hana-developer-cli-tool-example command-documentation.instructions.md

Instructions for writing or updating documentation for hana-cli command-line commands. They define a consistent format with command flows, parameter tables, syntax examples, and related commands.

In plain words
What is it for?
Creating or revising command files in docs/02-commands/, documenting parameters and usage, and adding Mermaid diagrams that show how commands work.
Why use it?
They make CLI documentation easier to use and protect existing explanatory content when only one section needs updating.

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/command-documentation
Clone the repo
git clone --depth 1 https://github.com/SAP-samples/hana-developer-cli-tool-example

Made for: GitHub Copilot.

Per session 9,187 This file is loaded in full into every session.
When invoked 9,187 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 $0.09187 $0.09187
Opus 5 $0.04594 $0.04594
Sonnet 5 $0.01837 $0.01837
Haiku 4.5 $0.00919 $0.00919

Measured yesterday against content hash b1e0ccc920e9, 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 command-documentation.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 yesterday.

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/command-documentation.instructions.md · 1,247 lines

How it starts

The opening of the file, as written. The whole thing — 1,247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI Command Documentation Guidelines

When documenting CLI commands for the hana-cli tool, follow this structured format to ensure consistency and completeness.

Preservation Rule (Do Not Strip Existing Content)

When updating an existing documentation file, preserve any additional description or educational content already present.

Only replace or insert content inside the specific section you are updating, and do not delete other paragraphs, lists, or subsections that provide extra context. This is especially important for Description and Educational Context content that may span multiple paragraphs.

Practical guidance:

  • Keep all existing descriptive paragraphs unless they directly contradict verified behavior.
  • When re-generating sections, update the section body but leave any extra subheadings or explanatory text that belong to the command.
  • Never remove sections like “What is …?”, “How is … Used?”, or other narrative blocks unless explicitly asked to delete them.

Critical: Filename vs Command Name

The filename is NOT the command name.

  • Filename: Uses kebab-case for organization (e.g., column-stats.md)
  • Command Name: Uses camelCase as defined in code (e.g., columnStats)
  • Source of Truth: Always the export const command in bin/[commandName].js

Example:

File:    docs/02-commands/analysis-tools/column-stats.md  ← kebab-case
Command: columnStats  ← camelCase (from bin/columnStats.js)
Help:    hana-cli columnStats [schema] [table]

Never assume the command name from the filename. Always verify in the command's source code.

Document Structure

Every command documentation file must include these sections in order:

1. Header Section

# commandName

> Command: `commandName`  
> Category: **Category Name**  
> Status: Production Ready | Early Access | Beta | Experimental

## Description

[Clear, concise description of what the command does]

[Optional: Extended explanation with context, use cases, and background information]

Read the full file on GitHub · 1,247 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. yesterday First seen · 1,247 lines · 9,187 tokens per session scan A b1e0ccc920e9

Subscribe to this mod's changes

hana-developer-cli-tool-example command-documentation.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 9,187 tokens to every session, about $0.0459 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.