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.
npx agentmods add commands/dheerg/swarms/onboardgit clone --depth 1 https://github.com/DheerG/swarmsWrote 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/dheerg/swarms/onboard)<a href="https://agentmods.dev/commands/dheerg/swarms/onboard"><img src="https://agentmods.dev/badge/commands/dheerg/swarms/onboard.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.02058 |
| Opus 5 | $0.00005 | $0.01029 |
| Sonnet 5 | $0.00002 | $0.00412 |
| Haiku 4.5 | $0.00001 | $0.00206 |
Grade A, and why
onboard 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 3d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/swarm:onboard
You are guiding a new swarm user through the four concepts they need before running /swarm:launch for the first time. Follow every step in order. Do NOT skip steps. Do NOT batch AskUserQuestion gates — each gate is its own turn so the user actually reads the concept before clicking.
If the user passed arguments with this command (e.g., /swarm:onboard build me a feature), acknowledge once that onboarding doesn't take a task — it teaches — and offer /swarm:launch with their task as a starting point when they're ready. Then continue with Step 1 unchanged.
The tone is direct and brief. Explain each concept, then ask a gate question that either advances or lets the user ask for more. Do not narrate your own process.
Step 1: Welcome
Output this welcome, verbatim:
Welcome to swarm. This is a short walkthrough — four concepts you need, then a choice about how to run, then your first team.
You can quit at any time by saying "stop." Nothing is spawned until you confirm at the end.
Then proceed to Step 2 in the same response.
Step 2: Concept — Outcomes
Output this explanation, verbatim:
Outcomes. Swarm wants to know what success looks like, not what to build.
- Implementation: "Add a Redis cache in front of the user service." — describes a solution.
- Outcome: "User profile reads return in under 50ms and don't hit the DB when cached." — describes the result.
Outcomes leave room for the team to reason about how. Constraints you want preserved ("don't change the public API") count as outcomes too.
Then use AskUserQuestion:
- question: "Got it?"
- header: "Outcomes"
- options:
- label: "Yes, continue" description: "Move on to the next concept"
- label: "Show me another example" description: "Give me one more outcome/implementation contrast"
If "Show me another example": output one more contrast example (pick any domain), then re-ask the same AskUserQuestion.
Step 3: Concept — Modes
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.
- 3d ago First seen · 193 lines · 11 tokens per session scan A 0eab2e0e47ea
onboard is a command published in the GitHub repository DheerG/swarms (86 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 2,058 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 2026-08-30.
Other commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
full
Run the full hope pipeline — intent, shape, target, freeze as needed — then execute.
save
Save this conversation as a new or existing reusable context.
fix-issue
!gh issue view $ARGUMENTS 2>/dev/null || echo "Could not fetch issue $ARGUMENTS".
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
session-log
Create or append a session log entry.