copilot-datagate copilot-instructions.md

Repository instructions for Copilot when working on DataGate, a Rust security boundary between an AI model and a real database. They define the source of truth, architecture, security rules and coding practices.

In plain words
What is it for?
Use them when adding features, changing database access, reviewing existing patterns or updating documentation to match the implementation.
Why use it?
They help keep database access read-only and ensure every request passes through the project’s policy checks and controlled query builder.

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/caucus-race/copilot-datagate/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Caucus-Race/copilot-datagate

Made for: GitHub Copilot.

Per session 1,397 This file is loaded in full into every session.
When invoked 1,397 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 $0.01397 $0.01397
Opus 5 $0.00698 $0.00698
Sonnet 5 $0.00279 $0.00279
Haiku 4.5 $0.00140 $0.00140

Measured yesterday against content hash 30b8aedca149, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-datagate copilot-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/copilot-instructions.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Queste istruzioni definiscono come Copilot deve generare codice e proporre modifiche in questo repository. L'obiettivo è coerenza, correttezza e rispetto del ruolo di security-boundary che DataGate ha tra un LLM e un database reale.

Source of Truth

  • In caso di conflitto tra documentazione e codice sorgente, il codice sorgente è autorevole.
  • Prima di implementare una feature, verifica i pattern esistenti nei moduli corrispondenti (src/policy.rs, src/query/, src/backend/, src/mcp/, ecc.).
  • Se rilevi drift tra istruzioni e implementazione, aggiorna questo file nello stesso lavoro.

Architettura (vedi Architecture.md per il dettaglio)

  • Core layer: connessioni, read-only, schema loader, policy engine, query builder, validazione input, limiti di complessità.
  • Nessun modulo può bypassare policy engine + query builder controllato per raggiungere un backend.
  • I tool MCP (src/mcp/) non parlano mai direttamente al backend: passano sempre da policy → query builder → backend.

Regole di sicurezza (non negoziabili)

  • Nessun SQL libero. Ogni query deve passare dal query builder controllato (select, search, aggregate) e da query parametrizzate.
  • Read-only garantito. Nessuna operazione di scrittura (INSERT/UPDATE/DELETE/DDL) deve mai essere raggiungibile da un tool MCP o da un path di codice applicativo.
  • Policy-first. Ogni operazione deve essere validata dal policy engine (tabelle, colonne, filtri, limiti di righe/complessità) prima di generare qualunque SQL.
  • Nessun leak di schema. Errori e risposte non devono mai esporre stack trace, SQL grezzo, o nomi di tabelle/colonne non autorizzate dalla policy.
  • Determinismo. Stessa richiesta → stessa risposta. Evitare comportamenti emergenti o dipendenti da stato nascosto.
  • Limiti sempre lato server. Rate limiting, limiti di output e di complessità non vanno mai delegati solo al client/tool.

Regole di codice (Rust)

  • Segui STYLEGUIDE.md: niente unwrap()/panic! su input esterno, cargo fmt + cargo clippy -D warnings puliti prima di ogni commit.
  • Errori di dominio con thiserror, errori applicativi con anyhow.
  • I/O asincrona con tokio; connessioni ai backend sempre tramite pool.
  • Credenziali backend solo da environment variables/runtime secret store (DB_URL o DB_*); mai password, URL con credenziali o segreti nei file del repository.
  • Mantieni i moduli piccoli e allineati ai confini descritti in Architecture.md; non introdurre dipendenze pesanti se non strettamente necessarie.

Read the full file on GitHub · 93 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 · 93 lines · 1,397 tokens per session scan A 30b8aedca149

Subscribe to this mod's changes

copilot-datagate copilot-instructions.md is an instructions file published in the GitHub repository Caucus-Race/copilot-datagate (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 1,397 tokens to every session, about $0.0070 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens