packmind packmind-cli-use-case-structure.instructions.md

A set of instructions for structuring command-line application use cases in PackmindHub/packmind. Use cases contain business operations, while handlers deal with user output and errors are represented by named custom types.

In plain words
What is it for?
Use it when adding or changing CLI use cases, their interfaces, command and response types, domain errors, or application implementations.
Why use it?
It keeps application logic separate from command-line presentation, making the code easier to reuse, test, and maintain.

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/packmindhub/packmind/packmind-cli-use-case-structure
Clone the repo
git clone --depth 1 https://github.com/PackmindHub/packmind

Made for: GitHub Copilot.

Per session 287 This file is loaded in full into every session.
When invoked 287 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 $0.00287 $0.00287
Opus 5 $0.00143 $0.00143
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00029 $0.00029

Measured 2d ago against content hash 980e0f5efb39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

packmind packmind-cli-use-case-structure.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.

apps/cli/.github/instructions/packmind-cli-use-case-structure.instructions.md · 18 lines

What it actually says

Standard: CLI Use Case Structure

Enforce clean separation between domain contracts and application logic in apps/cli use cases, ensuring use cases focus purely on business operations without presentation concerns like user output or ... :

  • Base all use case interfaces on IPublicUseCase<Command, Response> from @packmind/types
  • Create new error classes for domain-specific failure scenarios when existing errors do not apply
  • Define Command and Response types in the same file as the use case interface
  • Define use case interfaces in src/domain/useCases/ directory
  • Document the errors that a use case can throw so handlers know which error types to catch
  • Export error classes from individual files in src/domain/errors/ for reusability across use cases
  • Implement use cases in src/application/useCases/ directory
  • Keep use cases focused on business logic without any user output (no console logging, no outputError/outputSuccess calls)
  • Name error classes descriptively to indicate the specific failure condition (e.g., PackageNotFoundError, AccessDenied, InvalidStandardFormat)
  • Throw custom domain errors defined in src/domain/errors/ instead of generic Error instances

Full standard is available here for further request: CLI Use Case Structure

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 · 18 lines · 287 tokens per session scan A 980e0f5efb39

Subscribe to this mod's changes

packmind packmind-cli-use-case-structure.instructions.md is an instructions file published in the GitHub repository PackmindHub/packmind (306 stars, last pushed 4d ago), licensed Apache-2.0. It adds 287 tokens to every session, about $0.0014 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.