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 skills/aneja5/forge-skills/page-compositionnpx skills add aneja5/forge-skills --skill page-compositiongit clone --depth 1 https://github.com/aneja5/forge-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/aneja5/forge-skills/page-composition)<a href="https://agentmods.dev/skills/aneja5/forge-skills/page-composition"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/page-composition.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 5.1 | $0.00033 | $0.01613 |
| Opus 5 | $0.00016 | $0.00807 |
| Sonnet 5 | $0.00007 | $0.00323 |
| Haiku 4.5 | $0.00003 | $0.00161 |
Grade A, and why
page-composition 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Page Composition
Overview
Decide how pages are assembled from components: layout grid, page templates, responsive collapse strategy, navigation transformation per breakpoint, and content priority rules. Output is .forge/page-composition.md. Reads component-library (available pieces), design-system (breakpoints + spacing), and interaction-patterns (scroll, sticky, overlay behavior).
When to Use
- A product is about to start building pages and there's no named template vocabulary
- Routes have drifted into one-off layouts with no shared structure
- The sidebar collapses inconsistently on mobile (or doesn't collapse at all)
- A new responsive breakpoint is being added and nobody knows what should change
- A second product is joining the design system and needs to inherit layout conventions
When NOT to Use
- A single one-off marketing page — that's content, not composition
- Backend-only services with no UI
- A trivial layout fix inside one route —
incremental-implementation
Common Rationalizations
| Thought | Reality |
|---|---|
| "Every page is different" | Every page feels different, but most follow 3–4 templates. Name them and variation becomes predictable. |
| "We'll figure out responsive as we go" | "As we go" means the first 5 pages are desktop-only and mobile is retrofitted on day 10 under deadline pressure. |
| "Just make it responsive with Tailwind" | Tailwind handles the mechanics (sm:, md:, lg:). It doesn't decide what to do at each breakpoint. That's a design decision. |
| "Mobile can wait" | If field users open the product on phones, mobile IS the product. Desktop is the secondary experience. |
| "Sticky elements just work" | A sticky header that covers content on mobile is a bug. Sticky needs a rule. |
Red Flags
- A route with no defined template (a one-off layout)
- A sidebar that doesn't collapse on mobile (or hides instead of relocating)
- Content that disappears on small screens rather than relocating to a secondary tab/accordion
- Inconsistent grid usage across routes (12-col on one, free-flow on another)
- Scroll behavior differing between similar pages (infinite on one list, paginated on the next)
- Sticky element that covers content on mobile (header overlapping first row of a list)
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.
- 2d ago First seen · 128 lines · 33 tokens per session scan A 2e79db1f89d7
page-composition is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 1,613 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
migrate-bootstrap
Migrates a traditional Power Pages site from Bootstrap 3 to Bootstrap 5. Downloads the site, runs the pac pages bootstrap-migrate engine, reviews the change report, applies AI-assisted fixes for the residual hierarchy/CSS changes the engine only flags, uploads the migrated site (which auto-enables the Bootstrap 5…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
micro-interactions
Micro-interactions are small, purposeful animations and responses that reward the user and make the interface feel alive — an animated icon, a satisfying toggle, a subtle reveal. Borrowed from the natural world, they add delight without distraction. Use when designing interactive components, success states, toggles…
elevation-and-depth
Elevation — subtle shadows and layering — communicates visual hierarchy by lifting elements above the surface. Combined with border-radius, it creates the tactile quality of cards, modals, and interactive surfaces. Use when designing cards, dropdowns, modals, tooltips, or any floating UI element.
loading-states-and-perceived-performance
Manage user expectations during wait times with appropriate loading states — from simple spinners to complex skeleton screens and staggered animations. Perceived performance is often more important than actual load time. Use when designing data-heavy components, handling API calls, building hero sections, or improving…