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-wireframeWrote 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-wireframe)<a href="https://agentmods.dev/skills/aysnc-labs/angora/angora-wireframe"><img src="https://agentmods.dev/badge/skills/aysnc-labs/angora/angora-wireframe/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-wireframe"><img src="https://agentmods.dev/badge/skills/aysnc-labs/angora/angora-wireframe.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 | $0.00142 | $0.01277 |
| Opus 5.5 | $0.00057 | $0.00511 |
| Sonnet 5.5 | $0.00028 | $0.00255 |
| Haiku 4.5 | $0.00014 | $0.00128 |
Grade A, and why
angora-wireframe 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wireframe: $ARGUMENTS
Sketch page structure (hierarchy, layout, flow) before committing to visual design.
Before you start
- Read
src/system.md— intent and scope. - Read
src/styles/global.css— know the container max-width and spacing tokens. - Check if the wireframe already exists — look for
src/pages/design-system/wireframes/<page-name>.astro. If it exists, read it first.
Ask: format preference
Use AskUserQuestion to ask the user which wireframe format they prefer:
- ASCII — wireframe stored as ASCII art in a
<pre>block. ~100-200 tokens per page. Best for fast iteration. - Visual — wireframe rendered as gray Tailwind boxes (
bg-muted border border-border, placeholder text). More visual but more tokens.
Output files
- Design system page —
src/pages/design-system/wireframes/<page-name>.astro(usingLayoutfrom_layout/)
No full-screen view needed — wireframes are working docs, not deliverables.
Steps
- Ask format — ASCII or Visual (see above).
- Sketch — create the wireframe page showing page structure: header, hero, sections, footer. Use placeholder text and rough proportions.
- Visual review — user opens page in browser (
pnpm dev). The sidebar auto-discovers wireframe pages viaimport.meta.glob— no manual nav registration needed. Approves or iterates. - Iterate — ask user for feedback ("move CTA above fold", "make it 3 columns", etc.) and update the wireframe.
- Notes — ask if they want to save notes with the wireframe (intent, constraints, open questions).
- Data sources — walk through each section and capture data source decisions.
ASCII format
Use a <pre> block with monospace box-drawing to show page structure:
<pre class="font-mono text-sm leading-relaxed text-muted-foreground">
┌─────────────────────────────────────┐
│ Logo Nav Nav [CTA] │
├─────────────────────────────────────┤
│ │
│ Hero Headline │
│ Subhead text │
│ [ Primary ] [ Secondary ] │
│ │
├─────────────────────────────────────┤
│ Feature 1 │ Feature 2 │ Feat 3│
└─────────────────────────────────────┘
</pre>
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 · 125 lines · 142 tokens per session scan A 56072a80da6d
angora-wireframe is a skill published in the GitHub repository Aysnc-Labs/angora (6 stars, last pushed 6mo ago), licensed MIT. It adds 142 tokens to every session and 1,277 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-wireframe compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| angora-wireframeAysnc-Labs/angora | Skill | 6 | 6mo ago | MIT | A | 142 | 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 |
| modular-scale-typographydembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 34 | Claude Code |
| data-display-and-selectiondembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 37 | Claude Code |
| design-dnazanwei/design-dna | Skill | 2.1k | 2mo ago | MIT | A | 192 | Claude Code, Codex |
| information-architecturedembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 33 | Claude Code |