What is host-tool-setup?

A workflow for checking, planning, approving, verifying, or rolling back host tools such as GitNexus, Serena, Context7, and MCP servers. These are tools that extend what a coding agent can inspect or use.

Use it to inspect the environment, create an installation plan, guide approved setup and configuration, verify tool availability, and report or roll back setup results.

It distinguishes a plan from an actual installation and prevents missing or unverified host tools from being treated as ready.

host-tool-setup — Skill for Claude Code and Codex by protect-my-hair

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.

Any agent

npx skills add protect-my-hair/nucleus-marketplace --skill host-tool-setup

Clone the repo

git clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplace

Made for: Claude Code, Codex.

Or install nucleus, the plugin that ships this one along with the rest of its 27 skills, 1 agent, 1 hook.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/host-tool-setup/github.svg)](https://agentmods.dev/skills/protect-my-hair/nucleus-marketplace/host-tool-setup)

Your own site

<a href="https://agentmods.dev/skills/protect-my-hair/nucleus-marketplace/host-tool-setup"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/host-tool-setup/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/protect-my-hair/nucleus-marketplace/host-tool-setup"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/host-tool-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,540 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.01540
Opus 5	$0.00018	$0.00770
Sonnet 5	$0.00007	$0.00308
Haiku 4.5	$0.00004	$0.00154

Measured 12d ago against content hash 99eb23c4cf72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

host-tool-setup 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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (assets/codex-session-start-hook.py, scripts/host_tool_setup.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.

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.

plugins/nucleus/skills/host-tool-setup/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:gitnexus
host-tool-install:serena
host-tool-install:context7
host-mcp-config:codex:gitnexus
host-mcp-config:claude:gitnexus
host-mcp-config:codex:serena
host-mcp-config:claude:serena
host-mcp-config:codex:context7
host-mcp-config:claude:context7
host-tool-activate:serena
host-tool-index:gitnexus
host-tool-verify

Read the full file on GitHub · 78 lines

Files

What ships with it

11 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.

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.

12d ago First seen · 78 lines · 37 tokens per session scan A 99eb23c4cf72

Subscribe to this mod's changes

host-tool-setup is a skill published in the GitHub repository protect-my-hair/nucleus-marketplace (162 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,540 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.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens