parallel-agent-contracts
🎯Skillfrom parcadei/continuous-claude-v3
|parallel-agent-contracts skill from parcadei/continuous-claude-v3
Installation
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill parallel-agent-contractsSkill Details
Parallel Agent Type Contracts
Overview
# Parallel Agent Type Contracts
When launching parallel agents for code implementation, prevent type duplication.
Required in Every Agent Prompt
1. Verification Command (MANDATORY)
```markdown
Before Marking Complete
Run verification:
\\\`bash
npx tsc --noEmit 2>&1 | head -20
\\\`
If ANY type errors exist, fix them before completing.
```
2. Grep-Before-Create
```markdown
Before Creating Any Type/Interface
First check if it exists:
\\\`bash
grep -r "interface YourTypeName\|type YourTypeName" src/
\\\`
If found, import it. NEVER duplicate existing types.
```
3. Canonical Type Map
Include relevant entries from this map in agent prompts:
| Type | Owner File | Import From |
|------|-----------|-------------|
| NormalizedTool | src/sdk/agent.ts | './agent' |
| ToolCall | src/sdk/agent.ts | './agent' |
| ToolResult | src/sdk/agent.ts | './agent' |
| ToolDefinition | src/sdk/agent.ts | './agent' |
| Message | src/sdk/types.ts | './types' |
| ContentBlock | src/sdk/types.ts | './types' |
| TokenUsage | src/sdk/types.ts | './types' |
| ProviderAdapter | src/sdk/providers/index.ts | './providers' |
| RiggClient | src/sdk/client.ts | './client' |
Prompt Template
When spawning implementation agents:
```markdown
# Task: [Description]
Type Ownership (DO NOT recreate)
- [List relevant types from canonical map]
Before Creating New Types
Run: grep -r "interface TypeName" src/ - if exists, import it.
Before Marking Complete
Run: npx tsc --noEmit 2>&1 | head -20
Fix all type errors before completing.
Your Implementation
[Actual task description]
```
Why This Works
- Type checker is the contract - tsc catches conflicts automatically
- Grep is fast - 1 second to check if type exists
- Explicit ownership - No ambiguity about where types live
- Fail fast - Agent can't claim "done" with broken types
More from this repository10
Enables seamless integration between Agentica agents and Claude Code CLI by managing proxy configurations, tool permissions, and response formatting.
Manages git commits by removing Claude attribution, generating reasoning documentation, and ensuring clean commit workflows.
Systematically diagnose and resolve hook registration, execution, and output issues in Claude Code projects by checking cache, settings, files, and manual testing.
Systematically researches, analyzes, plans, implements, and reviews migrations across frameworks, languages, and infrastructure with minimal risk.
Enables background agent execution with system-triggered progress notifications, avoiding manual polling and context flooding.
Provides comprehensive reference and infrastructure for building sophisticated multi-agent coordination patterns and workflows with precise API specifications and tracking mechanisms.
Generates a comprehensive summary of the current system's configuration, components, and key metrics across skills, agents, hooks, and other core systems.
Provides comprehensive CLI commands and flags for interacting with Claude Code, enabling headless mode, automation, and session management.
Traces and correlates Claude Code session events across parent and sub-agent interactions using comprehensive Braintrust instrumentation.
Rapidly edits files using AI-powered Morph Apply API with high accuracy and speed, without requiring full file context.