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.
npx agentmods add instructions/barrosohub/frontend-stack-blueprint/copilot-instructionsgit clone --depth 1 https://github.com/barrosohub/frontend-stack-blueprintWrote 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/instructions/barrosohub/frontend-stack-blueprint/copilot-instructions)<a href="https://agentmods.dev/instructions/barrosohub/frontend-stack-blueprint/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/barrosohub/frontend-stack-blueprint/copilot-instructions.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 | $0.01321 | $0.01321 |
| Opus 5 | $0.00660 | $0.00660 |
| Sonnet 5 | $0.00264 | $0.00264 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
frontend-stack-blueprint 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 4d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Custom Instructions
These instructions guide GitHub Copilot when working on projects that reference this Frontend Stack Blueprint repository.
Stack Reference
This project follows the Frontend Stack Blueprint — a canonical frontend stack for any new project. For the complete reference, see:
- Full spec: AGENTS.md
- Machine-readable versions: stack.yaml
- Complete single-file reference: llms-full.txt
Key Rules for Copilot
- Use TypeScript ≥7 with
strict: true— noany - Use React ≥19.2.7 function product components; class Error Boundaries are allowed
- Use pnpm as the default package manager
- Use Vite ≥8 with Node.js >=22.22
- Treat Bun ≥1 as an alternative runtime only
- Structure by feature (
src/features/), never by file type - Use
@/*path aliases, never../../../ - Use
cn()utility for conditional Tailwind classes - Use React Hook Form + Zod for forms with 2+ fields
- If the project needs ORM-backed server-side or edge relational data access, use Prisma ≥7; do not add ORM to purely static apps
- If the project needs authentication, use Better Auth ≥1; do not assume auth is mandatory
- If the project needs managed services, prefer Neon Postgres, Cloudflare D1, Cloudflare R2, Cloudflare KV, and Resend by capability; do not assume they are mandatory
- For new Cloudflare projects use Workers Static Assets; keep existing Pages projects unless migration is justified; use Vercel when explicitly requested
- Use TanStack Query for server state
- Use Zustand for client state (no Redux, MobX). TanStack Store remains under evaluation
- Use Motion (import from
motion/react) for animations - Use date-fns ≥4.1 + @date-fns/tz for dates and timezones (no Moment, no Day.js)
- Use the selected Base UI/Radix/React Aria/shadcn primitives before custom components
- Write tests with Vitest; use Playwright for critical deployed-UI journeys
- Never install packages outside this stack without asking
- Use Advanced Capabilities only when an explicit product requirement activates Markdown, tables, charts, diagrams, code editing, terminal, collaboration, or PDF viewing
- If root
DESIGN.mdexists, treat it as the provisional DESIGN.md Design Contract: read it before UI work and regenerate Tailwind tokens after intentional changes - Apply Official CLI-First when official docs recommend a CLI
- Run Impact Preflight before any official CLI execution; ask confirmation if non-trivial/uncertain
- Apply Production Reliability: authoritative CI, WCAG 2.2 AA, Core Web Vitals budgets, browser matrix, preview smoke, and rollback
- Validate public environment and API responses at runtime; use fetch cancellation/timeout and MSW degraded scenarios when networked
- Activate Sentry, OpenTelemetry, Statsig, and Storybook only when their operational capability applies
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.
- 4d ago First seen · 102 lines · 1,321 tokens per session scan A 324536329ca5
frontend-stack-blueprint copilot-instructions.md is an instructions file published in the GitHub repository barrosohub/frontend-stack-blueprint (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,321 tokens to every session, about $0.0066 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 instructions, from other repositories
own-planner AGENTS.md
Instructions for am-space/own-planner, covering agents.md, common commands, verify only one stack, single test project, class, or method and run the console chat loop (type exit to quit).
own-planner CLAUDE.md
Instructions for am-space/own-planner, covering claude.md, common commands, verify only one stack, single test project, class, or method and run the console chat loop (type exit to quit).
own-planner copilot-instructions.md
Instructions for am-space/own-planner, covering ownplanner copilot instructions, repository overview, architecture documentation, general rules and database migrations.
own-planner backend.instructions.md
Instructions for am-space/own-planner, covering backend instructions, technology, coding rules, layering rules and web server guidance.
own-planner frontend.instructions.md
Instructions for am-space/own-planner, covering frontend instructions, technology, coding rules and change preferences.
own-planner domain-app.instructions.md
Instructions for am-space/own-planner, covering domain and application layer instructions and coding rules.