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 Aysnc-Labs/angora --skill angora-mediagit clone --depth 1 https://github.com/Aysnc-Labs/angoraWrote 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-media)<a href="https://agentmods.dev/skills/aysnc-labs/angora/angora-media"><img src="https://agentmods.dev/badge/skills/aysnc-labs/angora/angora-media/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-media"><img src="https://agentmods.dev/badge/skills/aysnc-labs/angora/angora-media.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 | $0.00153 | $0.00776 |
| Opus 5 | $0.00077 | $0.00388 |
| Sonnet 5 | $0.00031 | $0.00155 |
| Haiku 4.5 | $0.00015 | $0.00078 |
Grade A, and why
angora-media 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 12d 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.
What it actually says
Media
Process images from the inbox/ directory into the media system.
Before you start
- Check inbox contents — list
inbox/directory. If empty (only.gitkeep), report "Inbox is empty. Drop images intoinbox/and run this again." - Check current media table — run:
node -e "
import db from './src/data/db.ts';
import { media } from './src/data/schema/tables/media.ts';
const rows = db.select().from(media).all();
console.table(rows);
"
Pipeline (for each image)
1. Visual analysis
Read the image file with the Read tool (Claude vision). Write alt text:
- Describe what's in the image, under 125 characters
- Don't start with "Image of" or "Photo of"
- Use
alt=""for purely decorative images (backgrounds, dividers)
2. Read dimensions
node -e "
import { imageSize } from 'image-size';
const result = imageSize('inbox/<filename>');
console.log(JSON.stringify(result));
"
Skip for SVGs (scalable — dimensions not meaningful).
3. Generate unique filename
node -e "
import { nanoid } from 'nanoid';
console.log(nanoid(8));
"
Preserve the original extension. Result: V1StGXR8.jpg
4. Move file
mv inbox/<original> public/media/<nanoid>.<ext>
5. Insert into media table
node -e "
import db from './src/data/db.ts';
import { media } from './src/data/schema/tables/media.ts';
db.insert(media).values({
path: 'media/<nanoid>.<ext>',
alt: '<alt text>',
type: 'image',
width: <width>,
height: <height>,
sourceName: '<original filename>',
}).run();
console.log('Inserted.');
"
6. Summary table
After processing all images, show a summary:
| Original | New path | Dimensions | Alt text |
|---|---|---|---|
| hero-bg.jpg | media/V1StGXR8.jpg | 1920x1080 | Dark gradient background with subtle grid pattern |
Rules
- Supported types: jpg, jpeg, png, gif, webp, avif, svg
- SVGs: skip dimension reading (scalable), set type to
svg - Never delete inbox files without explicit permission — ask after processing
- Skip non-image files — report them: "Found non-image files: [list]. These can be processed with the import skill (
/angora-import)." - Process images one at a time to ensure accuracy of alt text
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.
- 12d ago First seen · 93 lines · 153 tokens per session scan A 55f599834b18
angora-media is a skill published in the GitHub repository Aysnc-Labs/angora (6 stars, last pushed 4mo ago), licensed MIT. It adds 153 tokens to every session and 776 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
brand-visual-language
A brand's visual tone — playful or serious, rounded or angular — should be consistent across all UI elements. Shape language in typography, border-radius, and iconography communicates personality before a single word is read. Use when establishing a design system, choosing icon libraries, setting border-radius tokens…
data-display-and-selection
Complex data deserves multiple view modes — grid, list, table — chosen by the user based on their task. Row and item selection should use large hit areas (the whole row or card, not just a checkbox). Selected state is communicated through a subtle background colour shift. Mass actions appear when items are selected.…
generate-ui-from-brand
Pipeline skill — turns a URL or DESIGN.md into a concrete UI structure with decisions already made. Extracts live design tokens, normalizes them into a semantic system, applies UX principles, and outputs an actionable UI spec. Use when building UI for an existing brand from scratch, auditing a design system, or…
information-architecture
In large applications, information architecture determines whether users can find, understand, and act on data. Naming matters. The UI should mirror the data model and signal how data can be transformed. Dangerous or irreversible changes always require a confirm dialog. Use when designing navigation, naming entities…
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…
modal-and-overlay-patterns
Overlays — modals, drawers, bottom sheets, popovers — interrupt or augment the main flow. Each type has a different scope, blocking level, and appropriate use case. Use when designing dialogs, confirmation prompts, side panels, action sheets, or any UI element that appears above the main content layer.