own-planner backend.instructions.md

Backend development instructions for a C# application built with .NET, covering code style, asynchronous operations, dependency injection, and layer boundaries.

In plain words
What is it for?
Building or changing application services, web endpoints, infrastructure adapters, validation, logging, and asynchronous server operations.
Why use it?
They keep server-side changes consistent and prevent business logic, database access, and web concerns from being mixed together.

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/am-space/own-planner/backend
Clone the repo
git clone --depth 1 https://github.com/am-space/own-planner

Made for: GitHub Copilot.

Per session 374 This file is loaded in full into every session.
When invoked 374 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 $0.00374 $0.00374
Opus 5 $0.00187 $0.00187
Sonnet 5 $0.00075 $0.00075
Haiku 4.5 $0.00037 $0.00037

Measured 2d ago against content hash e9fe2abc750b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

own-planner backend.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/backend.instructions.md · 43 lines

What it actually says

Backend Instructions

Technology

  • Use C# for server-side changes.
  • Target .NET 10 and align with the existing code style in the edited project.
  • Preserve nullability annotations and existing async APIs.

Coding rules

  • Prefer async/await for I/O and service operations.
  • Preserve cancellation token flow where applicable.
  • Use dependency injection instead of direct construction when wiring services.
  • Validate public method arguments early.
  • Preserve structured logging patterns based on ILogger<T> and message templates.
  • Avoid sync-over-async unless there is already an established pattern and it cannot be changed safely.
  • Dispose async resources safely.

Layering rules

  • Keep domain logic in OwnPlanner.Domain.
  • Keep application orchestration, use-cases, and DTO mapping in OwnPlanner.Application.
  • Keep database, filesystem, external API, and adapter concerns in OwnPlanner.Infrastructure.
  • Keep HTTP, authentication, and presentation concerns in OwnPlanner.Web.Server.
  • Do not move infrastructure concerns into domain or application layers.

Web server guidance

  • Follow existing ASP.NET Core patterns for controllers, services, and registration.
  • Preserve authentication and user-isolation behavior.
  • When modifying chat-related services, preserve session behavior, async disposal, and structured logs.
  • Prefer extending existing services instead of duplicating cross-cutting logic.

Change preferences

  • Favor small, readable changes over broad refactors.
  • Keep public APIs stable unless the task explicitly requires a contract change.
  • When editing existing files, match their formatting and local conventions.
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 · 43 lines · 374 tokens per session scan A e9fe2abc750b

Subscribe to this mod's changes

own-planner backend.instructions.md is an instructions file published in the GitHub repository am-space/own-planner (2 stars, last pushed 4d ago), licensed MIT. It adds 374 tokens to every session, about $0.0019 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 2026-08-31.