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/jackguihx-alt/html2style/agents-mdgit clone --depth 1 https://github.com/jackguihx-alt/html2styleWrote 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/jackguihx-alt/html2style/agents-md)<a href="https://agentmods.dev/instructions/jackguihx-alt/html2style/agents-md"><img src="https://agentmods.dev/badge/instructions/jackguihx-alt/html2style/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 | $0.00318 | $0.00318 |
| Opus 5 | $0.00159 | $0.00159 |
| Sonnet 5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
html2style 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.
What it actually says
Agent Instructions
When a user asks to extract, transfer, document, or reproduce a website's design language, read SKILL.md and follow its evidence-first workflow.
Use the platform-neutral interfaces in this repository:
- Shell-capable agents: run
html2style doctor, thenhtml2style extract <url> <evidence.json> --profile full. - MCP-capable agents: call
browser_doctor, thenextract_website_evidence. - Default to style extraction when the user wants to understand a reference: build
style-profile.json, synthesizeSTYLE.md, and renderstyle-board.html. Stop there unless implementation was requested. - Before delivery, run
html2style skilland return the resulting design-style Skill. A human opensassets/preview.html; a later Agent session starts from itsSKILL.md. - Do not require a Codex, Claude, Cursor, or other vendor-specific browser plugin.
- Read
references/high-fidelity-reconstruction.mdfor replication work. Keep viewport, outer container, rendered image, and intrinsic asset geometry separate. - Read
references/design-language-transfer.mdwhen creating an original site from a reference style. Preserve design logic while replacing source identity, content, assets, and page architecture. - Generate
DESIGN.mdfrom measured evidence and renderdesign-system.html. - For complete replicas, run
html2style assetsandhtml2style audit --mode complete, then compare screenshots at identical viewports. Do not replace full-page scope with a representative sample.
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 · 16 lines · 318 tokens per session scan A fc93b37682c0
html2style AGENTS.md is an instructions file published in the GitHub repository jackguihx-alt/html2style (2 stars, last pushed 23d ago), licensed MIT. It adds 318 tokens to every session, about $0.0016 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
wonder-blocks CLAUDE.md
Claude Code instructions for Khan/wonder-blocks, covering wonder blocks design system, technology stack, coding conventions, file & export naming and typescript.
melta-ui AGENTS.md
Instructions for tsubotax/melta-ui, covering melta ui — ai エージェント作業ガイド, アーキテクチャ概要, 最初に読むファイル, 読み込みモード and 作業ルール.
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).
poster-maker CLAUDE.md
Instructions for dabodamjan/poster-maker, covering poster maker, project purpose, project structure, commands and key rules.
brandkit-mcp CLAUDE.md
Instructions for ejwhite7/brandkit-mcp, covering claude.md -- brandkit mcp, project overview, key concepts, repository structure and brand atomic system layout.
Design-Learn CLAUDE.md
Instructions for GalaxyXieyu/Design-Learn, covering claude.md, todo, quick start, server and vscode extension.