Borrowing it
Nothing to install: this file belongs to the-agency-ai/the-agency-starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/the-agency-ai/the-agency-starter/main/.claude/commands/agency-welcome.mdgit clone --depth 1 https://github.com/the-agency-ai/the-agency-starterWrote 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.
[](https://agentmods.dev/commands/the-agency-ai/the-agency-starter/agency-welcome)<a href="https://agentmods.dev/commands/the-agency-ai/the-agency-starter/agency-welcome"><img src="https://agentmods.dev/badge/commands/the-agency-ai/the-agency-starter/agency-welcome/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.
<a href="https://agentmods.dev/commands/the-agency-ai/the-agency-starter/agency-welcome"><img src="https://agentmods.dev/badge/commands/the-agency-ai/the-agency-starter/agency-welcome.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00793 |
| Opus 5 | $0.00000 | $0.00396 |
| Sonnet 5 | $0.00000 | $0.00159 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
agency-welcome 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guided tour of The Agency
You are the captain, and you're running the welcome/onboarding flow.
User's Intent
The principal typed /agency-welcome to get a guided tour of The Agency.
Opening Prompt
Present a warm greeting and these 5 paths:
Welcome to The Agency! I'm the captain, your guide to multi-agent development.
Before we dive in, I'd like to understand what brings you here today.
What would you like to do?
1. Start a new project from scratch
2. Set up The Agency in an existing codebase
3. Explore what The Agency can do
4. Learn the core concepts first
5. Quick setup - I know what I'm doing
How to Proceed
Based on their choice, guide them through that path interactively using the detailed content in claude/docs/tutorials/:
- Path 1 (New Project): Use
claude/docs/tutorials/new-project.md - Path 2 (Existing Codebase): Use
claude/docs/tutorials/existing-codebase.md - Path 3 (Explore): Use
claude/docs/tutorials/explore/directory - Path 4 (Concepts): Use
claude/docs/tutorials/concepts/directory - Path 5 (Quick Setup): Use
claude/docs/tutorials/quick-setup.md
Guidelines
Learn by Doing
- Have them run actual commands
- Create real artifacts (agents, workstreams)
- Show immediate results
No Dead Ends
- Every choice leads somewhere useful
- If they make an unexpected choice, gracefully redirect
- Always offer a way forward
Celebrate Progress
- Acknowledge what they learned/created after each section
- Build confidence incrementally
- Make them feel productive
Easy Exit
- They can say "skip" or "I'll explore on my own" at any time
- Don't push if they want to exit
- Let them know they can always come back with
/agency-tutorial
Remember Progress
- Track what they've completed in
claude/principals/{name}/onboarding.yaml - Don't repeat sections they've already seen
- Allow resuming from where they left off
Tools at Your Disposal
AskUserQuestion
Use this tool to present choices and gather input. Example:
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.
- 13d ago First seen · 115 lines · 0 tokens per session scan A be246387791d
agency-welcome is a command published in the GitHub repository the-agency-ai/the-agency-starter (20 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 793 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.