---
title: "teamwork-kit"
description: "Six-skill Instruction Layer for governed coding agents. The plugin installs skills only. Enforcement Layer guards are separate and are not installed or activated."
canonical: https://agentpluginsdirectory.com/plugins/teamwork-kit
last-updated: 2026-09-18
---

# teamwork-kit
Six-skill Instruction Layer for governed coding agents. The plugin installs skills only. Enforcement Layer guards are separate and are not installed or activated.
- Slug: teamwork-kit
- Publisher: Ezra Israel
- Repository: https://github.com/Ezra144israel/governed-agent-skills
- Manifest: plugin.json
- Version: 4.2.1
- License: MIT
- Category (editorial): other
- Skills: 6 (better-coding, plans, ship-or-fix, teamwork, test-the-test, thinking)
- MCP servers: 0
- Stars: 0
- Listing: https://agentpluginsdirectory.com/plugins/teamwork-kit
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What teamwork-kit does, in the publisher's words

Instructions guide the work. Guards check what judgment should not decide.

Version 4 has two layers. The Instruction Layer is six skills that tell coding agents how to work. The Enforcement Layer is two standalone guards that check the parts that should not depend on judgment.

The layers work together, but they are installed separately. The plugin installs only the six skills. It does not install, wire, or activate either guard. Not every skill needs a guard. Add enforcement only where a rule can be checked mechanically and the cost of a miss matters.

- You tell an agent what you want (you = operator, it drafts the plan = orchestrator seat).
- A second agent, or just a fresh session of the first, attacks the plan before anything is built (pressure-test seat).

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/Ezra144israel/governed-agent-skills/HEAD/README.md

## Skills

- better-coding: Evaluate minimum-sufficient implementation routes and enforce the selected route for a fixed, authorized outcome. Use after outcome, scope, authority, and acceptance evidence are fixed. Do not choose outcomes, set acceptance, adjudicate governance, grade finished work, design tests alone, conduct s…
- plans: Use for planning, roadmaps, design, architecture, sequencing, or before consequential work when no current FINAL plan plus GO covers it. Fire before changes to data or schemas, credentials or auth, production or releases, repository or source-home boundaries, irreversible work, or materially costly…
- ship-or-fix: Oracle-frozen Builder and independent-Judge convergence cycle. Load ONLY when the operator explicitly sets Governance Dial G2 for the task, or explicitly names this skill or an active work unit already running it. Never auto-activate on task class, such as security, auth, or payments. If a task see…
- teamwork: Full governance constitution for work that touches shared state, requires independent review, spans seats, or involves planning, architecture, code, reviews, dispatches, status reports, or canonical records. Not needed for quick factual questions or trivial one-off answers.
- test-the-test: Requires behavioral, failure-path, and durable-seam evidence for tests and review. Use when writing tests, reviewing test coverage, assessing behavioral test quality, or accepting high-risk behavior on test evidence.
- thinking: The working method for every nontrivial task: frame the objective, ground load-bearing facts, converge on a route, execute without drift, and verify before delivery. Use for analysis, planning, implementation, debugging, document work, reviews, and multi-stage tasks.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.