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/tdimino/claude-code-minoannpx agentmods add skills/tdimino/claude-code-minoan/image-wellWrote 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/tdimino/claude-code-minoan/image-well)<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/image-well"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/image-well/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/tdimino/claude-code-minoan/image-well"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/image-well.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 52 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00110 | $0.01458 |
| Opus 5 | $0.00055 | $0.00729 |
| Sonnet 5 | $0.00022 | $0.00292 |
| Haiku 4.5 | $0.00011 | $0.00146 |
Grade A, and why
image-well 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 10d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Well
Search and download images from 15 sources through a single CLI. Seven sources work with zero API keys (Openverse, Wikimedia, Met Museum, Cleveland Museum, Art Institute of Chicago, Getty Museum, NASA). Additional sources activate when keys are set.
Quick Start
# Search across all no-key sources
uv run ~/.claude/skills/image-well/scripts/well.py search "ancient Minoan fresco"
# Use a preset for domain-specific searches
uv run ~/.claude/skills/image-well/scripts/well.py search "F-35 fighter jet" --preset military
# Download results with metadata sidecars
uv run ~/.claude/skills/image-well/scripts/well.py search "sunset" --format download --output ./images/
# Check which sources are available
uv run ~/.claude/skills/image-well/scripts/well.py sources
# Visual HTML preview — opens in browser, no context pollution
uv run ~/.claude/skills/image-well/scripts/well.py search "bronze statue" --format html
# Output as JSON for piping
uv run ~/.claude/skills/image-well/scripts/well.py search "cat" --format json
Sources
| Tier | Source | Key Required | License |
|---|---|---|---|
| 1 | Openverse (800M+) | No | CC variants |
| 1 | Wikimedia Commons | No | CC variants |
| 1 | Met Museum (375k) | No | CC0 |
| 1 | Cleveland Museum (37k) | No | CC0 |
| 1 | Art Inst. Chicago (60k+) | No | Public Domain |
| 1 | Getty Museum (Open Content) | No | CC0 |
| 1 | NASA (140k) | No | Public Domain |
| 2 | Pexels | PEXELS_API_KEY |
Pexels License |
| 2 | Pixabay | PIXABAY_API_KEY |
Pixabay License |
| 2 | Rijksmuseum (700k) | RIJKSMUSEUM_API_KEY |
CC0 |
| 2 | Unsplash | UNSPLASH_ACCESS_KEY |
Unsplash License |
| 3 | Smithsonian | No | CC0 |
| 3 | Europeana (50M+) | EUROPEANA_API_KEY |
Mixed |
| 3 | Iconify (275k icons) | No | Various |
| 3 | Pollinations AI | No | Free Use (AI gen) |
Add Tier 2 keys to ~/.config/env/secrets.env for expanded coverage.
Source notes:
- Cleveland downloads the ~3400px print JPEG; the ~900px web derivative is the thumbnail. The archival TIFFs are never fetched.
- Art Institute of Chicago images are public domain (
PD), not formally CC0 —--license cc0accepts them. Downloads use AIC's preferred 843px IIIF size and are serialized (1/s) per their API etiquette. - Getty rides the collection website's undocumented JSON search API (
open_content=truefilter) — the only keyword-search surface Getty exposes. Every emitted row is gated on the CC0 URI in its IIIF manifest license; downloads at 1200px IIIF. Superb Greek/Roman/Etruscan; thin on Egypt/Near East.
What ships with it
20 files 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.
- README.md 9.4 KB
- scripts/_well_utils.py 26 KB runs code
- scripts/sources/__init__.py 2.5 KB runs code
- scripts/sources/artic.py 3.9 KB runs code
- scripts/sources/base.py 1.8 KB runs code
- scripts/sources/cleveland.py 3.9 KB runs code
- scripts/sources/europeana.py 3.3 KB runs code
- scripts/sources/getty.py 3.6 KB runs code
- scripts/sources/iconify.py 2.3 KB runs code
- scripts/sources/met_museum.py 3.7 KB runs code
- scripts/sources/nasa.py 3.0 KB runs code
- scripts/sources/openverse.py 2.8 KB runs code
- scripts/sources/pexels.py 2.2 KB runs code
- scripts/sources/pixabay.py 2.3 KB runs code
- scripts/sources/pollinations.py 2.2 KB runs code
- scripts/sources/rijksmuseum.py 2.5 KB runs code
- scripts/sources/smithsonian.py 5.1 KB runs code
- scripts/sources/unsplash.py 2.6 KB runs code
- scripts/sources/wikimedia.py 2.9 KB runs code
- scripts/well.py 12 KB runs code
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.
- 10d ago First seen · 124 lines · 110 tokens per session scan A 687b3bdc56c5
image-well is a skill published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed 2d ago), licensed MIT. It adds 110 tokens to every session and 1,458 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
art-director
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
app-builder
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…
fish-audio
Generate expressive audio clips using Fish Audio S2 TTS with bracket emotion tags. Record voice memos, narration, audio messages, or any spoken content.
voice-setup
Complete voice configuration in chat - desktop Talk and PTT shortcuts, microphone permissions, ElevenLabs/Deepgram TTS, and troubleshooting.
vellum-avatar
Customize the assistant's avatar - build a native character, upload an image, or generate one with AI.