Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Aysnc-Labs/angoranpx agentmods add skills/aysnc-labs/angora/angora-compose-pageWrote 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/aysnc-labs/angora/angora-compose-page)<a href="https://agentmods.dev/skills/aysnc-labs/angora/angora-compose-page"><img src="https://agentmods.dev/badge/skills/aysnc-labs/angora/angora-compose-page/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/aysnc-labs/angora/angora-compose-page"><img src="https://agentmods.dev/badge/skills/aysnc-labs/angora/angora-compose-page.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 | $0.00145 | $0.02448 |
| Opus 5.5 | $0.00058 | $0.00979 |
| Sonnet 5.5 | $0.00029 | $0.00490 |
| Haiku 4.5 | $0.00015 | $0.00245 |
Grade A, and why
angora-compose-page 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 2mo 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose Page: $ARGUMENTS
Build or update a full site page from approved components. Pages are living documents — this skill handles both creation and evolution.
Scope
This skill does two things:
- Design system layouts — full-page compositions in
src/pages/design-system/layouts/using real components with placeholder content. These are specimens, not production pages. - Site pages — real routes in
src/pages/with production content, database queries, SEO, and site layout wrappers.
Intent check: When the user says "update the home page" or similar, clarify before proceeding: "Do you mean the home layout in the design system (/design-system/layouts/home), or the actual website home page at src/pages/index.astro?"
Before you start
- Read
src/system.md— intent, accessibility standard, anti-patterns. - Read
src/styles/global.css— available tokens for page-level spacing and backgrounds. All color references must use semantic token utilities — raw palette classes don't exist. - Read design-principles.md — especially Spacing & Layout, Dark Mode, and Finishing Touches sections.
- Read tailwind-conventions.md — Tailwind v4 syntax rules.
- Inventory components — list
src/components/*.astroto know what's available. Only use approved, built components. - Read
src/components/Section.astro— understand the Section pattern before composing pages. Section accepts:seamless,fullWidth(drops flow width constraint),narrow(constrains to--container-narrow),withWrap(re-constrains children of full-width sections),withPadding(adds vertical padding without seamless),title(renders<h2>with automaticaria-labelledby). - Check for wireframe — look for
src/pages/design-system/wireframes/<page-name>.astro. If it exists, read it — especially the data source annotations in frontmatter. - Check for layout — look for
src/pages/design-system/layouts/<page-name>.astro. If a layout exists, it's an approved composition showing how components assemble for this page. Use it as the reference — match its section order, component choices, and visual rhythm. The real page replaces placeholder content with real data but follows the same structure. - Check for existing page — look for
src/pages/<page-name>.astro. If it exists, read it first. This is an evolution, not a rewrite. - Check for site layout — look in
src/layouts/for existing site layouts (header/footer wrappers).
What ships with it
1 file 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.
- 2mo ago First seen · 156 lines · 145 tokens per session scan A cfd14e4a6f31
angora-compose-page is a skill published in the GitHub repository Aysnc-Labs/angora (6 stars, last pushed 6mo ago), licensed MIT. It adds 145 tokens to every session and 2,448 once invoked, about $0.0006 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 2026-08-31.
angora-compose-page compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| angora-compose-pageAysnc-Labs/angora | Skill | 6 | 6mo ago | MIT | A | 145 | Claude Code |
| component-family-consistencydembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 38 | Claude Code |
| extract-designdembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 43 | Claude Code |
| data-display-and-selectiondembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 37 | Claude Code |
| information-architecturedembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 33 | Claude Code |
| modal-and-overlay-patternsdembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 38 | Claude Code |
| algorithmic-color-palettedembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 40 | Claude Code |