approval 。审批事实必须包含匹配的 planHash 和精确 approvedScopes。
- install、configure-mcp、activate、index、rollback 会写引导报告；AI 按 reference 引导用户选择安装方式、配置位置和验证步骤。
- 如果 summary.md 或 result.json 仍显示缺工具，当前 agent 必须先完成 host-tool-plan-review.subagentPreReview 并确认材料可提交人工审查，再继续安装确认和执行；不能把报告路径交给用户后结束。
- 用户确认后，由当前 agent 执行安装、用户级配置、Serena 初始化 / 激活、GitNexus 索引等动作；该确认前必须已完成 host-tool-plan-review.subagentPreReview 并确认材料可提交人工审查。
- 运行 verify 获取真实只读验证结果；缺工具或缺配置证据时返回 blocked。
- 运行 build-result，先读 summary.md，机器事实源是 result.json；未通过时继续安装会话，直到 verify 通过或用户明确拒绝。
What it can do on your machine
Read from SKILL.md and the folder at commit 3c82085. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Host Tool Setup loads about 932 tokens when it runs, and up to ~5.9k if it reads all its reference files. Until then it costs about 20 tokens; SKILL.md has 238 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from protect-my-hair/nucleus-marketplace at commit 3c82085, republished under its MIT licence (© protect-my-hair). 238 words, ~932 tokens.
Download SKILL.mdSave it as
.claude/skills/host-tool-setup/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.- name
- host-tool-setup
- description
- Use when 需要检查、规划、审批、验证或回滚 GitNexus、Serena、Context7、MCP 等宿主工具能力。
Host Tool Setup
用于宿主工具初始化。它独立于 target-repo-setup：目标仓库初始化成功不代表宿主工具已安装或可用；计划已生成，不代表工具已安装。
使用原则
SKILL.md负责路由、边界和人读口径；详细安装依据放在references/tool-installation.md。- 确定性 runtime 只负责
inspect、plan、确认校验、本机状态报告、verify和result.json。 install、configure-mcp、activate、index、rollback只写 guidance-only 报告，指向安装 reference；它们不是自动安装器，不写用户级配置。- 工具缺失时进入安装引导，不把 setup 判成失败。
- 计划已生成不代表工具已安装；确认继续也不代表工具可用。
- guidance-only 报告是中间证据，不是终点；如果宿主工具仍缺失或未验证，当前 agent 不得结束本轮 setup 回复。
- 真实安装、MCP 配置、Serena 初始化 / 激活和 GitNexus 索引由当前 agent 按
references/host-tool-install-session.md与references/tool-installation.md先完成host-tool-plan-review.subagentPreReview并确认材料可提交人工审查，再向用户确认后执行。 - 到达
host-tool-plan-review前，必须按 workflow 的subagentPreReview调度独立 reviewer 子代理；未取得“材料可提交人工审查”预审结论时，不得请求人工确认安装计划。
最短操作顺序
- 运行
inspect，只读检查 PATH、Codex / Claude Code 配置标记和目标仓库证据目录。 - 运行
plan，生成.nucleus/runs/<workflowRunId>/host-tool-setup/host-tool-plan.json和host-tool-plan.md。 - 读取
references/host-tool-install-session.md和references/tool-installation.md，根据 inspect 结果判断 GitNexus、Serena、Context7 需要哪种安装或配置引导。 - 如需执行审批后动作，先运行
approval --approval <approval.json>。审批事实必须包含匹配的planHash和精确approvedScopes。 install、configure-mcp、activate、index、rollback会写引导报告；AI 按 reference 引导用户选择安装方式、配置位置和验证步骤。- 如果
summary.md或result.json仍显示缺工具，当前 agent 必须先完成host-tool-plan-review.subagentPreReview并确认材料可提交人工审查，再继续安装确认和执行；不能把报告路径交给用户后结束。 - 用户确认后，由当前 agent 执行安装、用户级配置、Serena 初始化 / 激活、GitNexus 索引等动作；该确认前必须已完成
host-tool-plan-review.subagentPreReview并确认材料可提交人工审查。 - 运行
verify获取真实只读验证结果；缺工具或缺配置证据时返回 blocked。 - 运行
build-result，先读summary.md，机器事实源是result.json；未通过时继续安装会话，直到 verify 通过或用户明确拒绝。
子命令
运行 python3 scripts/host_tool_setup.py list-subcommands 查看完整能力。
- 真实只读能力：
inspect、plan、verify、build-result。 - 确认门控引导能力：
approval、install、configure-mcp、activate、index、rollback。
审批范围
稳定 scope：
host-tool-install:gitnexushost-tool-install:serenahost-tool-install:context7host-mcp-config:codex:gitnexushost-mcp-config:claude:gitnexushost-mcp-config:codex:serenahost-mcp-config:claude:serenahost-mcp-config:codex:context7host-mcp-config:claude:context7host-tool-activate:serenahost-tool-index:gitnexushost-tool-verify
不要新增泛化的 install-plan 或 tool-readiness scope。每个 scope 必须有 executor、report、verify 和 rollback 语义。
边界
- 证据只写
.nucleus/runs/<workflowRunId>/host-tool-setup/**。 - 不写
docs/requirement/**。 - 不把
.autocode/**、.claude/notepads/**、docs/bugfix/**当事实源。 - 脚本不写用户级
~/.codex、~/.claude、MCP 配置或系统工具目录。 - 写用户级配置、安装 npm/uv 工具、激活 Serena 或建立 GitNexus 索引前，AI 必须按 reference 向用户说明将做什么并等待确认。
SUCCEEDED只能由真实verify通过产生；确认通过、计划生成或 guidance report 都不等于成功。- 缺工具时不能停在
NEEDS_HUMAN_REVIEW、summary 或 guidance report；当前 agent 必须按安装会话 reference 先完成host-tool-plan-review.subagentPreReview并确认材料可提交人工审查，再继续安装确认和执行，然后重新运行 verify。
何时读取资源
- workflow step、artifact 和 result 语义：读
references/workflow-contract.md。 - scope、approval 和 planHash：读
references/approval-scopes.md。 - 缺工具后的 subagentPreReview、安装确认、执行和 verify 闭环：读
references/host-tool-install-session.md。 - GitNexus、Serena、Context7 安装和配置依据：读
references/tool-installation.md。 - 人读摘要和交付口径：读
references/human-result.md。 - 计划摘要模板来自
assets/host-tool-plan-template.md。 - Codex 入口纪律硬前置（可选）：读
references/codex-entry-hook.md，模板见assets/codex-session-start-hook.py与assets/codex-hooks.json。Claude Code 由插件自带 SessionStart hook 自动注入，无需本引导；Codex 需用户开启[features] hooks = true并/hooks审批后才生效，属审批式可选增强，非 setup 默认动作。
© protect-my-hair, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 11 other files (scripts, references, assets) in plugins/nucleus/skills/host-tool-setup of protect-my-hair/nucleus-marketplace.
- SKILL.md
- agents/openai.yaml
- assets/codex-hooks.json
- assets/codex-session-start-hook.py
- assets/host-tool-plan-template.md
- references/approval-scopes.md
- references/codex-entry-hook.md
- references/host-tool-install-session.md
- references/human-result.md
- references/tool-installation.md
- references/workflow-contract.md
- scripts/host_tool_setup.py
Open the folder on GitHubat commit 3c82085
Compare with similar skills
Host Tool Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Host Tool Setup this skillprotect-my-hair/nucleus-marketplace | 164 | — | ~932 | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Figma use_figma Plugin API Ruleswarpdotdev/warp | 65k | 4 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills | 8.5k | 6 repos | ~3.2k | Automated safety check: Notes | Apache-2.0 |
Similar skills
- Official
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
- Official
MCP Integration for Plugins
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
Figma use_figma Plugin API Rules
warpdotdev/warp
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
- Official
Stitch to Remotion Walkthrough Videos
google-labs-code/stitch-skills
Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.
MCP Development
coollabsio/coolify
A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.
More from protect-my-hair/nucleus-marketplace
All 18 skills in this repoNucleus Delivery Evidence Closure
protect-my-hair/nucleus-marketplace
Collects prior Nucleus task evidence into a candidate-only delivery closure package and PR/MR draft text, blocking if any feature's design, review or verification evidence is missing.
Nucleus Context Validator
protect-my-hair/nucleus-marketplace
Validates the context file for a Nucleus V2 workflow run, discovers standalone context from explicit input, and writes a blocked result when required context is missing.
Nucleus Session Binding Report
protect-my-hair/nucleus-marketplace
Collects, freezes and validates a Nucleus V2 session binding report that records the native Claude Code or Codex session ID, transcript path and hash.
Nucleus Result Package Builder
protect-my-hair/nucleus-marketplace
Builds the result.json file for a Nucleus V2 workflow run from its context, gates, blockers and step status, and exits non-zero when the run is blocked.
Defect Intake and RCA Candidates
protect-my-hair/nucleus-marketplace
Checks whether a defect report has enough context to be accepted, then drafts candidate-only root-cause evidence for human review without confirming causes or changing code.
Nucleus Delivery Evidence Finalizer
protect-my-hair/nucleus-marketplace
Combines the evidence from completed Nucleus workflow steps into a final evidence report and result package, without scheduling steps, updating trackers or opening pull requests.
Related
Works with
Questions about Host Tool Setup
What does Host Tool Setup do?
A skill your agent uses when 需要检查、规划、审批、验证或回滚 GitNexus、Serena、Context7、MCP 等宿主工具能力。. Host Tool Setup is an agent skill from protect-my-hair/nucleus-marketplace.
When should I use Host Tool Setup?
Host Tool Setup fits situations like: 需要检查、规划、审批、验证或回滚 GitNexus、Serena、Context7、MCP 等宿主工具能力.
How do I install Host Tool Setup in Claude Code?
Run `npx skills add protect-my-hair/nucleus-marketplace --skill host-tool-setup -a claude-code`. Or copy the skill folder (plugins/nucleus/skills/host-tool-setup in protect-my-hair/nucleus-marketplace) into .claude/skills/host-tool-setup in your project. Claude Code loads it when a task matches its description.
How do I install Host Tool Setup in Codex?
Run `npx skills add protect-my-hair/nucleus-marketplace --skill host-tool-setup -a codex`. Or copy the skill folder (plugins/nucleus/skills/host-tool-setup in protect-my-hair/nucleus-marketplace) into .agents/skills/host-tool-setup in your project. Codex loads it when a task matches its description.
Can I use Host Tool Setup in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add protect-my-hair/nucleus-marketplace --skill host-tool-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/host-tool-setup, .gemini/skills/host-tool-setup, .github/skills/host-tool-setup and .opencode/skills/host-tool-setup in your project.
What does Host Tool Setup need to run?
Going by SKILL.md and its folder, Host Tool Setup needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Host Tool Setup access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Host Tool Setup safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Host Tool Setup use?
Host Tool Setup is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Host Tool Setup use?
About 932 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5k tokens, read only when the agent opens those files.
What are the alternatives to Host Tool Setup?
Skills that share tags, products or a category with Host Tool Setup: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Host Tool Setup?
protect-my-hair (a GitHub user) maintains it in protect-my-hair/nucleus-marketplace, which has 164 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on July 23, 2026.
Source: protect-my-hair/nucleus-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.