Skip to content

Open source · MIT

agent-team

A Claude Code plugin that seats a team of AI roles in a project: a CEO, an Engineering lead, a Bar Raiser and whichever other seats the repo calls for, each with its own rulebook, its own workers on the right model, and a clear line on what it decides. A re-evaluation measures how each seat actually works and proposes changes.

Role
Creator · Solo build · MIT OSS
Period
Oct 2026 – present
Stack
Python (standard library) · Claude Code plugin · Agent Skills · GitHub Actions · and 1 more
Place
Remote · runs in any repository

MITOpen source

01 / 01

What I built

  • A team sized from evidence. The scan reads manifests, file names, CI, deploy configs and git history, and each proposed seat cites what raised it.
  • A measured re-evaluation loop. It reports each seat's activity over the last 30 days and what changed in the repo, then proposes changes. What the owner declines is remembered.
  • Seats that check each other. Work goes to a Bar Raiser for review, and seats exchange ASK, HANDOFF and RESULT messages instead of free-form chat.
  • Model tiers per seat. Typing goes to cheap, fast models and judgement to strong ones, steered from above.
  • Checked on every push. GitHub Actions runs the rulebook checks and seats a fresh project with the scaffold on Python 3.9 and 3.12; unit tests run on repo fixtures.
  • Runs my own builds. It seats the teams behind my private products, so every rule is tested on real work first.

Technical highlights

  • 01

    Python standard library only: no dependencies to install.

  • 02

    Releases follow semantic versioning, with every release listed in CHANGELOG.md.

  • 03

    Installs as a Claude Code plugin from its own marketplace, or by linking the skills from a clone.

  • 04

    Runs on Windows as well as macOS and Linux, since 1.3.1.

Outcomes

By the numbers.

3.9 + 3.12
Python versions CI runs on
3 teams
Offered per repo: lean, recommended, full
Visit project

See it in the wild.

This case study covers how agent-team was built — these links open what ships today: the live product, repo, demos, and supporting material.

Recent activity

The changelog.

October 2026
Oct 2026
released:agent-team · v1.3.1 — 1.3.1
GitHub ↗
Oct 2026
released:agent-team · v1.3.0 — seat an AI team in any project10 commits · Oct 2026
GitHub ↗
↗ Next case study

Wiregent

Wiregent frees disk space on Windows across C:, WSL and Docker, in one place. It works fully without AI. An optional advisor reads the scan, explains it and proposes what to clean, using a Claude subscription, a local AI server or an API key. Nothing is deleted until a person ticks it and presses Clean.