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 meitu/meitu-skills --skill text-codegit clone --depth 1 https://github.com/meitu/meitu-skillsWrote 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/meitu/meitu-skills/text-code)<a href="https://agentmods.dev/skills/meitu/meitu-skills/text-code"><img src="https://agentmods.dev/badge/skills/meitu/meitu-skills/text-code/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/meitu/meitu-skills/text-code"><img src="https://agentmods.dev/badge/skills/meitu/meitu-skills/text-code.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 | $0.00061 | $0.01778 |
| Opus 5.5 | $0.00024 | $0.00711 |
| Sonnet 5.5 | $0.00012 | $0.00356 |
| Haiku 4.5 | $0.00006 | $0.00178 |
Grade A, and why
text-code 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 2mo 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.
This is a copy
86% identical to text-code-edit — 102 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Text Code（代码生成）
Overview
从零生成 React/TSX 页面代码，支持素材参考（图片/视频）与 prompt 扩写。适用于落地页、活动页、数据可视化页面、界面原型、React 组件快速搭建。不处理：修改已有源码、非 React/HTML 框架、后端代码（Python/Java 等）、像素级还原设计稿、复杂后端对接。
API Mapping
| 场景 | 后端 API |
|---|---|
| React/TSX 页面代码生成 | text_code |
model 映射：
auto（默认）/ 不传 → 按路由规则决策pretzel_pro/pretzel_lite→ 直接指定模型- 模型回退链：
pretzel_pro→pretzel_lite
Dependencies
- meitu-cli:
>=2.0.6 - 凭证：CONFIG AKSK →
meitu tools update；EXEC AKSK → 跑命令（见根CONFIG.md） - 环境变量：
MEITU_OPENAPI_TOOL_TASK_MODE=command
Core Workflow
Preflight → Execute → Deliver
Preflight
meitu --version≥ 2.0.6，未装则npm install -g meitu-cli@latestmeitu auth verify --json→ 凭证无效走 CONFIG.md SOP- 确认本地
~/.meitu/tool-registry.json已包含text-code，否则meitu tools update - 解析 output_dir：
openclaw.yaml→./output/；else →~/.openclaw/workspace/visual/output/text-code/；mkdir -p {output_dir}
Execute
触发信号 / 路由规则
| 场景 | 判定关键词 | 路由 |
|---|---|---|
| 从零生成 React 页面 | 做个页面、生成网页、落地页、活动页、数据可视化、生成组件 | text_code |
| 简短 prompt + 有 prompt_name | prompt < 10 字符 |
自动扩写后调用 |
| 提供 source_code_url + 修改意图 | 改代码、加按钮、调样式 | 不属于本工具（走 text-code-edit） |
| 要求生成非 React/HTML 代码 | 后端、Python、Java | 告知仅支持 React/TSX |
参数定义
| 参数 | 类型 | 必填 | 范围 | 默认值 | 说明 |
|---|---|---|---|---|---|
prompt |
STRING | 是 | -- | -- | 页面描述，尽量详细。缺失 → 追问 |
model |
ENUM | 否 | auto / pretzel_pro / pretzel_lite | pretzel_pro | 模型选择，非法值回退 pretzel_pro |
image_list |
ARRAY | 否 | -- | [] | 参考图片 URL 列表，无效项静默过滤 |
video_list |
ARRAY | 否 | -- | [] | 参考视频 URL 列表，无效项静默过滤 |
prompt_name |
STRING | 否 | -- | -- | 系统提示词名称 |
工具调用
基础生成：
meitu text-code --prompt "{page_description}" --json --download-dir {output_dir} --skill_name skill_text-code
指定模型 + 参考素材：
meitu text-code \
--skill_name skill_text-code \
--prompt "{page_description}" \
--model pretzel_pro \
--image_list "{url1}" --image_list "{url2}" \
--json --download-dir {output_dir}
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.
- 2mo ago First seen · 146 lines · 61 tokens per session scan A 1c5aa02b58de
text-code is a skill published in the GitHub repository meitu/meitu-skills (36 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 1,778 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to text-code-edit, differing in 102 lines, and is treated as a copy.
text-code compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| text-codemeitu/meitu-skills | Skill | 36 | 2mo ago | MIT | A | 61 | Claude Code, Codex |
| build-ghost-appTryGhost/Ghost | Skill | 56k | yesterday | MIT | A | 44 | Claude Code, Codex |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | yesterday | MIT | A | 214 | Claude Code, Codex |
| material-ui-tailwindmui/material-ui | Skill | 99k | yesterday | MIT | A | 67 | Claude Code, Codex |
| fuzzy-rankingTanStack/table | Skill | 29k | 4d ago | MIT | A | 62 | Claude Code, Codex |
| r3f-best-practiceszebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 74 | Claude Code, Codex |
| git-safetytamagui/tamagui | Skill | 14k | yesterday | MIT | A | 0 | Claude Code |