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 HeroAshacker/wechat-content-pipeline --skill wechat-writergit clone --depth 1 https://github.com/HeroAshacker/wechat-content-pipelineWrote 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/heroashacker/wechat-content-pipeline/wechat-writer)<a href="https://agentmods.dev/skills/heroashacker/wechat-content-pipeline/wechat-writer"><img src="https://agentmods.dev/badge/skills/heroashacker/wechat-content-pipeline/wechat-writer/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/heroashacker/wechat-content-pipeline/wechat-writer"><img src="https://agentmods.dev/badge/skills/heroashacker/wechat-content-pipeline/wechat-writer.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 | $0.00118 | $0.01080 |
| Opus 5.5 | $0.00047 | $0.00432 |
| Sonnet 5.5 | $0.00024 | $0.00216 |
| Haiku 4.5 | $0.00012 | $0.00108 |
Grade A, and why
wechat-writer 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
微信公众号 AI 写作工具 (wechat-writer)
Instructions
从观点/想法出发，AI 生成完整公众号文章。
Step 1: 获取输入
- 观点文本: 分号分隔多个观点，如 "AI改变教育; 个性化学习是未来"
- 观点文件:
.txt文件路径 - 无输入: 提示用户提供观点
Step 2: 确定参数
| 参数 | 默认值 | 说明 |
|---|---|---|
| type | opinion | opinion/tutorial/listicle/commentary/story |
| provider | gemini | AI provider: gemini/deepseek/openai/claude |
| api-key | 无 | AI API Key |
| dry-run | false | 仅打印 prompt，不调用 API |
| list-types | false | 列出所有文章类型 |
| no-confirm | false | 跳过大纲确认 |
| outline-only | false | 仅输出大纲，不扩写全文 |
| title-candidates | 5 | 大纲阶段生成标题候选数量 |
| output | 无 | 输出文件路径 (-o) |
| polish | 无 | 写完后润色的 provider |
| polish-type | deai | 润色类型 |
| theme | 无 | 排版主题（触发 HTML 转换） |
Step 3: 执行写作
cd ~/Claude/🧪\ 小项目与测试/wx-format
# 基础：观点→文章
node index.js write "AI正在改变教育; 个性化学习是未来" --provider gemini
# 指定类型
node index.js write "量化交易3个误区" --type listicle
# 全流程：写作→润色→排版
node index.js write "观点1; 观点2" --provider gemini \
--polish gemini --polish-type deai -t simple -o article.html
# 仅生成大纲 + 5个标题候选
node index.js write "AI套娃思维" --outline-only --title-candidates 5
Step 4: 返回结果
- 输出 Markdown 到 stdout（可重定向）
- 带
-t时输出 HTML - 带
-o时写入文件
文章类型
| 类型 | 名称 | 特点 |
|---|---|---|
| opinion | 观点文 | 论点+论据+升华（默认） |
| tutorial | 教程文 | 步骤式 how-to |
| listicle | 盘点文 | Top N 列表 |
| commentary | 热点评论 | 新闻+分析 |
| story | 故事文 | 叙事驱动 |
Examples
Example 1: 观点→完整文章 + 排版
输入: 用户提供观点 "AI正在改变教育; 个性化学习是未来"
命令:
cd ~/Claude/🧪\ 小项目与测试/wx-format
node index.js write "AI正在改变教育; 个性化学习是未来" --provider gemini \
--polish gemini --polish-type deai -t simple -o article.html
输出: 生成大纲→确认→扩写全文→去AI味润色→simple主题排版→输出 article.html
Example 2: Dry-run 预览 prompt
输入: 用户想查看生成的 prompt 而不调用 API
命令:
node index.js write "量化交易3个误区" --type listicle --dry-run
输出: 打印完整 prompt 到终端，不消耗 API 额度
Error Handling
- AI 调用失败 → 检查
--api-key或环境变量配置 - 大纲不满意 → 不带
--no-confirm，手动确认/修改大纲 - 输出乱码 → 确认终端 UTF-8 编码
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 · 112 lines · 118 tokens per session scan A 6be538e1fb39
wechat-writer is a skill published in the GitHub repository HeroAshacker/wechat-content-pipeline (12 stars, last pushed 8mo ago), licensed MIT. It adds 118 tokens to every session and 1,080 once invoked, about $0.0005 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.
wechat-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wechat-writerHeroAshacker/wechat-content-pipeline | Skill | 12 | 8mo ago | MIT | A | 118 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |