Arbor backend.instructions.md

Backend coding rules for Arbor, an early version of software that lets autonomous agents make purchases. They specify how to organize a Python web service built with FastAPI and how to validate requests and test policy decisions.

In plain words
What is it for?
Use them when adding API endpoints, request and response data models, business logic, database code, validation, constants, and tests.
Why use it?
They give contributors consistent rules for where code belongs and how user input, database access, and purchase policies should be handled.

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/advaitgore/arbor/backend
Clone the repo
git clone --depth 1 https://github.com/advaitgore/Arbor

Made for: GitHub Copilot.

Per session 89 This file is loaded in full into every session.
When invoked 89 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 $0.00089 $0.00089
Opus 5 $0.00044 $0.00044
Sonnet 5 $0.00018 $0.00018
Haiku 4.5 $0.00009 $0.00009

Measured yesterday against content hash c1e8ca6a1ede, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Arbor 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 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/backend.instructions.md · 13 lines

What it actually says

Backend instructions

  • Use FastAPI routers for endpoints.
  • Use Pydantic schemas for request and response models.
  • Put core logic in services, not routes.
  • Keep database access organized and explicit.
  • Validate all user input.
  • Add tests for policy evaluation logic.
  • Avoid magic strings; use enums/constants where helpful.
  • Prefer simple, explicit code over abstraction-heavy designs.
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 · 13 lines · 89 tokens per session scan A c1e8ca6a1ede

Subscribe to this mod's changes

Arbor backend.instructions.md is an instructions file published in the GitHub repository advaitgore/Arbor (0 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session, about $0.0004 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.