setup

setup is a skill for Claude Code from HiAgencia/hi-claude. It costs 90 tokens per session (1,824 once invoked), scanned A, original, MIT.

A project-onboarding guide based on the hi-claude method. It examines a project, asks the user plain-language questions, and creates setup files from templates.

In plain words
What is it for?
Starting, initializing, or organizing a project; checking its folders and existing setup; and generating project documentation and configuration in English or Spanish.
Why use it?
It helps turn an unorganized or unfamiliar project into a clearer starting point. It also helps decide what information belongs in CLAUDE.md, a file that gives an AI assistant project instructions.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the hi-claude plugin — 8 skills, 6 agents shipped together

Good fit Starting, initializing, or organizing a project; checking its folders and existing setup; and generating project documentation and configuration in English or Spanish.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add HiAgencia/hi-claude
Claude Code
/plugin install hi-claude

Made for: Claude Code.

Or install hi-claude, the plugin that ships this one along with the rest of its 8 skills, 6 agents.

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.

agentmods badge for setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/hiagencia/hi-claude/setup/github.svg)](https://agentmods.dev/skills/hiagencia/hi-claude/setup)
Your own site
<a href="https://agentmods.dev/skills/hiagencia/hi-claude/setup"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/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.

agentmods 80×15 button for setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/hiagencia/hi-claude/setup"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,824 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.
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 5.1 $0.00090 $0.01824
Opus 5 $0.00045 $0.00912
Sonnet 5 $0.00018 $0.00365
Haiku 4.5 $0.00009 $0.00182

Measured 9d ago against content hash 326f58b40d4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 9d 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.

skills/setup/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hi-claude Setup

Onboard a project into the hi-claude method in ~5 minutes, interviewing the user in plain language (they may be non-technical) and generating everything from templates.

Phase 1 — Detect (no questions)

  1. Inspect the working directory: empty folder or existing project? Is there a CLAUDE.md (root or .claude/)? A docs/ folder? A git repo?
  2. Note which MCP servers, plugins, and skills are available in THIS session (they are in your context) — you will propose which ones belong in the project's CLAUDE.md.
  3. Detect the user's language from the conversation; generate everything in that language (templates exist in es and en).

Phase 2 — Interview

One AskUserQuestion call. The tool takes 2-4 closed options per question and adds "Other" for free text, so open answers arrive through it. Ask in the user's language, with plain words.

What must be resolved by the end of the interview — the wording is yours:

Must be resolved Becomes
What this project is the CLAUDE.md header, in the user's own words
What kind of work it is the folder tree: src/+tests/ for code, BRAND/+content/ for marketing, research/ for documents
Which of the tools connected in THIS session belong to the project the tools table, one "when to use it here" line each
Which limits are non-negotiable here the LIMITING rules
What makes a session CLOSED, in a way that can be RUN {{SESSION_DONE_CRITERION}} in the ROADMAP's §0

Ground every option in what you detected in the folder: a guess the user can correct beats a blank. For the last one, a runnable criterion is the point — the test suite green and the linter clean for code, the file published and reachable for content, every claim with its source for research.

Phase 3 — Propose (nothing written yet)

Present the exact plan: the file tree to create and the full CLAUDE.md content, built from ${CLAUDE_PLUGIN_ROOT}/skills/setup/templates/<lang>/CLAUDE.template.md with every {{PLACEHOLDER}} filled:

Read the full file on GitHub · 134 lines

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. 9d ago First seen · 134 lines · 90 tokens per session scan A 326f58b40d4d

Subscribe to this mod's changes

setup is a skill published in the GitHub repository HiAgencia/hi-claude (2 stars, last pushed 19d ago), licensed MIT. It adds 90 tokens to every session and 1,824 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories