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/iress/design-system/copilot-instructionsgit clone --depth 1 https://github.com/iress/design-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/instructions/iress/design-system/copilot-instructions)<a href="https://agentmods.dev/instructions/iress/design-system/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/iress/design-system/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 | $0.00808 | $0.00808 |
| Opus 5 | $0.00404 | $0.00404 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
design-system 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot Instructions for Iress Design System
This repository uses GitHub Copilot with specialized agents and instructions to maintain code quality and consistency.
Available Instructions
This repository contains domain-specific instructions located in .github/instructions/:
bugfixing.instructions.md- Comprehensive bug-fixing methodology and best practicescomponent-creation.instructions.md- Guidelines for creating new design system componentsfile-organization.instructions.md- File organization principles for implementation and test filesglobal.instructions.md- General workspace commands, test commands, and lintingpr-review.instructions.md- Code review standards and preferenceseslint.instructions.md- ESLint usage and file-specific linting patterns
Specialized Agents
Bug-Fixing Agent
A specialized agent for fixing bugs from the GitHub issue tracker. This agent:
- Follows the comprehensive methodology in
bugfixing.instructions.md - Handles bugs in both 5.x and main branches with cross-branch tracking
- Creates Storybook bug reproduction stories
- Provides multiple solution approaches with trade-offs
- Generates PR-ready documentation
- Integrates with GitHub Issues for automatic context retrieval
- Ensures bugs fixed on one branch are addressed on the other when applicable
Invocation: Invoke the bug-fixing agent by mentioning it with an issue number or bug description. Always specify which branch(es) are affected.
Location: .github/agents/bugFixAgent.md
Prompts
Component Meta Agent
A specialized agent for generating component metadata and thumbnails.
Location: .github/prompts/createComponentMeta.md
General Copilot Behavior
When assisting with this repository, GitHub Copilot should:
- Follow Existing Instructions: Always reference and follow the domain-specific instructions in
.github/instructions/ - Maintain Consistency: Follow established patterns and conventions in the codebase
- Use Progressive Communication: Confirm understanding before implementing changes
- Prefer Minimal Changes: Fix issues with targeted, minimal changes rather than over-engineering
- Test-Driven: Run tests after changes and ensure no regressions
- Document Changes: Provide clear explanations of what changed and why
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.
- 3d ago First seen · 87 lines · 808 tokens per session scan A 1c6959badba7
design-system copilot-instructions.md is an instructions file published in the GitHub repository iress/design-system (1 stars, last pushed 7d ago), licensed Apache-2.0. It adds 808 tokens to every session, about $0.0040 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
screenshot-to-code CLAUDE.md
Instructions for abi/screenshot-to-code, a project described as: Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue).
tidyfactor-design AGENTS.md
Instructions for alwkala/tidyfactor-design, covering ⚡ skill & 24 modular slash commands (7 lifecycle stages) and critical architecture (non-negotiable).
ui-ux-suite AGENTS.md
Instructions for Aboudjem/ui-ux-suite, covering agents.md: ui-ux-suite, what this tool is, how an ai agent should invoke it, preferred: the mcp tool uiuxauditrun and alternative: the cli.
gsap-transform gsap-plugins.instructions.md
Instructions for taotao135791-bit/gsap-transform: When using GSAP plugins (SplitText, MorphSVG, DrawSVG, MotionPath, Flip, Draggable, Inertia, Observer, CustomEase, CustomWiggle, ScrambleText, ScrollSmoother, Physics2D).
random-design-mcp AGENTS.md
AGENTS.md instructions for yanislav-igonin/random-design-mcp, covering agents.md, project purpose, repository map, architecture and product constraints.
react-design-systems-mcp CLAUDE.md
Instructions for agentience/react-design-systems-mcp, covering claude.md, project overview, development commands, building and running and install dependencies.