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/superdesigndev/superdesign-skill/agents-mdgit clone --depth 1 https://github.com/superdesigndev/superdesign-skillWrote 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/superdesigndev/superdesign-skill/agents-md)<a href="https://agentmods.dev/instructions/superdesigndev/superdesign-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/superdesigndev/superdesign-skill/agents-md.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 | $0.01698 | $0.01698 |
| Opus 5 | $0.00849 | $0.00849 |
| Sonnet 5 | $0.00340 | $0.00340 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
superdesign-skill 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 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project agent memory
This file is the project's committed home for project-intrinsic agent knowledge: build, test, release, architecture, and sharp-edge notes that should travel with the code.
What this repo is
A published agent skill (skills/superdesign/) that drives the SuperDesign design canvas via its CLI. The skill is prose, not code - there is no build/test suite. Files:
skills/superdesign/SKILL.md- entry point (front-matter + core workflow)skills/superdesign/references/SUPERDESIGN.md- main design workflow (always read) +COMMAND CONTRACTskills/superdesign/references/INIT.md- repo-analysis (init) instructionsskills/superdesign/references/RESUME.md- durable UI context + warm cross-session iteration pathskills/superdesign/references/GRAPHIC.md- poster/marketing-asset workflow (loaded only for graphics)skills/superdesign/references/PRESENTATION.md- outline approval, presentation generation, assets, and slide-safe iterationskills/superdesign/references/WEBSITE.md- live-site extraction recipes (loaded only for reference-URL tasks)skills/superdesign/references/COMPONENTS.md- Petite-Vue template spec (loaded only before create/update-component conversions)skills/superdesign/references/design-with-your-model.md- caller-model HTML authoring/import path (loaded only when explicitly requested or after create/iterate retry failure)skills/superdesign/{SUPERDESIGN,INIT}.md- deprecated compatibility forwarders (do not add content)
Skill flow invariant: two entry paths
SKILL.md branches on Step 1 into a real-codebase path (repo init is mandatory) and a no-codebase path (empty/scratch/sandbox workspace with no frontend code - skip init, gather design context conversationally, design via SUPERDESIGN.md "SOP: BRAND NEW PROJECT"). Before cold discovery, every real-codebase UI request checks .superdesign/resume.json; valid state for the same target follows RESUME.md regardless of request wording, reuses the saved bundle without rereading init/source context, and reads or adds only narrowly relevant source when targeted context expansion is required. Within the cold real-codebase path, SUPERDESIGN.md's UI TARGET ROUTING further splits by target: an existing rendered page goes reproduce-first (Step 3a ground truth), while a new page in the codebase skips reproduction entirely ("SOP: NEW TARGET IN EXISTING CODEBASE") - keep reproduction rules scoped to existing rendered targets. Any init/hard-gate rule you edit must stay scoped to the real-codebase path so it does not block the no-codebase path (see the HARD GATE and MANDATORY INIT rules in SUPERDESIGN.md). A separate Step 0 preflight halts when shell execution is unavailable (e.g. ChatGPT Chat mode) - distinct from the auth/login path, where the CLI actually ran.
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 · 48 lines · 1,698 tokens per session scan A 96d04d6502dc
superdesign-skill AGENTS.md is an instructions file published in the GitHub repository superdesigndev/superdesign-skill (493 stars, last pushed 13d ago), licensed MIT. It adds 1,698 tokens to every session, about $0.0085 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 2026-08-30.
Other instructions, from other repositories
html-anything AGENTS.md
AGENTS.md instructions for nexu-io/html-anything, covering this is not the next.js you know, workspace shape and commands.
stewie-pixel guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
seektty AGENTS.md
Instructions for Hilbert-beinghappy/seektty: This repository ships one out-of-tree DeepSeek Harness Bundle. Harness remains the only owner of Agent, Session, model, settings, permissions, Profile, plugin, and persistence state.
kleinanzeigen-reader CLAUDE.md
Instructions for its-me-prash/kleinanzeigen-reader, covering claude.md — kleinanzeigen-reader, what this repo is, auto-load instructions for claude code, quick command reference and fetch a listing.
clawchat-plugin-connect AGENTS.md
Instructions for XMethues/clawchat-plugin-connect, covering agent skills, issue tracker, triage labels and domain docs.
copy-thief AGENTS.md
Instructions for thalesholleben/copy-thief, covering agents.md, ponto de entrada, mapa do repositório, regras que não podem ser quebradas and como rodar / instalar.