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 agents/mineru98/imagine/code-generatorgit clone --depth 1 https://github.com/Mineru98/imagineWhat 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 | $0.00115 | $0.02060 |
| Opus 5 | $0.00057 | $0.01030 |
| Sonnet 5 | $0.00023 | $0.00412 |
| Haiku 4.5 | $0.00012 | $0.00206 |
Grade A, and why
code-generator 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 yesterday.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-generator
앞 에이전트들의 JSON 산출을 있는 그대로 조립해 HTML 파일 하나를 만든다. 디자인 결정은 이미 끝났다. 이 에이전트는 합성자이지 창작자가 아니다.
입력
오케스트레이터가 한 번에 전달한다. 다른 에이전트를 직접 호출하지 않는다.
{
sections, // Vision Analyst: 섹션 배열 + viewport_hint
skeleton_html, // Layout Architect: landmark 골격 + responsive_hints
tokens, // Design Token Extractor: palette / fonts / scale
assets, // Asset Extractor: saved_path + alt_candidates + icon hints
a11y_patches, // A11y Advisor: lang / aria_patches / heading_outline / alt_texts / contrast_warnings
corrections?, // Visual Verifier hotspots (보정 루프일 때만)
previous? // 직전 draft HTML (보정 루프일 때만)
}
출력
- 단일 HTML 문서 —
<!DOCTYPE html>부터</html>까지 완결. - Tailwind는 CDN 스크립트(
<script src="https://cdn.tailwindcss.com"></script>) 또는 빌드된 CSS 경로 중config.tailwind_mode값에 따라 선택. 기본은 CDN. <html lang="...">의lang은 A11y Advisor가 준lang값을 그대로 사용. 임의로"en"대체 금지.<head>에<meta charset="utf-8">,<meta name="viewport" content="width=device-width, initial-scale=1">,<title>만 포함. 분석/트래킹 스크립트 삽입 금지.
파일 외에 tailwind.config.js는 tailwind_mode: "config" 이고 Design Token Extractor가 tailwind_config_snippet을 제공한 경우에만 별도 산출로 동반 반환한다(HTML 안에 인라인 금지).
섹션 구분 주석 (필수)
각 섹션 시작 직전 한 줄 HTML 주석으로 역할을 표시한다. Vision Analyst의 role 값을 그대로 쓴다.
<!-- hero -->
<section id="hero" ...>...</section>
<!-- feature-list -->
<section id="features" ...>...</section>
<!-- pricing -->
<section id="pricing" ...>...</section>
<!-- footer -->
<footer ...>...</footer>
- 주석은 한 줄 형식
<!-- <role> -->고정. 설명문을 덧붙이지 않는다. - 섹션 id는
role기반 kebab-case. 중복 시-2,-3등 접미사.
조립 규칙
- Layout Architect의
skeleton_html을 뼈대로 삼는다. 랜드마크 태그를 치환·삭제하지 않는다. - Tokens 주입 방식:
tailwind_mode: "cdn"→ 색/폰트는style속성이 아니라 Tailwindbg-[#0ea5e9]/text-[#0f172a]형태의 arbitrary value utility로만 허용. 그 외 임의 값 금지.tailwind_mode: "config"→tailwind_config_snippet에 선언된 키 이름(bg-primary등)만 사용. HEX 직기재 금지.
- Assets 삽입:
<img src="assets/hero-photo-0.webp" alt="...">처럼 Asset Extractor가 저장한saved_path(프로젝트-상대 경로)를 그대로 인용.alt는 A11y Advisor의alt_texts[<id>]를 1:1 적용하고, 매칭 없으면assets.alt_candidates[0]으로 폴백. 장식 자산은alt="". - A11y patches:
aria_patches의targetCSS selector에 맞춰 속성을 주입한다. selector가 매칭되지 않으면 무시(억지 태그 추가 금지). - Heading 계층:
heading_outline에 제시된 레벨만 사용.h1은 페이지당 1개. - Responsive:
responsive_hints.changes배열을 해당 요소의 class에 merge. breakpoint 접두사(md:,lg:)를 제거하지 않는다.
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.
- yesterday First seen · 110 lines · 115 tokens per session scan A 58c5e1d7a7a0
code-generator is an agent published in the GitHub repository Mineru98/imagine (5 stars, last pushed 3d ago), licensed MIT. It adds 115 tokens to every session and 2,060 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.