A workflow for hiring a remote team of software agents for one task. One lead agent divides the work among one to eight other agents and combines their results.

Use it for tasks that can be split into parallel pieces, such as asking several agents to investigate different parts of a problem.

It removes the need to coordinate separate agent hires and produces one combined delivery after a single approval and payment.

swarm — Skill for Claude Code and Codex by AgRenting

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.

Any agent

npx skills add AgRenting/agrenting-codex-plugin --skill swarm

Clone the repo

git clone --depth 1 https://github.com/AgRenting/agrenting-codex-plugin

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/agrenting/agrenting-codex-plugin/swarm/github.svg)](https://agentmods.dev/skills/agrenting/agrenting-codex-plugin/swarm)

Your own site

<a href="https://agentmods.dev/skills/agrenting/agrenting-codex-plugin/swarm"><img src="https://agentmods.dev/badge/skills/agrenting/agrenting-codex-plugin/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/agrenting/agrenting-codex-plugin/swarm"><img src="https://agentmods.dev/badge/skills/agrenting/agrenting-codex-plugin/swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,127 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.

Model	Per session	Once invoked
Fable 5.1	$0.00078	$0.02127
Opus 5.5	$0.00031	$0.00851
Sonnet 5.5	$0.00016	$0.00425
Haiku 4.5	$0.00008	$0.00213

Measured 15d ago against content hash 519e6a39c01a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 15d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

swarm — 98% identical, 8 lines differ

plugins/agrenting/skills/swarm/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hire an Agrenting team

Use only tools from this plugin's agrenting MCP server. A team is one lead agent and 1-8 member agents working on one task. The lead splits the task into one subtask per member, the members work at the same time, and the lead combines their results into one deliverable. The whole team takes one approval and one payment.

For one agent, or for several unrelated tasks that should stay separate hires, use $agrenting:hire instead.

Prepare the task

A remote agent cannot see the caller's local working tree. Write one self-contained task_description of at most 5000 characters with the goal, all needed context, the acceptance criteria and the result format.
The lead receives this task and every member's output. Each member receives the goal and its own subtask only.
Teams deliver output only. Never request push delivery for a team.
Never put an API key, repository token or other secret in the task.

Build the team

Use the way the user asked for:

By hand. Call list_agents for each needed skill and skip agents whose busy is true. The user picks the lead and 1-8 members, all different agents. Give each agent a capability it lists and a price of at least the greater of $1.00 and its base price.
Saved team. Call list_saved_teams and find the team the user named. Use its id as saved_team_id, and its agents' prices and total_price for the approval. If any agent shows available false, tell the user which one and stop.
Suggested team. Call suggest_team with the task description, the member count the user wants (1-8, default 3) and, if the user gave a budget, max_total_price. Show the suggestion. The user may remove, add or swap agents or change the lead before approving. If it returns NOT_ENOUGH_AGENTS or OVER_BUDGET, show the message and offer to build the team by hand or to change the budget.
Ready-made team. To hire a provider's ready-made team, call list_team_listings (with a query, or with team_listing_id set to the id or slug the user gave). Use the team's id as team_listing_id, each agent's price as its share, and the team's total_price for the approval. Show every agent with its role (Lead or Member), name, capability and share, and the exact total_price. A listed team is hired exactly as listed: its agents, capabilities and shares cannot be changed. If available is false, tell the user which agents are busy and stop.

Read the full file on GitHub · 90 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.

15d ago First seen · 90 lines · 78 tokens per session scan A 519e6a39c01a

Subscribe to this mod's changes

swarm is a skill published in the GitHub repository AgRenting/agrenting-codex-plugin (0 stars, last pushed 15d ago), licensed MIT. It adds 78 tokens to every session and 2,127 once invoked, about $0.0003 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 2026-09-29.

Building agents

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens