Parallel Agent Contracts
- 460 installs
- 3.9k repo stars
- Updated January 26, 2026
- parcadei/continuous-claude-v3
parallel-agent-contracts is a Claude Code skill that defines mandatory prompt contracts so parallel coding agents avoid duplicate TypeScript types and pass npx tsc --noEmit checks.
About
parallel-agent-contracts is an orchestration skill from parcadei/continuous-claude-v3 for launching multiple Claude agents on shared TypeScript codebases without type duplication. Every agent prompt must include a verification step running npx tsc --noEmit and a grep-before-create rule that searches src/ for existing interface or type aliases before defining new ones. Developers reach for parallel-agent-contracts when splitting implementation across parallel agents and seeing repeated types, import conflicts, or type errors after concurrent edits. The skill is user-invocable false and encodes copy-paste markdown blocks agents embed directly into worker prompts.
- Enables parallel execution of multiple specialized agents
- Defines explicit contracts between agents for reliable handoff
- Reduces total tokens and wall-clock time on complex tasks
- Works with Continuous Claude v3 orchestration patterns
- Supports agentic workflows that require concurrent research, coding, and review
Parallel Agent Contracts by the numbers
- 460 all-time installs (skills.sh)
- +2 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #1,873 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill parallel-agent-contractsAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 460 |
|---|---|
| repo stars | ★ 3.9k |
| Last updated | January 26, 2026 |
| Repository | parcadei/continuous-claude-v3 ↗ |
How do parallel coding agents avoid duplicate TypeScript types?
Run multiple Claude agents in parallel with clear contracts so they collaborate without stepping on each other.
Who is it for?
Teams running multiple Claude or Cursor implementation agents on one TypeScript monorepo who keep hitting duplicate interfaces and type-check failures after parallel edits.
Skip if: Single-agent workflows, non-TypeScript codebases, or projects that do not use shared src/ type definitions.
When should I use this skill?
Launching two or more parallel implementation agents that may create interfaces, types, or shared modules in the same repository.
What you get
Standardized agent prompt sections with tsc verification steps and grep-before-create import rules
- Agent prompt contract blocks
- Verification command snippets
Files
Parallel Agent Type Contracts
When launching parallel agents for code implementation, prevent type duplication.
Required in Every Agent Prompt
1. Verification Command (MANDATORY)
## 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
## 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:
# 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
1. Type checker is the contract - tsc catches conflicts automatically 2. Grep is fast - 1 second to check if type exists 3. Explicit ownership - No ambiguity about where types live 4. Fail fast - Agent can't claim "done" with broken types
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Pick parallel-agent-contracts over generic multi-agent tips when parallel TypeScript workers need enforced tsc gates and grep-before-create rules, not just task splitting.
FAQ
What verification must parallel agents run per parallel-agent-contracts?
parallel-agent-contracts requires every agent to run npx tsc --noEmit and fix any reported type errors before marking a task complete, typically piping output through head -20 for quick inspection.
How does parallel-agent-contracts stop duplicate interfaces?
parallel-agent-contracts forces agents to grep src/ for existing interface or type names and import them instead of redefining duplicates, embedding that rule as a mandatory section in each parallel worker prompt.