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 skills add drn/dots --skill swarmgit clone --depth 1 https://github.com/drn/dotsWrote 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/drn/dots/swarm)<a href="https://agentmods.dev/skills/drn/dots/swarm"><img src="https://agentmods.dev/badge/skills/drn/dots/swarm.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 5.1 | $0.00034 | $0.02909 |
| Opus 5 | $0.00017 | $0.01455 |
| Sonnet 5 | $0.00007 | $0.00582 |
| Haiku 4.5 | $0.00003 | $0.00291 |
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 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Swarm
Agent teams with automatic progress monitoring. The lead thread stays alive, polls task status, and reports progress -- you never have to re-prompt to check in.
The Problem
When team-based skills (/dev, /explore, /debug, /contest) run in Conductor, the lead creates the team, sends initial assignments, and its turn ends. Agents work in the background, but the workspace appears idle. You have to manually re-prompt to check status.
The Fix
This skill uses native agent teams (TeamCreate + SendMessage) for full inter-agent communication, then adds an automatic monitoring loop that polls TaskList every 20 seconds and outputs progress. The lead thread never returns until all tasks are complete.
Arguments
$ARGUMENTS- Required: description of the task. Can be any kind of parallel work: development, research, debugging, review, etc.
If no arguments are provided, ask the user what they want to accomplish.
Context
- Current branch: !
git branch --show-current 2>/dev/null | head -1 - Git status: !
git status --short 2>/dev/null | head -20 - Project root: !
pwd - Project type: !
find . -maxdepth 1 \( -name go.mod -o -name Gemfile -o -name package.json -o -name Cargo.toml -o -name pyproject.toml -o -name setup.py -o -name requirements.txt \) 2>/dev/null | head -5 - Recent commits: !
git log --oneline -5 2>/dev/null | head -5 - Directory structure: !
find . -maxdepth 2 -type d -not -path '*/\.*' -not -path '*/node_modules/*' -not -path '*/vendor/*' 2>/dev/null | head -30
Overview
You are the swarm coordinator. You create an agent team, assign work, then actively monitor progress in a polling loop -- keeping the main thread alive and reporting status in real time.
Task: $ARGUMENTS
You coordinate, monitor, and synthesize. Agents do the work and communicate with each other.
How the monitoring loop works:
- Create team with
TeamCreate, spawn agents, send initial assignments viaSendMessage - Create tasks with
TaskCreateso agents can track progress viaTaskUpdate - Enter the monitoring loop:
Bash("sleep 20")to block the thread (keeps it alive in Conductor)TaskList()to check current task statuses- Output a progress table showing what changed since last check
- Repeat until all tasks are
completed
- Break out, process any queued agent messages, synthesize results
- Shut down team
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 · 344 lines · 34 tokens per session scan A 673db81ff7d2
swarm is a skill published in the GitHub repository drn/dots (23 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 2,909 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…