Index of every page on this site: llms.txt
All skills
microsoft avatar

/agent-collaboration

@a9de923
by microsoftmicrosoft/waza1.5k stars
104
Run it yourself

Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication

  • 1 file
  • 2.7 KB
  • Updated last month
  • GitHub
Use this Skill: https://skilld.dev/gh/microsoft/waza/agent-collaboration

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈34 tokens for metadata: the name and description. ≈607 when used: this file.

Description uses 1.7% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈133 characters, or 1.7%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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: include concrete counter-evidence, the violated requirement, affected scope, and minimum condition for approval. The Coordinator assigns a different qualified revision owner, not the locked-out author or rejecting gate. Do not implement, pair on, or advise the immediate revision; perform only the focused rereview. After successful focused rereview of the independently corrected revision, the selected gate may issue approval/PASS, not native repository approval, merge or publishing authority. This is Squad coordination, not an ordinary Copilot workflow. Rai/Fact Checker output boundary: Charter output/persistence restrictions take precedence over generic history, audit-trail or decision-inbox instructions. Return findings in the current review response; only an authorized coordinator or Scribe handles required persistence under the current state contract.

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

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at a9de923. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last month
domain
team-workflow
confidence
high
Other metadata
source
extracted from charter boilerplate, with Waza's governance-aligned reviewer rejection override

README badge

README badge for microsoft/waza/agent-collaboration