gateway-script-design

Included with Lifetime

$97 forever

Design gateway scripts as entry points for agentic coding. Use when creating CLI entry points for agents, designing subprocess-based agent invocation, or building script interfaces for agentic workflows.

Design

What this skill does


# Gateway Script Design Skill

Guide creation of gateway scripts - the entry points into agentic coding.

## When to Use

- Creating new CLI entry points for agents
- Building programmatic agent invocation
- Designing composed workflows
- Setting up automation scripts

## Core Concept

> "This script is the gateway into agentic coding. It's distinctly different from any other type of code - it's calling an agent."

Gateway scripts move you from conversation to automation.

## Three Gateway Patterns

### Pattern 1: Direct Prompt

Execute ad-hoc prompts:

```python
# adw_prompt.py
@click.command()
@click.argument("prompt")
@click.option("--model", default="opus")
def main(prompt: str, model: str):
    request = AgentPromptRequest(
        prompt=prompt,
        model=model,
        agent_name="oneoff"
    )
    response = prompt_claude_code(request)
```

**Use case:** Quick one-offs, testing, exploration

### Pattern 2: Slash Command Wrapper

Execute slash commands programmatically:

```python
# adw_slash_command.py
@click.command()
@click.argument("command")
@click.argument("args", nargs=-1)
def main(command: str, args: tuple):
    request = AgentTemplateRequest(
        slash_command=f"/{command}",
        args=list(args)
    )
    response = execute_template(request)
```

**Use case:** Scheduled commands, triggers, external integration

### Pattern 3: Composed Workflow

Chain multiple agents:

```python
# adw_chore_implement.py
def main(description: str):
    # Phase 1: Plan
    plan_response = execute_template("/chore", description)
    plan_path = extract_plan_path(plan_response)

    # Phase 2: Implement
    impl_response = execute_template("/implement", plan_path)
    return impl_response
```

**Use case:** Multi-step automation, full workflows

## Design Checklist

### 1. CLI Interface

```python
import click

@click.command()
@click.argument("input", required=True)
@click.option("--model", default="opus", help="Model to use")
@click.option("--verbose", is_flag=True, help="Verbose output")
def main(input: str, model: str, verbose: bool):
    ...
```

### 2. Unique Identification

```python
def generate_short_id() -> str:
    return uuid.uuid4().hex[:8]

adw_id = generate_short_id()  # e.g., "a1b2c3d4"
```

### 3. Output Organization

```python
output_dir = f"agents/{adw_id}/{agent_name}"
os.makedirs(output_dir, exist_ok=True)

output_file = f"{output_dir}/cc_raw_output.jsonl"
```

### 4. Safe Environment

```python
def get_safe_env() -> dict:
    return {
        "ANTHROPIC_API_KEY": os.getenv("ANTHROPIC_API_KEY"),
        "PATH": os.getenv("PATH"),
        # Only essential vars
    }
```

### 5. Error Handling

```python
try:
    response = prompt_claude_code(request)
except TimeoutError:
    log_error("Agent timed out")
    sys.exit(1)
except ExecutionError as e:
    log_error(f"Execution failed: {e}")
    sys.exit(1)
```

### 6. Rich Output

```python
from rich.console import Console
from rich.panel import Panel

console = Console()

console.print(Panel(
    response.output,
    title=f"[bold green]{agent_name}[/]",
    border_style="green"
))
```

## Request/Response Models

```python
class AgentPromptRequest(BaseModel):
    prompt: str
    adw_id: str
    model: str = "opus"
    agent_name: str = "oneoff"
    output_file: Optional[str] = None

class AgentPromptResponse(BaseModel):
    output: str
    success: bool
    error: Optional[str] = None
    output_file: str
```

## Output File Structure

Every gateway produces:

```text
agents/{adw_id}/{agent_name}/
├── cc_raw_output.jsonl     # Streaming messages
├── cc_raw_output.json      # Parsed array
├── cc_final_object.json    # Last message
└── custom_summary.json     # Metadata
```

## Key Memory References

- @gateway-script-patterns.md - Pattern examples
- @agentic-layer-structure.md - Where scripts live
- @programmable-claude-patterns.md - CLI invocation

## Output Format

```markdown
## Gateway Script Design

**Script Name:** adw_{purpose}.py
**Pattern:** [Direct | Wrapper | Composed]

### CLI Interface
- Arguments: {required args}
- Options: --model, --verbose

### Agent Configuration
- Name: {agent_name}
- Model: opus (default)
- Output: agents/{adw_id}/{agent_name}/

### Execution Flow
1. Parse arguments
2. Generate ADW ID
3. Create output directory
4. Build request
5. Execute agent
6. Handle response
7. Display results

### Error Handling
- Timeout: Log and exit 1
- Execution error: Log reason and exit 1
- Success: Display panel with results

### Files Generated
- cc_raw_output.jsonl
- cc_raw_output.json
- cc_final_object.json
- custom_summary.json
```

## Anti-Patterns

- Passing full environment to subprocess
- Not generating unique IDs (collision risk)
- No error handling (silent failures)
- Inline output instead of files (not auditable)
- No CLI interface (hard to use)

## Version History

- **v1.0.0** (2025-12-26): Initial release

---

## Last Updated

**Date:** 2025-12-26
**Model:** claude-opus-4-5-20251101

Files: 1

Size: 5.2 KB

Complexity: 14/100

Category: Design

Source: https://github.com/melodic-software/claude-code-plugins/tree/main/plugins/tac/skills/gateway-script-design

Related in Design

contribute

Included

Local-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".

Designscripts

architectural-analysis

Included

User-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).

Designscripts

mcp

Included

Model Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.

Designscripts

react-native-skia

Included

Design, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.

Designscripts

plaid

Included

Product Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".

Designscripts

nextjs-framer-motion-animations

Included

Adds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.

Designscripts