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.
npx agentmods add instructions/sap-samples/hana-developer-cli-tool-example/utility-module-developmentgit clone --depth 1 https://github.com/SAP-samples/hana-developer-cli-tool-exampleWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03861 | $0.03861 |
| Opus 5 | $0.01930 | $0.01930 |
| Sonnet 5 | $0.00772 | $0.00772 |
| Haiku 4.5 | $0.00386 | $0.00386 |
Grade A, and why
hana-developer-cli-tool-example utility-module-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.
How it starts
The opening of the file, as written. The whole thing — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Utility Module Development Guidelines
Use this guide when creating or modifying JavaScript utility files in the utils/ directory (excluding utils/database/ which has separate instructions).
Scope and Purpose
This guide applies to shared utility modules in utils/ that provide common functionality across CLI commands, routes, and other components. Key modules include:
base.js/base-lite.js- Core functionality and database connectionsconnections.js- Connection parameter resolutionlocale.js- Locale detection and normalizationsqlInjection.js- SQL injection preventioncommandSuggestions.js- Command suggestion systemconfig-loader.js- Configuration file loadingmassConvert.js,massExport.js, etc. - Bulk operation utilitiesdbInspect.js- Database schema inspectiondoc-linker.js- Documentation cross-linkingversionCheck.js- Version validation
Critical Principles
- Type Safety: Use
@ts-checkand JSDoc annotations for type information - Lazy Loading: Defer expensive imports until needed to optimize startup time
- Internationalization: All user-facing strings must use
bundle.getText() - Error Handling: Provide clear, actionable error messages with context
- Debug Support: Use
base.debug()for diagnostic logging - Caching: Implement intelligent caching for expensive operations
- Pure Functions: Prefer stateless functions with predictable behavior
- Configuration: Support configuration overrides from config files
File Structure Template
/*eslint-env node, es6 */
// @ts-check
/**
* @module moduleName - Brief description of module purpose
*/
// Standard imports
import * as base from "./base.js"
import * as fs from 'fs'
import * as path from 'path'
// Module-level state (minimize)
const cache = new Map()
/**
* Main function documentation
* @param {string} param1 - Description
* @param {number} [param2] - Optional parameter
* @returns {Promise<ReturnType>} Description of return value
*/
export async function mainFunction(param1, param2) {
base.debug(base.bundle.getText("debug.call", ["mainFunction"]))
try {
// Implementation
return result
} catch (error) {
throw new Error(base.bundle.getText("error.specificError", [param1]))
}
}
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.
- 2d ago First seen · 624 lines · 3,861 tokens per session scan A 50927a413c9b
hana-developer-cli-tool-example utility-module-development.instructions.md is an instructions file published in the GitHub repository SAP-samples/hana-developer-cli-tool-example (109 stars, last pushed 6d ago), licensed Apache-2.0. It adds 3,861 tokens to every session, about $0.0193 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.
Other instructions, from other repositories
spec-kit-zh AGENTS.md
Instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.
coder CLAUDE.md
Claude Code instructions for coder/coder, a project described as: Secure environments for developers and their agents.
ClaudeCodeUsage AGENTS.md
Instructions for ClaudeCodeUsage/ClaudeCodeUsage, covering agents.md, product identity and scope, architecture boundaries, safety and privacy invariants and codex beta data and performance invariants.
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
vscode-gitlens CLAUDE.md
Claude Code instructions for gitkraken/vscode-gitlens, a project described as: Supercharge Git inside VS Code and unlock untapped knowledge within each repository — Visualize code authorship at a glance via Git blame annotations and CodeLens, seamlessly navigate and explore Git repositories, gain valuable insights via…