subagent-handoff

Enforces user-observable verification and reporting formats for dispatched subagents.

2|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/jonaseck2/slaktforskning --skill subagent-handoff
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-handoff
Source: https://github.com/jonaseck2/slaktforskning/tree/main/.claude/skills/subagent-handoff
Command: npx skills add https://github.com/jonaseck2/slaktforskning --skill subagent-handoff

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents subagent work from being marked complete when it does not actually move toward the plan’s user-observable outcome, even if it looks spec-correct or “tests pass.”

Core Features & Use Cases

  • User-goal-first prompting: Forces every subagent prompt to start from the plan’s User goal and to stop/escalate if the task fails that goal.
  • Verification-before-done: Requires the dispatcher to perform explicit user-observable checks (UI/MCP/file/gazetteer resolution) before marking tasks done.
  • Consistent reviewer/implementer reporting: Standardizes reports into three required answers to reduce omission and optimism.
  • Git worktree guardrails: Mandates rebase + branch verification to avoid CWD drift and accidental commits to the wrong branch.
  • Project-local MCP/tool alignment: Ensures outcome checks match the project’s built-in MCP + genealogy-research context.

Quick Start

Use the subagent-handoff skill templates to dispatch implementer, spec-reviewer, and code-quality-reviewer subagents for a task, then run an explicit user-observable verification step before marking the task done.

Frequently Asked Questions about subagent-handoff

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I ensure dispatched subagents actually meet user goals instead of just passing tests?

To ensure dispatched subagents meet user goals, enforce user-observable verification before marking tasks done. This requires prompts to start from the plan's user goal and explicit checks like UI or file resolution, preventing false completion when tests pass but outcomes fail.

What is the best way to standardize reporting for spec-reviewer and implementer subagents?

Standardize subagent reporting by mandating three required answers in every dispatch flow. This consistent reviewer and implementer reporting format reduces omission and optimism, ensuring code review and spec compliance checks are verifiable.

Can I use git worktrees to avoid CWD drift during subagent dispatch workflows?

Git worktrees are used to avoid CWD drift during subagent dispatch workflows. The skill mandates strict worktree discipline with rebase and branch verification, preventing accidental commits to the wrong branch.

Why does my subagent task pass spec compliance but fail the user-observable outcome?

Subagent tasks pass spec compliance but fail user-observable outcomes when verification lacks explicit UI or file checks. The skill solves this by requiring dispatcher verification gates that check user goals before marking tasks complete.

Do I need project-local prompt templates to verify user goals in dispatcher workflows?

Project-local prompt templates are required to verify user goals in dispatcher workflows. They force every subagent prompt to start from the plan's user goal and align outcome checks with the project's built-in MCP and genealogy-research context.