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 agentmods add skills/znlgis/my-opencode-deepseek-config/prototypenpx skills add znlgis/my-opencode-deepseek-config --skill prototypegit clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-configWrote 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/znlgis/my-opencode-deepseek-config/prototype)<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/prototype"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/prototype.svg" alt="Measured on agentmods" 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 | $0.00095 | $0.00623 |
| Opus 5 | $0.00048 | $0.00311 |
| Sonnet 5 | $0.00019 | $0.00125 |
| Haiku 4.5 | $0.00010 | $0.00062 |
Grade A, and why
prototype 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 3d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype
Settle a design question empirically with the cheapest runnable artifact, then throw it away. A prototype is evidence, not product code.
When to use
- A logic/behavior question: "does this flow work end-to-end?"
- A UI question: "which layout/style variant is better?"
- You are about to write a spec or have a long back-and-forth over a decision that a 5-minute demo would settle.
Not for: building real features (use deep-worker), or questions answerable
by reading (use explore).
The two kinds
| Question type | Build |
|---|---|
| Logic / behavior | a single self-contained HTML file with inline JS that interactively demonstrates the logic end-to-end |
| UI / style | one route with 2–3 style/layout variants rendered side by side (or toggled), so the choice is visible, not argued |
Iron rules
- One day, one use. The artifact is thrown away; do not extend or maintain it.
- One command to run.
open prototype.html(or equivalent); no build step, no dependencies, no framework. - No persistence. No backend, no DB, no localStorage (unless the prototype is about persistence itself).
- Skip polish. No design system, no tests, no error handling beyond what the demo needs. Fake data is fine.
- Show state after every action. After each interaction, render the current state so the behavior is observable, not inferred.
Workflow
- State the design question in one sentence.
- Pick the kind (logic vs UI).
- Build the single HTML file in the working tree.
- Run it (open in browser); confirm it demonstrates the answer.
- Show the result to the user; capture the decision.
- Commit to a throwaway branch as the primary source (e.g.
git checkout -b throwaway/prototype-<topic>), then discard after the decision is recorded.
Rules
- Never let a prototype silently become production code.
- If the question is still open after the demo, that is the answer: it was the wrong question — rephrase, do not extend the prototype.
- Keep the artifact self-contained; no external CDN unless strictly required.
- Record the decision (and the prototype's path) in the relevant plan/spec, not in the prototype.
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.
- 3d ago First seen · 59 lines · 95 tokens per session scan A 4192d619646b
prototype is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed 5d ago), licensed MIT. It adds 95 tokens to every session and 623 once invoked, about $0.0005 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
image-generator
Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.
weibo-poster
微博内容创作 - 140字优化、话题热搜、@提及策略、配图描述、发布时机.
xiaohongshu-writer
小红书笔记写作助手 - 标题优化、emoji策略、话题标签、封面文案、笔记结构.
excel-helper
Excel 表格助手 - 公式编写、数据透视表、图表可视化、宏自动化、数据清洗.
word-writer
Word 文档助手 - 文章撰写、格式排版、模板选择、目录生成、批量处理.
code-mate-antigravity
Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.