auto-team

auto-team is a skill for Claude Code, Codex from hidobeats/hido-claude-kit. It costs 26 tokens per session (1,647 once invoked), scanned A, original, MIT.

A task coordinator for coding work that splits at least three independent parts across separate git worktrees, which are isolated copies of a project.

In plain words
What is it for?
Use it for large changes with independent workstreams, such as updating different modules or files in parallel and then merging the results into one branch.
Why use it?
It helps shorten large jobs by letting separate agents work at the same time without changing the same files. It is not meant for small fixes or tasks whose parts depend on one another.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for large changes with independent workstreams, such as updating different modules or files in parallel and then merging the results into one branch.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hidobeats/hido-claude-kit/auto-team
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 hidobeats/hido-claude-kit --skill auto-team
Clone the repo
git clone --depth 1 https://github.com/hidobeats/hido-claude-kit

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.

agentmods badge for auto-team

README.md
[![agentmods](https://agentmods.dev/badge/skills/hidobeats/hido-claude-kit/auto-team/github.svg)](https://agentmods.dev/skills/hidobeats/hido-claude-kit/auto-team)
Your own site
<a href="https://agentmods.dev/skills/hidobeats/hido-claude-kit/auto-team"><img src="https://agentmods.dev/badge/skills/hidobeats/hido-claude-kit/auto-team/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 auto-team

Your own site · 80×15
<a href="https://agentmods.dev/skills/hidobeats/hido-claude-kit/auto-team"><img src="https://agentmods.dev/badge/skills/hidobeats/hido-claude-kit/auto-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,647 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 $0.01647
Opus 5.5 $0.00010 $0.00659
Sonnet 5.5 $0.00005 $0.00329
Haiku 4.5 $0.00003 $0.00165

Measured 2mo ago against content hash 8d4bbebf16fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto-team 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 2mo 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.

skills/auto-team/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Team

Orchestrate parallel agent work using native TeamCreate, TaskCreate, and Agent tools with worktree isolation. Each teammate works in an isolated git worktree; results merge into an integration branch.

When to Use

ALL must be true:

  • 3+ independent parts that can run in parallel
  • Parts touch different files/modules (no shared-file edits)
  • Task would take >30 min sequentially

Do NOT use when:

  • Single file edit, small bug fix, simple feature
  • Parts depend on each other sequentially
  • User explicitly wants single-session work
  • Dirty working tree (commit or stash first)
digraph decision {
  "3+ independent parts?" [shape=diamond];
  "Touch different files?" [shape=diamond];
  ">30 min sequential?" [shape=diamond];
  "Use auto-team" [shape=box];
  "Use single session" [shape=box];

  "3+ independent parts?" -> "Touch different files?" [label="yes"];
  "3+ independent parts?" -> "Use single session" [label="no"];
  "Touch different files?" -> ">30 min sequential?" [label="yes"];
  "Touch different files?" -> "Use single session" [label="no"];
  ">30 min sequential?" -> "Use auto-team" [label="yes"];
  ">30 min sequential?" -> "Use single session" [label="no"];
}

Workflow

Phase 0: Preflight (NEVER skip)

git rev-parse --git-dir        # Must be a git repo
git status --porcelain          # Must be clean — if dirty, ask user to commit/stash
git branch --show-current       # Record as ORIGINAL_BRANCH for rollback
git worktree list               # Check no conflicts

Stop and inform user if any check fails.

Phase 1: Plan & Approve

Present plan to user, wait for confirmation:

I'll split this into [N] parallel tasks:

1. [task] -> feature/[name] (opus — complex logic)
2. [task] -> feature/[name] (sonnet — implementation)
3. [task] -> feature/[name] (sonnet — tests)

Integration branch: feature/integration-[project]
Cost: ~[N]x single session tokens

Proceed?

3-4 teammates max for cost efficiency.

Phase 2: Create Integration Branch

Read the full file on GitHub · 236 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.

  1. 2mo ago First seen · 236 lines · 26 tokens per session scan A 8d4bbebf16fe

Subscribe to this mod's changes

auto-team is a skill published in the GitHub repository hidobeats/hido-claude-kit (2 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 1,647 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 2026-08-31.

Related

auto-team compared with skills from other repositories

auto-team next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
auto-teamhidobeats/hido-claude-kitSkill27mo agoMITA26Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex