New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Squad Agent Collaboration Patterns

by microsoft in microsoft/waza

Shared collaboration rules for a team of squad agents covering worktree awareness, writing decisions to an inbox, cross-agent requests and reviewer lockout.

OfficialMITAuto-check passedAgent Workflows

Install Squad Agent Collaboration Patterns

skills CLI
$ npx skills add microsoft/waza --skill agent-collaboration -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install microsoft/waza agent-collaboration --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/microsoft/waza.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.copilot/skills/agent-collaboration .claude/skills/agent-collaboration && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-collaboration
GitHub stars
1.4k
Used in
4 other repos
Token cost
~500 tokens
SKILL.md length
225 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
MIT

At a glance

Shared collaboration rules for a team of squad agents covering worktree awareness, writing decisions to an inbox, cross-agent requests and reviewer lockout.

  • Recording a decision that affects other agents on a squad
  • SKILL.md covers Context, Patterns and Anti-Patterns
  • Calls git
  • Asking for another agent's input without leaving your own domain

What it does

Instead of repeating the same collaboration section in every agent charter, this skill keeps it in one place. Agents find the team root from their spawn prompt, fall back to git rev-parse --show-toplevel, and never assume the working directory is the repo root. A decision that affects teammates is written as a small file in .squad/decisions/inbox/, named after the agent and a short slug, with a date, title, author and what was decided.

When an agent needs another member's input, it says so in its response and the coordinator brings that member in, rather than doing work outside its own domain. If a reviewer rejects work, the original author is locked out of revising that artifact and a different agent must take over. Listed anti-patterns include reading every agent charter, writing straight to .squad/decisions.md and editing other agents' history.md files, which are Scribe's job.

When your agent uses it

  • Recording a decision that affects other agents on a squad
  • Asking for another agent's input without leaving your own domain
  • Working in a git worktree where the current directory is not the repo root
  • Handing a rejected artifact to a different agent for revision

Example prompts

  • “Record the decision to switch to the new API client where the other squad agents will see it.”
  • “I need input from the database agent. How should I ask for it?”
  • “My review was rejected. Who should revise the artifact, and how do I say so?”

Requirements

  • A squad setup with a .squad directory

What it can do on your machine

Read from SKILL.md and the folder at commit 774df00. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Squad Agent Collaboration Patterns loads about 500 tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 225 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~500

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from microsoft/waza at commit 774df00, republished under its MIT licence (© microsoft). 225 words, ~500 tokens.

Download SKILL.mdSave it as .claude/skills/agent-collaboration/SKILL.md (or your agent's skills folder).
name
agent-collaboration
description
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
domain
team-workflow
confidence
high
source
extracted from charter boilerplate — identical content in 18+ agent charters

Context

Every agent on the team follows identical collaboration patterns for worktree awareness, decision recording, and cross-agent communication. These were previously duplicated in every charter's Collaboration section (~300 bytes × 18 agents = ~5.4KB of redundant context). Now centralized here.

The coordinator's spawn prompt already instructs agents to read decisions.md and their history.md. This skill adds the patterns for WRITING decisions and requesting help.

Patterns

Worktree Awareness

Use the TEAM ROOT path provided in your spawn prompt. All .squad/ paths are relative to this root. If TEAM ROOT is not provided (rare), run git rev-parse --show-toplevel as fallback. Never assume CWD is the repo root.

Decision Recording

After making a decision that affects other team members, write it to: .squad/decisions/inbox/{your-name}-{brief-slug}.md

Format:

### {date}: {decision title}
**By:** {Your Name}
**What:** {the decision}
**Why:** {rationale}
Cross-Agent Communication

If you need another team member's input, say so in your response. The coordinator will bring them in. Don't try to do work outside your domain.

Reviewer Protocol

If you have reviewer authority and reject work: the original author is locked out from revising that artifact. A different agent must own the revision. State who should revise in your rejection response.

Anti-Patterns

  • Don't read all agent charters — you only need your own context + decisions.md
  • Don't write directly to .squad/decisions.md — always use the inbox drop-box
  • Don't modify other agents' history.md files — that's Scribe's job
  • Don't assume CWD is the repo root — always use TEAM ROOT

© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .copilot/skills/agent-collaboration of microsoft/waza.

Open the folder on GitHubat commit 774df00

Used in 4 other repositories

We found 5 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 4 other GitHub owners. This page covers the copy in microsoft/waza, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Squad Agent Collaboration Patterns next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Squad Agent Collaboration Patterns compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Squad Agent Collaboration Patterns this skillmicrosoft/waza1.4k4 repos~500Automated safety check: PassMIT
Agtx Task Sweepfynnfluegge/agtx1.7k—~1.7kAutomated safety check: PassApache-2.0
PRP Workstream OrchestratorWirasm/prp2.3k—~3.5kAutomated safety check: PassMIT
aweb Team Coordinationawebai/aweb115—~4kAutomated safety check: PassMIT
Qwen Code Team CoordinatorQwenLM/qwen-code28k—~994Automated safety check: PassApache-2.0
Agenthubalirezarezvani/claude-skills28k—~2kAutomated safety check: PassMIT

Similar skills

  • Agtx Task Sweep

    fynnfluegge/agtx

    Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session.

    1.7k GitHub stars~1.7k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed

  • PRP Workstream Orchestrator

    Wirasm/prp

    Coordinates several PRP workstreams in isolated Git worktrees from one session, verifying proof, holding merge gates and sequencing the merges.

    2.3k GitHub stars~3.5k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed

  • aweb Team Coordination

    awebai/aweb

    Guides decisions for agents working in an aweb team: when to check shared state, claim tasks, take locks, read team roles and instructions, and open separate worktrees.

    115 GitHub stars~4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Qwen Code Team Coordinator

    QwenLM/qwen-code

    Leads a small team of Qwen Code teammates: read-only investigators work in parallel, then one writer pinned to a git worktree makes the changes.

    28k GitHub stars~994 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Agenthub

    alirezarezvani/claude-skills

    Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation.

    28k GitHub stars~2k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • ClawTeam Multi-Agent Swarm

    win4r/ClawTeam-OpenClaw

    Launches a swarm of specialist Hermes agents in git-worktree-isolated tmux windows with a kanban board and file-based inboxes, using built-in templates like hedge-fund and code-review.

    1.5k GitHub starsUsed in 1 repo~2.9k tokens
    Agent WorkflowsAuto-check passed

More from microsoft/waza

All 16 skills in this repo

  • Squad Commands Menu

    microsoft/waza

    Official

    Shows a categorized, interactive menu of common Squad operations, such as install, upgrade and team management, and collects arguments before running anything.

    1.4k GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check passed

  • waza azd Extension Publisher

    microsoft/waza

    Official

    Walks through releasing a new version of the waza azd extension: changelog from commits, semver bump with your confirmation, and a release PR.

    1.4k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Squad Git Branching Workflow

    microsoft/waza

    Official

    Dev-first branching model for the Squad project: feature work branches from dev, issue branches follow a naming rule and parallel issues use git worktrees.

    1.4k GitHub starsUsed in 4 repos~1.5k tokens
    Auto-check passed

  • Waza Skill Evaluator

    microsoft/waza

    Official

    Evaluates agent skills with a Go CLI that runs YAML-defined benchmarks, compares runs and scores the quality of SKILL.md frontmatter.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • Reviewer Protocol

    microsoft/waza

    Official

    Reviewer rejection workflow and strict lockout semantics. An agent skill from microsoft/waza.

    1.4k GitHub starsUsed in 4 repos~1.1k tokens
    Auto-check passed

  • Waza Interactive

    microsoft/waza

    Official

    Walks you through creating, running and reading waza evals for an agent skill, then proposes concrete fixes when tasks fail or the score is low.

    1.4k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Squad Agent Collaboration Patterns

What does Squad Agent Collaboration Patterns do?

Shared collaboration rules for a team of squad agents covering worktree awareness, writing decisions to an inbox, cross-agent requests and reviewer lockout. Instead of repeating the same collaboration section in every agent charter, this skill keeps it in one place. Agents find the team root from their spawn prompt, fall back to git rev-parse --show-toplevel, and never assume the working directory is the repo root.

When should I use Squad Agent Collaboration Patterns?

Squad Agent Collaboration Patterns fits situations like: recording a decision that affects other agents on a squad; asking for another agent's input without leaving your own domain; working in a git worktree where the current directory is not the repo root; handing a rejected artifact to a different agent for revision.

How do I install Squad Agent Collaboration Patterns in Claude Code?

Run `npx skills add microsoft/waza --skill agent-collaboration -a claude-code`. Or copy the skill folder (.copilot/skills/agent-collaboration in microsoft/waza) into .claude/skills/agent-collaboration in your project. Claude Code loads it when a task matches its description.

How do I install Squad Agent Collaboration Patterns in Codex?

Run `npx skills add microsoft/waza --skill agent-collaboration -a codex`. Or copy the skill folder (.copilot/skills/agent-collaboration in microsoft/waza) into .agents/skills/agent-collaboration in your project. Codex loads it when a task matches its description.

Can I use Squad Agent Collaboration Patterns in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/waza --skill agent-collaboration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-collaboration, .gemini/skills/agent-collaboration, .github/skills/agent-collaboration and .opencode/skills/agent-collaboration in your project.

What does Squad Agent Collaboration Patterns need to run?

Going by SKILL.md and its folder, Squad Agent Collaboration Patterns needs the command-line tools its instructions call (git). Our summary lists: A squad setup with a .squad directory.

Does Squad Agent Collaboration Patterns access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Squad Agent Collaboration Patterns safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Squad Agent Collaboration Patterns use?

Squad Agent Collaboration Patterns is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Squad Agent Collaboration Patterns use?

About 500 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Squad Agent Collaboration Patterns?

Skills that share tags, products or a category with Squad Agent Collaboration Patterns: Agtx Task Sweep (fynnfluegge/agtx, 1.7k stars), PRP Workstream Orchestrator (Wirasm/prp, 2.3k stars), aweb Team Coordination (awebai/aweb, 115 stars) and Qwen Code Team Coordinator (QwenLM/qwen-code, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Squad Agent Collaboration Patterns?

microsoft (a GitHub organization, an official publisher) maintains it in microsoft/waza, which has 1,403 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 6, 2026.

Source: microsoft/waza on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.