Multi-agent team and swarm workflow for DeepSeek Harness using bounded subagents, parallel workflows, disjoint ownership, and independent review.
Scanned 9/6/2026
Install to Claude Code
Skills Directorynpx -y skills add wellorbetter/dsh-product-delivery-workflow --skill agent-team --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Agent Team?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/wellorbetter-agent-team)More formats (shields.io, HTML) on the badges page.
---
name: agent-team
description: Multi-agent team and swarm workflow for DeepSeek Harness using bounded subagents, parallel workflows, disjoint ownership, and independent review.
user-invocable: true
---
# Agent Team
Use DSH `subagent`, `subagent_fork`, and `workflow` to coordinate parallel work when delegation is explicitly requested or required by an active workflow.
Define the objective and independent workstreams. Keep the immediate blocking task local. Delegate only concrete, self-contained work with exact file ownership, inputs, outputs, acceptance checks, and prohibited actions. Tell workers they share the workspace and must not revert other edits. Use explorers for read-only investigation, workers for bounded implementation, reviewers for independent verification, and the parent agent as integrator. Do not duplicate work. Prefer fewer strong agents. Integrate results and validate the combined state.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
