Back to Skills

agent-handoff-markers

verified

Standardized inline markers for inter-agent communication. Use when creating handoff annotations for other agents, scanning for pending work from upstream agents, or when the user mentions handoff markers, agent coordination, or cross-agent communication.

View on GitHub

Marketplace

laurigates-plugins

laurigates/claude-plugins

Plugin

agent-patterns-plugin

ai

Repository

laurigates/claude-plugins
3stars

agent-patterns-plugin/skills/agent-handoff-markers/SKILL.md

Last Verified

January 24, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/laurigates/claude-plugins/blob/main/agent-patterns-plugin/skills/agent-handoff-markers/SKILL.md -a claude-code --skill agent-handoff-markers

Installation paths:

Claude
.claude/skills/agent-handoff-markers/
Powered by add-skill CLI

Instructions

# Agent Handoff Markers

Structured inline markers for asynchronous agent-to-agent communication.

## Benefits

### Asynchronous Agent Coordination
- Agents can request work from other agents without blocking
- Work can be discovered and processed in future sessions
- Enables non-linear development workflows

### Traceability
- Clear audit trail of inter-agent requests
- Completion markers show what was delivered
- Referenced files provide full context

### Reduced Context Switching
- Agents can complete their current work before handling handoffs
- Markers persist until addressed
- No need for immediate handoff processing

### Improved Code Documentation
- Markers serve as inline documentation of intent
- Requirements are captured at the point of need
- Context is preserved alongside the code

### Workflow Flexibility
- Any agent can create markers for any other agent
- Priority levels allow triage
- Type categorization enables filtering

### CI/CD Integration Potential
- Markers can be scanned in pre-commit hooks
- Blocking markers could fail builds if unaddressed
- Automated reports of pending work

## Core Concept

Handoff markers are structured comments in code that:
1. Request work from a specific agent
2. Provide context for the receiving agent
3. Define requirements and constraints
4. Track completion status

## Marker Format

### Basic Structure

```typescript
// @AGENT-HANDOFF-MARKER(target-agent) {
//   type: "category",
//   context: "what this code does",
//   needs: ["requirement 1", "requirement 2"],
//   priority: "blocking|enhancement",
//   refs: ["path/to/related/file"]
// }
```

### Full Example

```typescript
// @AGENT-HANDOFF-MARKER(ux-implementation) {
//   type: "form-validation",
//   context: "User registration form with email/password",
//   needs: [
//     "error message placement strategy",
//     "focus management on validation failure",
//     "ARIA live region for error announcements",
//     "inline vs summary validation decision"
//

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
10990 chars