startup

startup is a command for Claude Code from spideynolove/claude-dotfiles. It costs 21 tokens per session (531 once invoked), scanned A, original, MIT.

A single project-onboarding command that checks whether the project has its codebase notes, project instructions, and detected team roles. It runs only the missing setup phases.

In plain words
What is it for?
Use it to analyse an unfamiliar codebase, create a CLAUDE.md instruction file when needed, detect project roles, and report the setup status.
Why use it?
It gives a new project a consistent starting point without repeating setup work that has already been completed.

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/spideynolove/claude-dotfiles/startup
Clone the repo
git clone --depth 1 https://github.com/spideynolove/claude-dotfiles

Made for: Claude Code.

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 startup

README.md
[![agentmods](https://agentmods.dev/badge/commands/spideynolove/claude-dotfiles/startup.svg)](https://agentmods.dev/commands/spideynolove/claude-dotfiles/startup)
Your own site
<a href="https://agentmods.dev/commands/spideynolove/claude-dotfiles/startup"><img src="https://agentmods.dev/badge/commands/spideynolove/claude-dotfiles/startup.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 531 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 5.1 $0.00021 $0.00531
Opus 5 $0.00010 $0.00266
Sonnet 5 $0.00004 $0.00106
Haiku 4.5 $0.00002 $0.00053

Measured 5d ago against content hash 8fa475a1a6ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

startup 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 5d 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-global-backup/commands/startup.md · 69 lines

What it actually says

Single entry point for project onboarding. Chains three phases in sequence, skipping any that are already complete.

Phase A — Codebase Analysis

Check if .aim/memory.jsonl exists:

[ -f .aim/memory.jsonl ] && echo "Knowledge graph exists" || echo "NEEDS_ONBOARD"

If NEEDS_ONBOARD: spawn the codebase-analyst agent to build the knowledge graph:

Agent(subagent_type: "codebase-analyst", prompt: "Analyze the codebase at $(pwd). Store findings in .aim/")

Wait for completion before proceeding.

Phase B — Project CLAUDE.md

Check if CLAUDE.md exists:

[ -f CLAUDE.md ] && echo "CLAUDE.md exists" || echo "NEEDS_INIT"

If NEEDS_INIT: run /init-project to generate it via an external CLI.

Wait for completion before proceeding.

Phase C — Role Detection

Check if .aim/roles.json exists:

[ -f .aim/roles.json ] && echo "Roles defined" || echo "NEEDS_ROLES"

If NEEDS_ROLES: run /detect-roles to detect project type and generate roles.

Summary

After all phases complete, print:

Startup complete:
  Knowledge graph: <entity count from .aim/memory.jsonl or "skipped">
  CLAUDE.md: <exists | generated | skipped>
  Project type: <from .aim/roles.json or "not detected">
  Roles: <comma-separated role IDs or "none">

Read the actual files to populate the summary:

[ -f .aim/memory.jsonl ] && echo "Entities: $(grep -c '"type":"entity"' .aim/memory.jsonl)"
[ -f .aim/roles.json ] && python3 -c "import json; r=json.load(open('.aim/roles.json')); print(f\"Type: {r['project_type']}, Roles: {', '.join(x['id'] for x in r['roles'])}\")"

Rules

  • Run phases in order: A → B → C
  • Skip any phase where the output file already exists
  • If a phase fails, log the error and continue to the next phase
  • Do not ask the user between phases unless /detect-roles requires confirmation
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. 5d ago First seen · 69 lines · 21 tokens per session scan A 8fa475a1a6ad

Subscribe to this mod's changes

startup is a command published in the GitHub repository spideynolove/claude-dotfiles (2 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 531 once invoked, about $0.0001 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.