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 opensolon/soloncode --skill soloncode-skin-skillgit clone --depth 1 https://github.com/opensolon/soloncodeWrote 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/opensolon/soloncode/soloncode-skin-skill)<a href="https://agentmods.dev/skills/opensolon/soloncode/soloncode-skin-skill"><img src="https://agentmods.dev/badge/skills/opensolon/soloncode/soloncode-skin-skill/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/opensolon/soloncode/soloncode-skin-skill"><img src="https://agentmods.dev/badge/skills/opensolon/soloncode/soloncode-skin-skill.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 | $0.00078 | $0.03404 |
| Opus 5.5 | $0.00031 | $0.01362 |
| Sonnet 5.5 | $0.00016 | $0.00681 |
| Haiku 4.5 | $0.00008 | $0.00340 |
Grade A, and why
soloncode-skin-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SolonCode Skin Generator
根据用户自然语言需求，生成可直接上传安装的 SolonCode Web 皮肤 Zip。
目标产物始终是可安装的 zip（默认 .uploads/{name}-yyyyMMddHH.zip），不是零散 CSS 片段。
作用范围：仅 SolonCode Web UI 皮肤系统。
禁止：改 soloncode-desktop；生成 js/html/svg/可执行文件；使用保留名。
When to Use
- 「做个皮肤 / 生成 skin / 换肤 / 主题包」
- 「设置面板加背景 / 像 ddd 那样」
- 「海洋/极光/护眼/高对比风格」
- 「欢迎页别太空 / 主区氛围图」
- 「根据 skin.md / skin-spec 出 zip」
Critical Rules
- 交付物必须是 zip：至少含
skin.json+skin.css。 name合法：^[a-zA-Z0-9][a-zA-Z0-9_-]{0,63}$，且不是default/eyecare/contrast。- 选择器绑定 name：
[data-skin="{name}"][data-theme="light|dark"]，light/dark 成对；模板 id 必须改干净。 - 图片只写包内相对路径：优先
url("./assets/...")；禁止..与绝对路径；不推荐外链。 - 列表预览固定
preview.png（不要只给 webp/jpg）。 - 限制：zip ≤ 8MB；单资源 ≤ 2MB（仅
skin.css例外；skin.json也算资源）；解压总量 ≤ 32MB。 - 可读性优先：输入框/正文/代码块必须可读；功能色（success/danger/git）默认不动。
- 不要臆造 token：当前无
--bg-welcome-image等官方欢迎区槽位。 - 无可靠位图能力时用 CSS 渐变；有 Pillow 时用本 skill 的
gen_bg.py/gen_preview.py。 - 详细规范按需加载：
references/skin-spec.md。
Progressive Loading
| 需要时 | 读取 / 执行 |
|---|---|
| 完整规范 / 变量表 / 排障 | references/skin-spec.md |
| 一键生成（推荐） | scripts/make_skin.py |
| 脚手架 | scripts/scaffold_skin.py |
| 预览图 | scripts/gen_preview.py |
| 有结构背景图 | scripts/gen_bg.py |
| 模板 A/B/C/D | assets/templates/{minimal-accent,ocean-gradient,settings-panel,full-theme}/ |
| 校验 | scripts/validate_skin.py |
| 打包 | scripts/pack_skin.py |
脚本路径：先定位本 skill 根目录，再 python3 scripts/...。
依赖：校验/打包仅需标准库；生成 PNG 需要 Pillow（pip install pillow）。
Workflow
0. 优先一键（Agent 默认路径）
用户给了风格词时，直接：
python3 scripts/make_skin.py \
--name aurora \
--recipe c \
--theme aurora \
--display-name "极光设置" \
--with-assets \
--force
# 默认产出：.uploads/aurora-yyyyMMddHH.zip（如 aurora-2026071715.zip）
| 参数 | 说明 |
|---|---|
--name |
皮肤 id |
--recipe |
a/b/c/d/e/f |
--theme |
ocean/forest/aurora/ink/warm/pink/business |
--with-assets |
配方 C/D 生成有结构 PNG 并写入 url("./assets/...") |
--no-preview |
跳过 preview.png（默认会生成） |
--work-dir |
保留工作目录便于再改 |
-o |
输出 zip（默认 .uploads/{name}-yyyyMMddHH.zip，避免覆盖冲突） |
What ships with it
16 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.
- assets/templates/full-theme/skin.css 4.0 KB
- assets/templates/full-theme/skin.json 224 B
- assets/templates/minimal-accent/skin.css 564 B
- assets/templates/minimal-accent/skin.json 183 B
- assets/templates/ocean-gradient/skin.css 1.6 KB
- assets/templates/ocean-gradient/skin.json 182 B
- assets/templates/README.md 1.4 KB
- assets/templates/settings-panel/skin.css 3.2 KB
- assets/templates/settings-panel/skin.json 227 B
- references/skin-spec.md 36 KB
- scripts/gen_bg.py 7.6 KB runs code
- scripts/gen_preview.py 6.1 KB runs code
- scripts/make_skin.py 4.0 KB runs code
- scripts/pack_skin.py 5.3 KB runs code
- scripts/scaffold_skin.py 18 KB runs code
- scripts/validate_skin.py 14 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.
- 1mo ago First seen · 266 lines · 78 tokens per session scan A fa76b8262e74
soloncode-skin-skill is a skill published in the GitHub repository opensolon/soloncode (197 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 3,404 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
ph-git
(PH) Use only for an explicit Git operation with scoped status, diff, and transport discipline.
ph-deep-interview
(PH) Resolve material product uncertainty with evidence-based, answer-dependent questions; skip facts and decisions already established.
ph-philosophy-refinement
(PH) Use only when the user explicitly asks to change, review, or persist reusable development philosophy.
ph-programming
(PH) Use for a clear scoped implementation request; inspect local conventions and verify only the requested change.
ph-grill-me
(PH) Pressure-test a concrete decision, design, or plan only when the user asks to examine assumptions, alternatives, risks, or trade-offs.
ph-implementation
(PH) Use for concrete implementation authorized by the user's request or an accepted plan, with focused verification.