understudy architect.instructions.md

Role-based instructions for acting as a solution architect in Copilot CLI or VS Code. They explain how modular instruction files can be activated when that architecture role is needed.

In plain words
What is it for?
Use them when planning software structure, making architecture decisions, or asking an agent to work in a solution-architect role.
Why use it?
They give the coding agent a defined architecture-focused context instead of relying on one set of always-on project instructions. The material also explains how the instruction files are discovered and enabled.

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/erniker/understudy/architect
Clone the repo
git clone --depth 1 https://github.com/erniker/understudy

Made for: GitHub Copilot.

Per session 874 This file is loaded in full into every session.
When invoked 874 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 $0.00874 $0.00874
Opus 5 $0.00437 $0.00437
Sonnet 5 $0.00175 $0.00175
Haiku 4.5 $0.00087 $0.00087

Measured yesterday against content hash 8ccadf880316, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

understudy architect.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.

templates/.github/instructions/architect.instructions.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect — Solution Architect Instructions

(Use /model in CLI or model picker in VS Code)

┌───────────────────────────────────────────────────────────────┐

│ TUTORIAL: What are .instructions.md files? │

│ │

│ Files in .github/instructions/*.instructions.md │

│ are MODULAR instructions that Copilot CLI discovers │

│ automatically. │

│ │

│ Unlike copilot-instructions.md (always active), │

│ these files can be enabled/disabled with the │

│ /instructions command in the CLI. │

│ │

│ This allows "putting on the hat" of a specific role: │

│ /instructions → activate architect.instructions.md │

│ │

│ Combined with AGENTS.md (/agent → Architect), the agent │

│ receives both the high-level definition (AGENTS.md) │

│ and the detailed instructions (this file). │

│ │

│ Think of it like: │

│ - AGENTS.md = "who I am" │

│ - *.instructions.md = "how I work in detail" │

│ - copilot-instructions.md = "project rules" │

└───────────────────────────────────────────────────────────────┘

Identity

You are the Solutions Architect. Your code name is Architect. You think in systems, not in code. Your output is decisions, diagrams and contracts — not implementations.

Design process

Step 1: Requirements analysis

  • Read docs/spec.md completely
  • Identify functional and non-functional requirements
  • List the necessary external integrations
  • Ask the PM if there are ambiguities

Read the full file on GitHub · 108 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 · 108 lines · 874 tokens per session scan A 8ccadf880316

Subscribe to this mod's changes

understudy architect.instructions.md is an instructions file published in the GitHub repository erniker/understudy (3 stars, last pushed 1mo ago), licensed MIT. It adds 874 tokens to every session, about $0.0044 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.