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 patriceckhart/zot --skill write-zot-themesgit clone --depth 1 https://github.com/patriceckhart/zotWrote 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/patriceckhart/zot/write-zot-themes)<a href="https://agentmods.dev/skills/patriceckhart/zot/write-zot-themes"><img src="https://agentmods.dev/badge/skills/patriceckhart/zot/write-zot-themes/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/patriceckhart/zot/write-zot-themes"><img src="https://agentmods.dev/badge/skills/patriceckhart/zot/write-zot-themes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.02259 |
| Opus 5 | $0.00012 | $0.01130 |
| Sonnet 5 | $0.00005 | $0.00452 |
| Haiku 4.5 | $0.00002 | $0.00226 |
Grade A, and why
write-zot-themes 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- write-terva-themes — 88% identical, 58 lines differ
How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing zot themes
Use this skill when the user asks for help creating, editing, installing, debugging, or packaging a zot color theme. Read this skill before generating a theme file or advising on theme extension layout.
What a zot theme is
A zot theme is a JSON file that overrides any subset of zot's built-in light/dark theme values. Theme files are intentionally permissive: nothing is required. A file may contain only colors, only spinner settings, only syntax colors, or only metadata. Missing values always inherit from the built-in detected light/dark default.
User themes are discovered from:
$ZOT_HOME/themes/*.json
Extension themes are discovered in-place from loaded extension dirs:
$ZOT_HOME/extensions/<extension>/theme.json
$ZOT_HOME/extensions/<extension>/themes/theme.json
<project>/.zot/extensions/<extension>/theme.json
<project>/.zot/extensions/<extension>/themes/theme.json
zot does not copy extension themes into $ZOT_HOME/themes; extension
owned themes stay in the extension directory. The settings picker stores
an absolute path for extension-owned themes and loads that file directly.
Minimal examples
Empty / metadata-only theme
Valid; inherits all colors/spinner/syntax from zot defaults.
{
"name": "my-theme",
"description": "Metadata only; all visuals inherit zot defaults."
}
Change one color for both light and dark
{
"name": "pink-accent",
"colors": {
"accent": 204
}
}
Change one color per mode
{
"name": "split-accent",
"colors": {
"dark": { "accent": 204 },
"light": { "accent": 161 }
}
}
Spinner-only theme
Top-level spinner overrides are valid and apply to both modes.
{
"name": "custom-spinner",
"description": "Only changes the busy spinner.",
"spinner_frames": ["◢", "◣", "◤", "◥"],
"spinner_messages": ["working"],
"spinner_interval_ms": 120
}
Dark-only theme also works in light terminals
If colors.light is missing, zot applies colors.dark overrides on
top of the built-in light default when running in light mode. The
inverse is also true: if dark is missing but light exists, light
settings are used on dark defaults.
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 · 341 lines · 23 tokens per session scan A 92a676079f48
write-zot-themes is a skill published in the GitHub repository patriceckhart/zot (336 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 2,259 once invoked, about $0.0001 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
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.
dataviz
Design guidance for charts, graphs, dashboards, maps, and data visualizations, including a local palette validator.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.