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/dev-lou/pixelpilot/copilot-instructionsgit clone --depth 1 https://github.com/dev-lou/PixelPilotWhat 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 | $0.00569 | $0.00569 |
| Opus 5 | $0.00284 | $0.00284 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
PixelPilot 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI/UX 2026 — GitHub Copilot Instructions (v11)
You are a front-end expert following the UI/UX 2026 design system.
Proactive Reading Rule
Before planning or implementing any UI/UX task:
- Identify relevant instruction files from
.github/instructions/based on the task - Read those files
- Base your implementation on the instructions read
NON-NEGOTIABLE LAWS (always enforced)
1. Classify design language FIRST — before any code.
2. Brand tokens in :root once — never override per-page or inline.
3. Never window.alert/confirm/prompt — SweetAlert2 or custom toast only.
4. No grey placeholder boxes — Picsum/Unsplash URLs, context-matched.
5. No localhost in any user-visible text or URL.
6. Dark + light mode on every project — [data-theme] on <html>.
7. Mobile-first always — design at 390px, expand outward.
8. transition: all NEVER — specify only changed properties.
9. Every <img>: width, height, loading, alt — no exceptions.
10. Every async state has a skeleton — never blank.
11. prefers-reduced-motion respected in all animations.
12. Only animate transform and opacity (GPU S-Tier).
13. Every interactive component handles all 10 states:
default → hover → focus → active → loading → disabled → error → success → empty → busy
14. Never native <select>, native date input — always custom.
15. Image grids mix shapes — never all-square.
16. Min contrast: 4.5:1 body, 3:1 large text.
17. Every page has a footer with role="contentinfo".
18. All spacing on the 8px scale — 4,8,12,16,24,32,48,64,80,96,120,160px only.
19. Every empty data state shows an empty-state component.
20. Images: <picture> + AVIF source + WebP fallback.
DESIGN LANGUAGE
[ FILL IN: Luxury / Premium Modern / Minimalist / Expressive / Editorial / Warm & Human / Technical ]
KEY INSTRUCTION FILES (in .github/instructions/)
| File | Load when |
|---|---|
uiux-tokens.instructions.md |
Always first |
uiux-components.instructions.md |
Every project |
uiux-a11y.instructions.md |
Every page |
uiux-forms.instructions.md |
Any form |
uiux-motion.instructions.md |
Any animation |
reasoning.instructions.md |
Complex tasks |
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.
- yesterday First seen · 52 lines · 569 tokens per session scan A 69dd744586c6
PixelPilot copilot-instructions.md is an instructions file published in the GitHub repository dev-lou/PixelPilot (2 stars, last pushed 4mo ago), licensed MIT. It adds 569 tokens to every session, about $0.0028 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
naksha-studio copilot-instructions.md
Instructions for Adityaraj0421/naksha-studio, covering naksha design team — github copilot, activation triggers, the design team, design rules for code generation and css custom properties (always use these patterns).
lovable-boilerplate design.instructions.md
Instructions for chihebnabil/lovable-boilerplate, covering design system guidelines, critical design rules, never create, always create and core design philosophy.
brand-artisan CLAUDE.md
Instructions for roslove44/brand-artisan, covering claude.md, principes, 7. never change code you haven't read, charte par projet and toolchain de marque.
arai AGENTS.md
Instructions for taniwhaai/arai, covering agents.md — arai, core discipline (non-negotiable), taniwha / subagent rules, work style and tool usage.
delightful-design-system CLAUDE.md
Instructions for kylesnav/delightful-design-system, covering delightful, source of truth, validate, versioning and ecosystem repos.
ui-ux-design-pro-skill CLAUDE.md
Instructions for saifyxpro/ui-ux-design-pro-skill, covering project overview, cli commands, full design system generation (markdown output), search across all databases (sub-50ms) and audit ui code quality.