Borrowing it
Nothing to install: this file belongs to cypress-io/cypress-design. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cypress-io/cypress-design/main/AGENTS.mdgit clone --depth 1 https://github.com/cypress-io/cypress-designWrote 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/cypress-io/cypress-design/agents-md)<a href="https://agentmods.dev/instructions/cypress-io/cypress-design/agents-md"><img src="https://agentmods.dev/badge/instructions/cypress-io/cypress-design/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/cypress-io/cypress-design/agents-md"><img src="https://agentmods.dev/badge/instructions/cypress-io/cypress-design/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02316 | $0.02316 |
| Opus 5.5 | $0.00926 | $0.00926 |
| Sonnet 5.5 | $0.00463 | $0.00463 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
cypress-design AGENTS.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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guidance
Before doing any work, you MUST read:
/.agents/architecture.md— repo structure, build, deploy./.agents/index.md— router for design, voice, and component guidance. Fetch only the pillars and components the task needs. Don't load them all preemptively.
Before claiming any UI / visual / content task is done, run /.agents/review-checklist.md against your own diff.
When the work is a product brief, initiative, or design proposal (not just a UI surface), also run /.agents/product-review-checklist.md — problem defined before solution, alternatives compared, success metric + measurement infrastructure, review date, and a post-launch keep/iterate/kill decision.
Before pushing, run the checks in ReadMe.md under "Before you push" — CI runs more than the pre-commit hook does — and add a changeset if the diff touches a published package (see /.agents/architecture.md under "Publishing"). Never bypass the hook with --no-verify.
PRs are squash-merged, so the PR title becomes the commit on main. Write it as a Conventional Commit, type(scope): sentence (for example docs(agents): recommend contrast steps that meet WCAG AA), following git log --oneline on main. Branch commit messages are discarded at merge; keep them short.
When opening a PR, lead the description with the problem and goal (why / what) before the implementation (how) — see .github/pull_request_template.md. Reviewers, human and AI, evaluate against the stated goal; a description that's all how steers them toward syntax nitpicks instead of substance.
Everything under /.agents/ is also served at https://design.cypress.io/agents/ for consumer repos to fetch — same files, single source of truth. Cross-doc links in these files use absolute https://design.cypress.io/agents/... URLs (not relative paths) so that agents fetching one doc over HTTP can follow links to the rest — keep new links absolute. scripts/copy-agents.mjs also generates llms.txt at the domain root listing every served doc, so the whole tree is discoverable from https://design.cypress.io/llms.txt.
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 Changed · +13 lines · +651 tokens per session a17801cc97b0
- 5d ago First seen · 84 lines · 1,665 tokens per session scan A bb29077a42fd
cypress-design AGENTS.md is an instructions file published in the GitHub repository cypress-io/cypress-design (13 stars, last pushed 3d ago), licensed MIT. It adds 2,316 tokens to every session, about $0.0093 per session on Opus 5.5. 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 2026-10-24.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.