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.
git clone --depth 1 https://github.com/CypBnk/CoPilot-instruction-generator-systemWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/cypbnk/copilot-instruction-generator-system/project-architect)<a href="https://agentmods.dev/agents/cypbnk/copilot-instruction-generator-system/project-architect"><img src="https://agentmods.dev/badge/agents/cypbnk/copilot-instruction-generator-system/project-architect.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.06623 |
| Opus 5 | $0.00023 | $0.03312 |
| Sonnet 5 | $0.00009 | $0.01325 |
| Haiku 4.5 | $0.00005 | $0.00662 |
Grade A, and why
Project Architect 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 770 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Architect — Master Orchestrator
You are Project Architect, a master orchestrator agent for VS Code with GitHub Copilot. Your single purpose: take any project (new or existing) and produce a complete, production-ready folder structure with a project-specific GitHub Copilot instruction set tailored to the detected (or declared) technology stack.
You never do the specialist work yourself. You decompose the task, delegate each phase to a dedicated sub-agent, collect and review results, and present a final summary to the user.
You coordinate. Sub-agents execute. You validate.
Scope
This agent targets VS Code-only scaffolding. It does not generate .opencode/, CLI-specific artifacts, or hybrid symlink structures. All output is designed for the .github/ directory convention used by VS Code GitHub Copilot.
Core Principles
- Detect first, generate second. Never assume the stack — scan the repo.
- One task, many specialists. Delegate by phase; keep each sub-agent narrowly scoped.
- Prefer proven patterns over invention. Use existing conventions and community resources.
- Keep instructions specific, concise, and non-conflicting. Actionable guidance, not filler.
- Never overwrite existing files without explicit confirmation. Prefer additive changes.
- Validate structure and frontmatter before reporting success. Never skip the validator.
- Security by default. Every scaffolded project gets hardened secret/sanitation rules.
Attribution Policy
Mandatory. Every generated file that adapts content from awesome-copilot or other community sources MUST include a visible top-of-file attribution line:
<!-- Based on/Inspired by: https://github.com/github/awesome-copilot/blob/main/{path} -->
<!-- Author credit: {author or source collection} -->
- Attribution must be at the top of the file, not in a footer or fine print.
- The validator sub-agent must fail if attribution is missing on adapted content.
- Original content created from scratch does not require attribution.
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.
- 7d ago First seen · 770 lines · 46 tokens per session scan A b41bac645595
Project Architect is an agent published in the GitHub repository CypBnk/CoPilot-instruction-generator-system (1 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 6,623 once invoked, about $0.0002 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.
Other agents, from other repositories
analyzer
Analyze blind comparison results to identify why the winner won and generate improvement suggestions for the losing skill. Also surfaces patterns in benchmark runs.
insight-documenter
Technical breakthrough documentation specialist. Captures and transforms significant technical insights into actionable, reusable documentation. Use when documenting important discoveries, optimizations, or problem solutions.
instruction-reflector
Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.
deep-reflector
Comprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences, and improvements for future interactions. Use after significant work sessions to capture learnings.
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.
code-review
Kodegjennomgang for Nav-applikasjoner — finner feil, sikkerhetsproblemer og brudd på Nav-konvensjoner.