Borrowing it
Nothing to install: this file belongs to LE-VAI/designesy-org. 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/LE-VAI/designesy-org/main/AGENTS.mdgit clone --depth 1 https://github.com/LE-VAI/designesy-orgWrote 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/le-vai/designesy-org/agents-md)<a href="https://agentmods.dev/instructions/le-vai/designesy-org/agents-md"><img src="https://agentmods.dev/badge/instructions/le-vai/designesy-org/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/le-vai/designesy-org/agents-md"><img src="https://agentmods.dev/badge/instructions/le-vai/designesy-org/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 | $0.01064 | $0.01064 |
| Opus 5.5 | $0.00426 | $0.00426 |
| Sonnet 5.5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
designesy-org 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 10d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designesy Agent Rules
You are operating inside Designesy.
This is not a typical web project.
Designesy is design intelligence infrastructure.
Core Understanding
Designesy turns: sources → principles → contracts → tools → systems → better designed work
Do Not
- Do not generate generic AI SaaS layouts.
- Do not assume this is a normal startup project.
- Do not build UI before structure and contracts exist.
- Do not invent design systems without source or rationale.
- Do not treat Labs as a blog or gallery.
Always
- Start from purpose, context, and system role.
- Use contracts (DESIGN.md) before inventing decisions.
- Prefer structure over surface.
- Encode reusable rules instead of one-off styling.
- Separate observed facts from derived design decisions.
- Verify outputs when visual quality matters.
Public Copy
- No em dashes in visible copy. A colon sits between a label and its description; a period, comma, semicolon or parentheses carries the rest; a middot joins a name to its descriptor.
- State the positive claim. Keep a negative when it carries a fact (a privacy guarantee, a scope limit, a prohibition, a disclaimer); rewrite "not X, but Y" pivots.
- Number ranges read "to" (5 to 10), in prose and in tables.
- Say a missing value in words. In a dense table use
NotMeasuredfromapps/site/app/lib/data/figure.tsx: a dash for the eye, words for a screen reader. - Quotations stay verbatim. Contract text changes only with its contract: the
*-contract.tsmodules and the/contractspages move together. - The build holds the line:
scripts/check-voice.jsfails a page that gains em dashes or pivots beyondscripts/voice-baseline.json, andscripts/check-jsx-glue.jsfails a sentence that wraps so JSX glues two words together, and a space that can drop out of an accessible name. Keep the space inside a text run: wrap one word earlier, or write it into the neighbouring text or string (Fixes <span>,{` ${value}`}). In inline content, a{' '}(or a lone space between two children) beside text can be dropped from a name computed from content: links, buttons, summaries, headings, table headers and cells, a label's control. In a flex or grid container Chrome keeps it, and the gate flags it there too. Between two host elements (<span>,<b>) it is safe; a component that returns text, such as a number in a fragment, counts as text.
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.
- 10d ago Changed · +8 lines · +155 tokens per session d790bd005dc2
- 23d ago Changed · +14 lines · +198 tokens per session d1b72adc7835
- 26d ago Changed · +15 lines · +199 tokens per session 791352ae44c0
- 1mo ago Changed · +19 lines · +263 tokens per session 49d683d3430d
- 2mo ago First seen · 49 lines · 249 tokens per session scan A 6a690e8ddfcd
designesy-org AGENTS.md is an instructions file published in the GitHub repository LE-VAI/designesy-org (0 stars, last pushed yesterday), licensed MIT. It adds 1,064 tokens to every session, about $0.0043 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 2026-08-31.
designesy-org AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| designesy-org AGENTS.mdLE-VAI/designesy-org | Instructions file | 0 | yesterday | MIT | A | 1,064 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |