hana-developer-cli-tool-example automation-script-development.instructions.md

Coding guidelines for Node.js automation scripts stored in a project's scripts/ folder. They cover scripts that generate, update, enhance, or fill files from templates.

In plain words
What is it for?
Use them when building documentation generators, example-file generators, changelog converters, metadata extractors, template fillers, or scripts that update existing content.
Why use it?
They reduce inconsistent file handling, missing metadata, weak error reporting, and undocumented scripts. They also help scripts fit the project's npm commands.

Instructions file for GitHub Copilot

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/sap-samples/hana-developer-cli-tool-example/automation-script-development
Clone the repo
git clone --depth 1 https://github.com/SAP-samples/hana-developer-cli-tool-example

Made for: GitHub Copilot.

Per session 4,780 This file is loaded in full into every session.
When invoked 4,780 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.04780 $0.04780
Opus 5 $0.02390 $0.02390
Sonnet 5 $0.00956 $0.00956
Haiku 4.5 $0.00478 $0.00478

Measured 2d ago against content hash 03a92b3164a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hana-developer-cli-tool-example automation-script-development.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/instructions/automation-script-development.instructions.md · 780 lines

How it starts

The opening of the file, as written. The whole thing — 780 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automation Script Development Guidelines

Use this guide when creating or modifying automation scripts in the scripts/ folder.

Scope and Purpose

This guide applies to automation and code generation scripts in the scripts/ folder:

Script Categories:

  • scripts/generate-*.js - Generate new files (docs, config, examples)
  • scripts/enhance-*.js - Enhance existing files with extracted metadata
  • scripts/update-*.js - Update existing files with new content
  • scripts/populate-*.js - Populate templates with data
  • scripts/CHANGELOG.js - Generate changelog from JSON

Common Scripts:

  • scripts/generate-command-docs.js - Generate command documentation
  • scripts/generate-sidebar-config.js - Generate VitePress sidebar config
  • scripts/generate-examples.js - Generate example files
  • scripts/enhance-command-docs.js - Enhance docs with metadata from source
  • scripts/update-epilogues.js - Update command epilogues
  • scripts/populate-command-docs.js - Populate doc templates
  • scripts/CHANGELOG.js - Convert CHANGELOG.json to markdown

Critical Principles

  1. Shebang: Start with #!/usr/bin/env node for direct execution
  2. ESM Modules: Use ES module syntax (import/export)
  3. Type Safety: Add @ts-check for basic type checking
  4. Safe File I/O: Check existence before reading, backup before overwriting
  5. Clear Logging: Provide progress updates and success/failure messages
  6. Exit Codes: Use proper exit codes (0=success, 1=failure)
  7. Idempotency: Scripts should be safe to run multiple times
  8. Documentation: Include JSDoc header explaining purpose

File Structure Template

#!/usr/bin/env node
/**
 * Brief description of what this script does
 * 
 * Usage: node script-name.js [options]
 * 
 * Examples:
 *   node script-name.js
 *   node script-name.js --force
 */

import fs from 'fs'
import path from 'path'

// Node 20.11+: import.meta.dirname / import.meta.filename
const __dirname = import.meta.dirname

// Constants
const SOURCE_DIR = path.join(__dirname, 'source')
const OUTPUT_DIR = path.join(__dirname, 'output')

/**
 * Main execution function
 */
async function main() {
    try {
        console.log('Starting script...')
        
        // Script logic here
        
        console.log('✅ Script completed successfully')
        process.exit(0)
    } catch (error) {
        console.error('❌ Script failed:', error.message)
        console.error(error.stack)
        process.exit(1)
    }
}

main()

Read the full file on GitHub · 780 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 780 lines · 4,780 tokens per session scan A 03a92b3164a1

Subscribe to this mod's changes

hana-developer-cli-tool-example automation-script-development.instructions.md is an instructions file published in the GitHub repository SAP-samples/hana-developer-cli-tool-example (109 stars, last pushed 7d ago), licensed Apache-2.0. It adds 4,780 tokens to every session, about $0.0239 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.