hand-drawn-styles is a tool-independent library of prompt recipes for applying predefined hand-drawn visual styles to image concepts. It is for AI agents that need to produce ready-to-copy image prompts without changing the requested subject or generating the image themselves. Its catalogue skill and instruction make these recipes available to coding agents.
Borrowing it
Nothing to install: this file belongs to threerocks/hand-drawn-styles. 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/threerocks/hand-drawn-styles/main/AGENTS.mdgit clone --depth 1 https://github.com/threerocks/hand-drawn-stylesWrote 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/threerocks/hand-drawn-styles/agents-md)<a href="https://agentmods.dev/instructions/threerocks/hand-drawn-styles/agents-md"><img src="https://agentmods.dev/badge/instructions/threerocks/hand-drawn-styles/agents-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/threerocks/hand-drawn-styles/agents-md"><img src="https://agentmods.dev/badge/instructions/threerocks/hand-drawn-styles/agents-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 | $0.01026 | $0.01026 |
| Opus 5.5 | $0.00410 | $0.00410 |
| Sonnet 5.5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
hand-drawn-styles AGENTS.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 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.
What it actually says
AGENTS.md
供读取 AGENTS.md 的 Agent 工具使用(OpenAI Codex CLI、Gemini CLI、Cursor、Jules 等)。
手绘风格生图提示词能力
当用户希望生成"手绘 / 插画风格"的图像、或要一段对应的生图提示词时:
- 按 PROTOCOL.md 的 5 步流程执行(确定画风 → 取配方 → 自动填占位符 → 处理比例 → 输出 prompt)。
- 画风模板从 STYLES.md 取。
- 能执行脚本时优先用
scripts/render_prompt.py,禁止手工缩写、同义改写或混入业务项目自定义画风规则。 - 风格 3.1 的正式生产、多页或连续故事必须完整消费
family-crayon-card-v4：基础生成后依次执行scribble-correction与scribble-chaos-correction，再执行style-contract-check。三次图像操作只得到final-candidate，独立验收报告为 pass 才能成为 final；证据不足或审核失败不可放行。记录与迁移见 docs/style-3.1-review.md。 - 风格 19 正式生产必须完整使用正式 JSON 调用包:每张携带原创锚点,锁定模型快照和高保真参考图输入,基础图只标为
candidate-only,通过acceptance_contract后才能标为 final;任一条件不可用时停止生产。 - 风格 20 正式生产必须完整使用正式 JSON 调用包:使用固定原创锚点生成
final-candidate,然后运行机读验收器;失败候选整张拒收并重新生成,禁止用通用画风迁移编辑修补。 - 风格22为 v1.1.0 朱墨写意转绘，先完整执行 内置 sweety-image-art-direction 预处理，默认输出带画风锚点与可选
--source-image内容原图的 JSON；不要把锚点人物或物件复制到新内容，来源与发布状态见 迁入记录。 - 风格23皮影彩染为已确认入库的v0.1首版，先执行包内美术指导分析，输出独立全幅皮影作品的提示词，不需要或展示原片；普通调用不生图，试作证据见 23号记录。
- 其他画风默认只输出最终 prompt 纯文本;风格 3.1/19/20/22 输出带参考锚点的 JSON 调用包。不要生图。
维护者验证例外
当用户明确要求新增、升级或验收仓库中的画风时,可在维护流程中调用图像模型做多轮样图验证。此例外只用于研发和验收,不改变本项目面向普通使用者“只输出 prompt”的能力边界。
维护者验证必须:
- 先固定参考图、测试场景和判定维度,再开始出图。
- 每轮只针对已观察到的稳定偏差修改配方,保留可复核的候选样图。
- 至少验证参考图同构场景与一个跨主体场景,不能凭单张满意图入库。
- 最终入库图片必须使用
sweety-image-privacy清理 EXIF、GPS、来源字段和 macOS 来源扩展属性,并保留审计结果。
想用在你自己的项目里:安装整个 skill 并按画风编号调用。不要只复制某几句配方,也不要在业务项目维护第二份画风真源。
图片存储规则
所有图片均使用 Cloudflare Pages 公开链接，地址、大小和 SHA-256 登记在 assets/image-manifest.json。Git 与安装包禁止保存图片二进制。新增图片必须依次完成隐私清理、登记、完整站点部署、匿名下载校验，再提交引用。执行细则见 docs/image-hosting.md。
运行参考图由渲染器下载到独立缓存，校验成功后输出绝对路径。首次调用需要网络；缺图、校验失败或离线缓存失效时停止正式调用，不得省略参考图。安装检查与打包检查必须覆盖全部画风。
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 Changed · +2 lines · +169 tokens per session 3b8cd19391e3
- 8d ago Changed · +51 tokens per session 97613b731540
- 15d ago Changed · +6 lines · +151 tokens per session 0f9b54805ea3
- 16d ago Changed · +2 lines · +133 tokens per session e60c43c88432
- 1mo ago First seen · 27 lines · 522 tokens per session scan A 62178a265ceb
hand-drawn-styles AGENTS.md is an instructions file published in the GitHub repository threerocks/hand-drawn-styles (2,543 stars, last pushed 2d ago), licensed MIT. It adds 1,026 tokens to every session, about $0.0041 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 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.