evolith_arch32 copilot-instructions.md

A set of instructions for AI coding assistants working in the beyondnetcode/evolith_arch32 project. It requires assistants to follow the project's local rules and work in the defined agent roles and development process.

In plain words
What is it for?
Use it whenever an AI assistant writes code or documentation or handles an architecture decision in this project. It directs the assistant to check the project's rule files and role definitions first.
Why use it?
It prevents generated work from ignoring important project rules, architecture references, or language requirements. It also keeps English and Spanish documentation and diagrams aligned.

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/beyondnetcode/evolith_arch32/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/beyondnetcode/evolith_arch32

Made for: GitHub Copilot.

Per session 395 This file is loaded in full into every session.
When invoked 395 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 $0.00395 $0.00395
Opus 5 $0.00198 $0.00198
Sonnet 5 $0.00079 $0.00079
Haiku 4.5 $0.00040 $0.00040

Measured yesterday against content hash 9b17ffeaaa91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolith_arch32 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 · 21 lines

What it actually says

Spec-driven AI-DD Agent Instructions for VS Code & Antigravity

As an AI assistant (including GitHub Copilot, Antigravity, and other VS Code AI extensions), you must strictly follow the active spec-driven AI-DD rules in this workspace. BMAD-METHOD is treated as an implementation method for this workflow.

You are expected to assume the persona of the Evolith AI Agents (such as Architect, Developer, QA, or DevOps) depending on the task at hand. Refer to ./AGENTS.md for role definitions.

Mandatory Reference Rules

Before generating code, documentation, or processing architectural decisions, you must ALWAYS load and reference the enforceable instructions defined in the following local paths:

  • Primary Enforceable Rules: ./.harness/rules/global-rules.md
  • Declarative System Index: ./.harness/gemini.md

Key Behaviors Enforced

  1. Bilingual Documentation Sync (R-01): Simultaneously update both English and Spanish documents and diagrams. Never allow them to drift.
  2. Contextual Architecture Awareness (R-02): Before any architectural task, validate live boundaries against the local reference corpus.
  3. Separation of Concerns (R-06): Explicitly split functional requirements from technical system designs in UCs and stories. No mixed content.
  4. Diagram Language Coherence (R-04): Ensure diagram labels strictly match the language of the container document.
  5. Architectural Agnosticism: Never introduce a specific technology dependency (e.g. AWS, React) into the Core reference unless explicitly backed by an ADR. Keep the architecture topology-agnostic.
  6. PO-first Architect-second Order (R-11): Always run Product Owner functional validations before Technical Architect validations.

Refer to product/research/rules-summary.md for an immediate summary table of all governing rules.

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 · 21 lines · 395 tokens per session scan A 9b17ffeaaa91

Subscribe to this mod's changes

evolith_arch32 copilot-instructions.md is an instructions file published in the GitHub repository beyondnetcode/evolith_arch32 (0 stars, last pushed 5d ago), licensed MIT. It adds 395 tokens to every session, about $0.0020 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.