native-subtitle-quote-image is an agent skill that takes video frames and produces 3:4 social-media images while preserving embedded subtitles or adding clearly marked, reviewed script subtitles. It is for people who want to select quotes from local videos or YouTube links and receive checked image sets plus an overview image, either through a coding agent or a Python script. The catalogue entry is the skill used for this video-to-image workflow.
Borrowing it
Nothing to install: this file belongs to chengyi-ai/native-subtitle-quote-image. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chengyi-ai/native-subtitle-quote-image/main/CLAUDE.mdgit clone --depth 1 https://github.com/chengyi-ai/native-subtitle-quote-imageWrote 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/instructions/chengyi-ai/native-subtitle-quote-image/claude-md)<a href="https://agentmods.dev/instructions/chengyi-ai/native-subtitle-quote-image/claude-md"><img src="https://agentmods.dev/badge/instructions/chengyi-ai/native-subtitle-quote-image/claude-md/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/instructions/chengyi-ai/native-subtitle-quote-image/claude-md"><img src="https://agentmods.dev/badge/instructions/chengyi-ai/native-subtitle-quote-image/claude-md.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 | $0.00472 | $0.00472 |
| Opus 5.5 | $0.00189 | $0.00189 |
| Sonnet 5.5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
native-subtitle-quote-image CLAUDE.md 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 16d 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.
What it actually says
CLAUDE.md
本仓库是 Agent Skill「原生字幕拼图」：把视频真实帧做成保留原字幕（原生模式）或绘制已审核台词（脚本模式）的长图。
目录
skills/native-subtitle-quote-image/：Skill 本体，发布时打包的就是这个目录。SKILL.md：Agent 使用说明；references/：详细流程文档。scripts/native_subtitle_stitch.py：渲染 CLI（sample/render/render-script）。scripts/check_environment.py、scripts/check_update.py：环境与版本检查。VERSION：Skill 版本。
scripts/validate_repo.py：打包不变量检查；scripts/bump_version.py：发版改版本号。tests/：unittest测试。README.md/README_EN.md/README_KO.md：三语 README，内容需保持同步。.github/：CI 与 Agent 工作流，见docs/agent-workflow.md。
不可违背的原则
- 原生字幕模式只裁切画面里已有的字幕，不 OCR、不重绘、不翻译、不覆盖。
- 脚本字幕模式必须明确标注为后期绘制，不得冒充原字幕或人物逐字引语。
- 不帮助绕过 DRM 或平台访问控制。
开发约定
-
Python 3.10+，依赖见
skills/native-subtitle-quote-image/requirements.txt。 -
提交前必须通过：
python scripts/validate_repo.py python -m unittest discover -s tests -
行为改动配测试；用户可见变化同步
SKILL.md与三语 README。 -
版本号只在发版时由
scripts/bump_version.py修改，功能 PR 不要动。 -
提交信息使用
fix:/feat:/docs:/test:/ci:前缀，简体中文描述。
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.
- 16d ago First seen · 36 lines · 472 tokens per session scan A c90c7e286ee5
native-subtitle-quote-image CLAUDE.md is an instructions file published in the GitHub repository chengyi-ai/native-subtitle-quote-image (2,740 stars, last pushed 4d ago), licensed MIT. It adds 472 tokens to every session, about $0.0019 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 2026-10-09.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.