quickstart

An interactive onboarding command that examines a project and configures this Claude Code template for it.

In plain words
What is it for?
Use it to detect the language, framework, package manager, tests, and database; update CLAUDE.md; choose MCP servers; install dependencies; and verify the setup.
Why use it?
It removes the manual work of identifying the project's technology, writing setup details, choosing services, and checking that everything works.

Command for Claude Code

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 commands/liortesta/clawdagent/quickstart
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 497 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00497
Opus 5 $0.00000 $0.00249
Sonnet 5 $0.00000 $0.00099
Haiku 4.5 $0.00000 $0.00050

Measured 2d ago against content hash 3e84db79ce39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quickstart 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 2d 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.

.claude/commands/quickstart.md · 63 lines

What it actually says

Quickstart — Interactive Project Onboarding

Guide the user through setting up this Claude Code template in their project. Ask questions, configure, and verify — step by step.

Process:

Step 1: Project Detection

  • Scan the current directory
  • Detect: language, framework, package manager, test framework, database
  • Show findings and ask user to confirm/correct

Step 2: Configure CLAUDE.md

  • Fill in the Architecture section with detected values
  • Fill in Key Commands with actual commands (npm/pnpm/yarn)
  • Ask: "What are the most important project conventions I should know?"
  • Add answers to Project Conventions section

Step 3: Configure MCP Servers

  • Ask which MCP servers to activate:
    • GitHub: "Do you want me to manage GitHub issues/PRs? (need GITHUB_TOKEN)"
    • Playwright: "Do you have a web UI to test?"
    • PostgreSQL: "Do you use PostgreSQL? (need DATABASE_URL)"
    • Brave Search: "Do you want web search capability? (need BRAVE_API_KEY)"
    • Slack: "Do you want Slack notifications? (need SLACK_BOT_TOKEN)"
  • For servers with tokens: ask user to provide them
  • Disable unused servers (comment out in .mcp.json)

Step 4: Install Dependencies

  • Run bootstrap.sh (or bootstrap.ps1 on Windows)
  • Install project dependencies
  • Install LSP servers if needed

Step 5: Verify Setup

  • Run /test-setup to verify everything
  • Fix any issues found
  • Run /setup-project for full project configuration

Step 6: First Task

  • Ask: "What's the first thing you want to build or fix?"
  • Recommend the right command to start:
    • New feature → "/plan [feature]"
    • Bug fix → "/self-heal"
    • Code review → "/review"
    • Understand codebase → "/plan analyze the entire codebase"

Output at End:

## Quickstart Complete!

**Project**: [name]
**Stack**: [language + framework]
**Active MCP Servers**: [list]
**Agents Available**: [count]
**Commands Available**: [count]

**Recommended first steps:**
1. `/plan [your first task]`
2. Start building!

$ARGUMENTS

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. 2d ago First seen · 63 lines · 0 tokens per session scan A 3e84db79ce39

Subscribe to this mod's changes

quickstart is a command published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 497 tokens. 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.