deciduous: Command for Claude Code

.claude/commands/demo-swarm.md

demo-swarm is a command for Claude Code from notactuallytreyanastasio/deciduous. It costs 26 tokens per session (494 once invoked), scanned A, original, Apache-2.0.

A demonstration that coordinates one lead AI worker and four supporting workers to build a Tetris game. Each worker uses its own worktree and branch, while the lead combines the work after unit, type, and browser tests pass.

In plain words
What is it for?
Use it to demonstrate multi-agent game development on macOS in iTerm2 or Ghostty, with separate workers for the core, shell, view, and quality checks.
Why use it?
It shows how several coding agents can divide a project and communicate without editing the same working copy at once. It also records the sessions for later replay.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is notactuallytreyanastasio/deciduous's own configuration. It tells Claude Code how to work on deciduous itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything deciduous configures →

Reuse

Borrowing it

Nothing to install: this file belongs to notactuallytreyanastasio/deciduous. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/notactuallytreyanastasio/deciduous/main/.claude/commands/demo-swarm.md
Clone the repo
git clone --depth 1 https://github.com/notactuallytreyanastasio/deciduous

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 demo-swarm

README.md
[![agentmods](https://agentmods.dev/badge/commands/notactuallytreyanastasio/deciduous/demo-swarm/github.svg)](https://agentmods.dev/commands/notactuallytreyanastasio/deciduous/demo-swarm)
Your own site
<a href="https://agentmods.dev/commands/notactuallytreyanastasio/deciduous/demo-swarm"><img src="https://agentmods.dev/badge/commands/notactuallytreyanastasio/deciduous/demo-swarm/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.

agentmods 80×15 button for demo-swarm

Your own site · 80×15
<a href="https://agentmods.dev/commands/notactuallytreyanastasio/deciduous/demo-swarm"><img src="https://agentmods.dev/badge/commands/notactuallytreyanastasio/deciduous/demo-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 494 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00026 $0.00494
Opus 5.5 $0.00010 $0.00198
Sonnet 5.5 $0.00005 $0.00099
Haiku 4.5 $0.00003 $0.00049

Measured 1mo ago against content hash 14dab331b91c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

demo-swarm 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 1mo 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/demo-swarm.md · 41 lines

What it actually says

/demo-swarm

Run this with the Bash tool, exactly, and nothing else first:

deciduous demo-swarm $ARGUMENTS

It works only in iTerm2 or Ghostty on macOS. It creates a fresh repository (default ~/deciduous-swarm/swarm-MMDD-HHMM) and opens a new window. The lead pane (Opus) walks through the setup, then four Sonnet workers start, each in its own worktree and branch: the functional core, the imperative shell, the view, and QA. They share one deciduous workspace, coordinate on its message board (post_message, read_messages; direct messages only for interrupts), and integrate through the lead, which merges only when unit tests, the type check and browser tests pass. Every pane is recorded with timestamps under .swarm/rec/ for later replay.

Then tell the user, in two or three sentences, what opened: the arena path, the workspace and the recording directory, all printed by the command, and that the lead pane accepts instructions.

If it refuses because the terminal is not iTerm2 or Ghostty, or claude or the deciduous MCP server is missing, say so in one sentence and stop. Do not work around the check or start sessions another way.

If instead there is no such subcommand -- error: unrecognized subcommand 'demo-swarm' -- the deciduous that answered is older than 1.0.4, the first release to carry it. This happens even right after installing a newer one, when a second deciduous sits earlier on PATH than ~/.cargo/bin. Say that, and name deciduous --version and which -a deciduous to tell which, and cargo install deciduous --force to fix it. Those are the user's to run, not yours: this command may run only deciduous demo-swarm.

This is a demonstration, not work on this project: log nothing to the graph for it.

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. 1mo ago First seen · 41 lines · 26 tokens per session scan A 14dab331b91c

Subscribe to this mod's changes

demo-swarm is a command published in the GitHub repository notactuallytreyanastasio/deciduous (169 stars, last pushed 13d ago), licensed Apache-2.0. It adds 26 tokens to every session and 494 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-27.

Related

demo-swarm compared with commands from other repositories

demo-swarm next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
demo-swarmnotactuallytreyanastasio/deciduousCommand16913d agoApache-2.0A26Claude Code
tech-debtstriderZA/OpenCodeGameStudiosCommand114yesterdayMITA9Claude Code
simHorizonRobotics/EmbodiedGenCommand7182mo agoApache-2.0A11Claude Code
team-uistriderZA/OpenCodeGameStudiosCommand114yesterdayMITA11Claude Code
cert-checkMRCalderon3D/everything-game-dev-codeCommand10428d agoMITA11Claude Code
combat-designMRCalderon3D/everything-game-dev-codeCommand10428d agoMITA14Claude Code
ui-flow-reviewMRCalderon3D/everything-game-dev-codeCommand10428d agoMITA15Claude Code