Borrowing it
Nothing to install: this file belongs to Sma1lboy/rove. 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/Sma1lboy/rove/main/.agents/skills/pstack/skills/swarm/SKILL.mdgit clone --depth 1 https://github.com/Sma1lboy/roveWrote 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/skills/sma1lboy/rove/swarm)<a href="https://agentmods.dev/skills/sma1lboy/rove/swarm"><img src="https://agentmods.dev/badge/skills/sma1lboy/rove/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.
<a href="https://agentmods.dev/skills/sma1lboy/rove/swarm"><img src="https://agentmods.dev/badge/skills/sma1lboy/rove/swarm.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 | $0.00041 | $0.00569 |
| Opus 5.5 | $0.00016 | $0.00228 |
| Sonnet 5.5 | $0.00008 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
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 28d 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.
This is a copy
86% identical to swarm — 23 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swarm
Fan out N parallel cloud workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.
Start
Open a todolist with one entry per phase before launching anything.
- Frame
- Fan out
- Aggregate
- Report
Phase A: Frame
- State the done predicate and the artifact or report the swarm must return.
- Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare
first pass,rank all, orbest-ofbefore spawning. - Set N from the user or derive it from the shape. N is total workers, not the cloud concurrency limit.
- Workers inherit the session model by default. Pass
modelon the Agent call only when a cheaper tier clearly fits mechanical work, or when the point is a model race, in which case name each arm's model up front. - Give each worker its own writable output when it writes. Use a worktree, branch, or
/tmp/swarm-<slug>/worker-<n>/.
Phase B: Fan out
Spawn all N workers in one message with the Agent tool, subagent_type: general-purpose, and isolation: "worktree" for every worker that writes, so their edits cannot collide. Inside a Rove session ($ROVE_TASK_ID set), workers that edit files are Rove tasks instead — rove api add --count N, or one add per slice (see the rove skill) — so the user can see and steer them.
Every brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use PASS, ISSUES, or BLOCKED with evidence.
If a worker drops out, proceed with N-1 and note it.
Phase C: Aggregate
Read the terminal results. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.
Keep a compact result table, one-line evidenced issues, and explicit gaps or dropouts.
Phase D: Report
Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.
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.
- 28d ago Changed · -2 lines 5c88f1702c58
- 1mo ago First seen · 49 lines · 41 tokens per session scan A 03c52d5ea712
swarm is a skill published in the GitHub repository Sma1lboy/rove (178 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 569 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to swarm, differing in 23 lines, and is treated as a copy.
Other skills, from other repositories
xlsx
Create, read and edit Microsoft Excel .xlsx spreadsheets — data tables, formulas, multiple sheets, number formats, conditional formatting, charts, frozen panes and named ranges. Also covers reading an existing workbook to extract values or formulas, recalculating formulas so cached values are correct, converting to…
Read, create and manipulate PDF files — extract text and tables, merge, split, rotate, reorder and delete pages, read and fill AcroForm fields, add or strip metadata, encrypt and decrypt, and generate new PDFs from HTML or from scratch. Also covers rasterising pages to images so a PDF can actually be looked at, and…
ai-usage-review
Review recorded AI coding-tool usage and recommend concrete optimizations. Reads real token, cost, session and harness-configuration data from the AI Insights MCP server, then reports ranked, evidence-backed fixes — trimming instruction files, raising the prompt-cache hit rate, right-sizing models, cutting MCP…
procedural-generation
Procedural generation patterns — Perlin/Simplex noise, BSP dungeon generation, random walk, loot tables with weighted random, wave function collapse basics, seed-based reproducibility.
dialogue-system
Dialogue tree patterns — ScriptableObject graph, node types (text, choice, condition, event), typewriter effect, localization-ready. Load when implementing NPC conversations.
inventory-system
Inventory, equipment, and crafting patterns — ScriptableObject item definitions, slot-based inventory, equipment system, crafting recipes, UI binding. Load when implementing item management.