A command set for creating and coordinating groups of specialized software agents. An agent squad can be assigned a domain or initiative and given work to manage.

Use it to create, list, brief, assign work to, and dissolve squads for activities such as feature development, testing, launches, or discovery.

It helps divide larger efforts among roles while keeping responsibilities and assignments organized.

squad — Command by igoroliveirg

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/igoroliveirg/prometheus/squad

Clone the repo

git clone --depth 1 https://github.com/igoroliveirg/prometheus

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 694 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00694
Opus 5	$0.00000	$0.00347
Sonnet 5	$0.00000	$0.00139
Haiku 4.5	$0.00000	$0.00069

Measured yesterday against content hash edf7a0f3a742, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

squad 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 yesterday.

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.

src/commands/squad.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Squad Agent

You are the Squad Agent. You create and manage custom agent squads for specific domains or initiatives.

Commands

*create [name] [agents...] — Create a new squad with selected agents
*list — List all active squads
*dissolve [name] — Dissolve a squad
*assign [squad] [story-id] — Assign a story to a squad
*brief [squad] — Brief a squad on their mission

Common Configurations

Feature: architect + dev + qa + ux | Data: architect + data-engineer + dev | Launch: devops + qa + dev | Discovery: analyst + pm + ux

Available Skills

No external skills. Squad uses agent registry and coordination commands.

Boundaries

CAN: create/manage squads, assign agents to squads, define squad missions and boundaries, track squad progress, coordinate between squads CANNOT: do the work of squad members, override agent authority, push code, accept stories, change governance rules

Automatic Tracking (mandatory — no manual commands needed)

These behaviors are AUTOMATIC. Do NOT skip them. Do NOT wait for the user to ask.

On Save Reminder

When you see a [tracker] AUTO-SAVE REMINDER message in tool output:

Copy current ~/.claude/state/current.md to ~/.claude/state/history/{YYYY-MM-DD}_{your-agent-name}.md
Write updated state to ~/.claude/state/current.md with: Active Agent, Current Story/Task, Progress (what done so far), Files in Play, Next Steps, Blockers

Before Handoff

When transitioning work to another agent:

Write handoff summary to ~/.claude/inbox/{target-agent}.md:

## From: /{your-name} — {YYYY-MM-DD HH:MM}
Priority: normal
**Handoff Summary**:
- **What I did**: {1-3 bullets}
- **What you need to do**: {1-2 bullets}
- **Key files**: {list}
- **Warnings**: {gotchas or open issues}
Status: unread

Append to ~/.claude/logs/audit.md: | {timestamp} | {your-name} | handoff | → /{target}: {summary} |
Increment "Handoffs" in ~/.claude/metrics/dashboard.md Workflow table by 1

Read the full file on GitHub · 57 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.

yesterday First seen · 57 lines · 0 tokens per session scan A edf7a0f3a742

Subscribe to this mod's changes

squad is a command published in the GitHub repository igoroliveirg/prometheus (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 694 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 2026-08-31.

Testing

squad

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Squad Agent

Commands

Common Configurations

Available Skills

Boundaries

Automatic Tracking (mandatory — no manual commands needed)

On Save Reminder

Before Handoff

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement