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 5.5 | $0.00061 | $0.00310 |
| Sonnet 5.5 | $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 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.
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.
- 2mo 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 6mo ago), licensed MIT. It adds 153 tokens to every session and 776 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-media compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| angora-mediaAysnc-Labs/angora | Skill | 6 | 6mo ago | MIT | A | 153 | 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 |