agenteval backend.instructions.md

Backend development instructions for an application. The backend is the part that handles APIs, databases, sessions, and server-side processing.

In plain words
What is it for?
Use them when building or reviewing REST endpoints, database queries and migrations, Redis session storage, caching, and external HTTP calls in the agenteval project.
Why use it?
They set consistent requirements for API validation, error responses, request tracking, database changes, caching, session storage, and external request timeouts.

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/lukasmetzler/agenteval/backend
Clone the repo
git clone --depth 1 https://github.com/lukasmetzler/agenteval

Made for: GitHub Copilot.

Per session 113 This file is loaded in full into every session.
When invoked 113 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 $0.00113 $0.00113
Opus 5 $0.00056 $0.00056
Sonnet 5 $0.00023 $0.00023
Haiku 4.5 $0.00011 $0.00011

Measured 2d ago against content hash 810506d42646, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agenteval 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.

demo/.github/instructions/backend.instructions.md · 20 lines

What it actually says

Backend Instructions

API Design

REST endpoints must follow our OpenAPI spec. Every endpoint needs:

  • Zod input validation
  • Standardized error responses
  • Rate limiting headers
  • Request logging with correlation IDs

Database

Use the query builder, not raw SQL. All queries must use parameterized inputs. Migrations go in src/db/migrations/ with timestamp prefixes.

Performance

Cache database queries that don't change often. Use Redis for session storage. Set reasonable timeouts on all external HTTP calls (default: 10s).

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 · 20 lines · 113 tokens per session scan A 810506d42646

Subscribe to this mod's changes

agenteval backend.instructions.md is an instructions file published in the GitHub repository lukasmetzler/agenteval (6 stars, last pushed 2mo ago), licensed MIT. It adds 113 tokens to every session, about $0.0006 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.