Team composition patterns — build the right agent team
Sizing heuristics, preset teams (review, debug, feature, security), agent-type selection and display modes for Claude Code's Agent Teams
- What
- Sizing heuristics, preset teams (review, debug, feature, security), agent-type selection and display modes for Claude Code's Agent Teams
- Cost
- Free
- Needs
- Claude Code with the Agent Teams feature (for the subagent_type and teammateMode mechanics); no accounts or API keys needed.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a multi-agent playbook by @wshobson for composing agent teams in Claude Code's Agent Teams feature: team-sizing heuristics by complexity (1–2 for simple up to 4–5 for very complex, with "start with the smallest team that covers all dimensions"), seven preset compositions (Review, Debug, Feature, Fullstack, Research, Security, Migration teams) with sizes, agent roles, and when-to-use triggers, an agent-type selection table (general-purpose vs read-only Explore/Plan vs specialized team-reviewer/debugger/implementer/lead with their tool sets), display-mode configuration (tmux, iTerm2, in-process for CI), custom-team guidelines, and a troubleshooting section covering the classic failure modes (read-only agents assigned writes, oversized teams, duplicate review dimensions, teammates not receiving tasks). Honest caveats: the mechanics (subagent_type, teammateMode, the team-* agent roles) are specific to Claude Code's Agent Teams — the heuristics and presets transfer, the configuration syntax does not; coordination overhead grows fast past 4–5 teammates. Credit to its creator. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Team Composition Patterns is a free Muse skill, a playbook for composing agent teams for Agent Teams. It gives team-sizing heuristics by complexity, from one to two for simple work up to four to five for very complex work, with seven preset compositions, starting with the smallest team that covers all dimensions.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 46891e7Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: Claude Code with the Agent Teams feature (for the subagent_type and teammateMode mechanics); no accounts or API keys needed. Install "Team composition patterns — build the right agent team" for me. It's a multi-agent playbook: team-sizing heuristics, seven preset compositions (review, debug, feature, fullstack, research, security, migration), agent-type selection by tool needs, display modes (tmux/iTerm2/in-process), and troubleshooting for classic multi-agent failure modes. Repository: https://raw.githubusercontent.com/wshobson/agents/46891e7e60da0e52baf1050b7b6391b64e84c6d9/plugins/agent-teams/skills/team-composition-patterns/SKILL.md Pinned version: install the code at commit 46891e7e60da0e52baf1050b7b6391b64e84c6d9 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "team-composition-patterns". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. save my API key in the vault). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 46891e7 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: files.pythonhosted.org, pypi.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.