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 jxoesneon/Ciel --skill hermes-cli-skinninggit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/hermes-cli-skinning)<a href="https://agentmods.dev/skills/jxoesneon/ciel/hermes-cli-skinning"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/hermes-cli-skinning/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/jxoesneon/ciel/hermes-cli-skinning"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/hermes-cli-skinning.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 | $0.00041 | $0.00946 |
| Opus 5 | $0.00020 | $0.00473 |
| Sonnet 5 | $0.00008 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
hermes-cli-skinning scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
dependencies: { skills: [], mcp: [], system: ["python3", "curl"] } How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CIEL ADAPTATION: Hermes CLI Skinning
This skill converts any reference image into a complete CLI skin with an image-derived banner in rich markup ([#rrggbb]char[/] runs). While originally built for Hermes CLI, the image-to-ASCII pattern is reusable for any CLI banner system — the density ramp, luminance mapping, and run-length rich-markup compression are platform-agnostic primitives.
When to Use
- User asks for a theme/skin based on an image ("make my terminal look like this artwork").
- Existing skins are palette-only; this adds true pictorial banner art.
- Any CLI theming task requiring image-to-ASCII conversion with color preservation.
Procedure
- Gather inputs: Reference image URL/path + theme identity (name, persona, accent hues). Download locally:
curl -fsSL URL -o /tmp/ref.jpg. - Palette extraction: Read dominant hues (vision or quantize to ~8 colors). Derive: background (darkest), accent (most vivid), text (lightest), plus semantic ok/warn/error.
- Convert — Option A (fast preview):
brew install TheZoraiz/ascii-image-converter; ascii-image-converter ref.jpg -d 64,60 --save-txt out/. ANSI truecolor output — use Option B for final artifact. - Convert — Option B (recommended Pillow pipeline):
- Resize to W columns (~64) × round(W × h/w × 0.5) rows (terminal cells are ~2x tall).
- Quantize to 24 colors (
Image.quantize(method=MEDIANCUT)) for compact YAML (~26KB at 64×57). - Map luminance (0.2126R+0.7152G+0.0722B) onto ramp
" .:-=+*#%@". - Emit run-length rich markup: consecutive same-char+same-color cells become one
[#hex]ccc[/]run.
- Write the skin: Full schema with all
colorskeys present,backgroundset,ui_accent≥ 4.5:1 vs background. Inject art underbanner_hero: |-indented exactly 2 spaces. - Validate + activate:
python3 -c "import yaml; yaml.safe_load(open(skin_path))"thenhermes config set display.skin <name>.
I/O Contract
- Input: image path/URL, skin name, optional persona notes.
- Output: skin YAML path, activation status, optional preview PNG.
- Idempotent: yes — re-running overwrites the same skin file.
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.
- 8d ago First seen · 56 lines · 41 tokens per session scan A eeefaadcad29
hermes-cli-skinning is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 41 tokens to every session and 946 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
slidev
Use when the user wants to create slides, build a presentation or talk, make a deck or pitch, export slides to PDF, work with an existing slides.md, run slidev dev mode, or build a static slide site. Also applies when the user mentions "presentation", "keynote", "talk", "lecture", "deck", "slide deck", or asks to turn…
screenshot-automation
Automatically captures, crops, and beautifies screenshots from URLs for your portfolio or docs.
automated-video-marketing-asset
Stop editing videos manually. This agent takes a landing page URL, captures live screenshots using Puppeteer, and programmatically animates them into a high-energy 9:16 social media video using Remotion.
avatar-video-producer
AI Avatars need more than just text; they need gestures and timing. This agent takes a list of topics and generates casual, 'Avatar-Ready' scripts with gestural commands (e.g., [nod], [point], [pause]).
brand-kit-gen
Instantly create cohesive visual identity starter kits for multiple projects. This agent generates logos, seamless background patterns, and defines color palettes for an entire portfolio of brands.
video-frames
Extract frames or short clips from videos using ffmpeg.