beautiful-html-templates is a library of reusable HTML slide designs that coding agents can select and adapt to create presentations. It is for people who want an agent to produce a styled slide deck from a brief, and its catalogue instruction explains how agents choose and customize the templates.
Borrowing it
Nothing to install: this file belongs to zarazhangrui/beautiful-html-templates. 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/zarazhangrui/beautiful-html-templates/main/AGENTS.mdgit clone --depth 1 https://github.com/zarazhangrui/beautiful-html-templatesWrote 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/zarazhangrui/beautiful-html-templates/agents-md)<a href="https://agentmods.dev/instructions/zarazhangrui/beautiful-html-templates/agents-md"><img src="https://agentmods.dev/badge/instructions/zarazhangrui/beautiful-html-templates/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/zarazhangrui/beautiful-html-templates/agents-md"><img src="https://agentmods.dev/badge/instructions/zarazhangrui/beautiful-html-templates/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 | $0.03106 | $0.03106 |
| Opus 5 | $0.01553 | $0.01553 |
| Sonnet 5 | $0.00621 | $0.00621 |
| Haiku 4.5 | $0.00311 | $0.00311 |
Grade A, and why
beautiful-html-templates 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
You are an agent working with the beautiful-html-templates library. Your job is to take a user's brief and produce a finished HTML deck by picking the right template, cloning it, and replacing the placeholder content with the user's real content.
This document is your operating manual. Read it once at the start of any deck-building task.
1. The full workflow
For every deck-building request, follow this exact sequence. Do not skip the clarifying step or the preview step.
Step 1 — Ask the user about occasion and mood
Before reading any files, ask the user:
"Two quick questions before I pick a template:
- What's the occasion? (e.g. founder pitch, research synthesis, brand manifesto, classroom kickoff, etc.)
- What mood / vibe do you want? (e.g. confident & punchy, quiet & literary, warm & playful, dark & moody, etc.)"
Wait for the user's answer. Do not pick yet. Even if the brief seems obvious, ask — the user's taste often surprises in ways no inferred brief can capture.
Step 2 — Read index.json and pick 3 candidates
Read index.json at the repo root. Match the user's stated occasion + mood against each template's mood, tone, best_for, and formality. Pick three templates whose tones genuinely fit. The three should be different enough from each other that the user has a real choice — e.g. don't pick three editorial templates if the brief is editorial; pick one editorial, one warmer alternative, and one wildcard that re-interprets the brief.
Step 3 — Build a title-slide preview of each candidate
For each of the 3 candidates:
- Read the template's
template.htmlto learn its visual system. - Take the first slide only (the cover / title slide of that template).
- Replace the placeholder content with the user's actual deck topic / title / subtitle / author / date — i.e., make this preview real, not generic.
- Save the preview as a standalone HTML file in a temp folder, e.g.
previews/01-<slug>.html. Keep all sibling assets (styles.css,deck-stage.js, etc.) the template needs so the preview opens correctly.
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 First seen · 211 lines · 3,106 tokens per session scan A ed619bb7d956
beautiful-html-templates AGENTS.md is an instructions file published in the GitHub repository zarazhangrui/beautiful-html-templates (4,522 stars, last pushed 3mo ago), licensed MIT. It adds 3,106 tokens to every session, about $0.0155 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.