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 skills add Yesterday-AI/skills --skill yesterday-pagesgit clone --depth 1 https://github.com/Yesterday-AI/skillsWrote 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/skills/yesterday-ai/skills/yesterday-pages)<a href="https://agentmods.dev/skills/yesterday-ai/skills/yesterday-pages"><img src="https://agentmods.dev/badge/skills/yesterday-ai/skills/yesterday-pages/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/skills/yesterday-ai/skills/yesterday-pages"><img src="https://agentmods.dev/badge/skills/yesterday-ai/skills/yesterday-pages.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 | $0.00050 | $0.00786 |
| Opus 5.5 | $0.00020 | $0.00314 |
| Sonnet 5.5 | $0.00010 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
yesterday-pages 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 6d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yesterday Pages
Principle
Choose the form from the message. Build one clear information experience, not a decorated document.
Read brand.md before designing. Use assets/foundation.css as the token source; take only the rules the output needs.
Autonomy
Complete the work in one run: specify, review, decide, build, render, revise, deliver.
Do not ask the user to select a type, approve an outline, choose an interaction, or review a draft. Infer those decisions from audience, material, and outcome. If input is incomplete, proceed with stated assumptions and disclose unavailable sources in the handoff.
Route
Select one leading type. A page may borrow supporting patterns, but must keep one dominant reading mode and one signature interaction.
| Type | Choose when | Read exactly this reference |
|---|---|---|
| Editorial / Whitepaper | Evidence, argument, comparison, research, analysis, offer | editorial.html |
| Visual Story | Supplied images carry part of the argument | visual-story.html |
| Interactive Explainer / Prototype | Understanding improves through changing state or trying a mechanism | interactive-explainer.html |
References demonstrate composition and behavior. Do not clone their page structure or sample content.
Workflow
- Inspect every supplied source. For image folders, inventory subject, orientation, visual weight, negative space, and semantic fit.
- Write a compact internal brief: audience, single thesis, desired action, evidence hierarchy, leading type, signature interaction.
- Review the brief against source and audience; decide, then outline the scan path. Remove repetition and unsupported claims. Preserve links and uncertainty.
- Build semantic HTML with inline CSS and vanilla JavaScript. Default to one responsive
.htmlfile; keep supplied images in a relative asset folder. Use the official wordmark fromassets/yesterday-wordmark.svg. - For data, choose the chart from the claim. Prefer accessible inline SVG, direct labels,
<title>,<desc>, and a visible takeaway. Interaction may reveal detail, never the core finding. - Use motion only for sequence, causality, change, or state. Support
prefers-reduced-motion. Make every control keyboard-operable and visibly focused. - Render, inspect, and revise using quality.md. Deliver only the finished artifact and a concise handoff.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 61 lines · 50 tokens per session scan A 9cabb36ddc25
yesterday-pages is a skill published in the GitHub repository Yesterday-AI/skills (2 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 786 once invoked, about $0.0002 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 2026-10-14.
Other skills, from other repositories
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…
design-review
Five-dimension design audit (frontend UI/UX · server data-model & flow · endpoint spec · daemon-runtime/SDK & local-cache-first · built-in skill/agent-role), executed by a NON-implementing agent. Every dimension gets a verdict; N/A only with a stated reason. A dimension the design silently skipped must be surfaced as…
web-artifacts-builder
Suite of tools for creating elaborate, multi-component Prismer HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
baoyu-design
Create polished design artifacts as self-contained HTML: UI mockups, interactive prototypes, wireframes, landing pages, dashboards, app screens, mobile apps, slide decks (a.k.a. PPT / PowerPoint presentations), documents and résumés, animations, 3D objects, research reports, HTML email, diagrams, fliers, and visual…
ui-designer/design-system
A shared set of rules for a product’s visual design, covering colors, fonts, spacing, corner shapes, shadows, and animations.