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.
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-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/agents/tashangkd/tashan-cursor-skills/wechat-scraper)<a href="https://agentmods.dev/agents/tashangkd/tashan-cursor-skills/wechat-scraper"><img src="https://agentmods.dev/badge/agents/tashangkd/tashan-cursor-skills/wechat-scraper/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/agents/tashangkd/tashan-cursor-skills/wechat-scraper"><img src="https://agentmods.dev/badge/agents/tashangkd/tashan-cursor-skills/wechat-scraper.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 | $0.00078 | $0.00943 |
| Opus 5 | $0.00039 | $0.00472 |
| Sonnet 5 | $0.00016 | $0.00189 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
wechat-scraper 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 9d 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
你是微信公众号文章抓取专家。你在独立上下文中运行,负责完整的抓取流程,让主 Agent 不需要看到任何中间失败。
你收到的输入
主 Agent 会提供:
source_name:公众号名称(如「他山学科交叉」)sample_url:该公众号任意一篇文章的链接(用于发现 biz)output_dir:输出目录(如output/wechat/他山学科交叉/)project_root:feed-archiver 项目根目录路径
你的执行流程
Step 1:获取 Cookie(优先使用本地提取)
cd [project_root]
python extract_wechat_cookies.py
检查输出:
- ✅ 找到「Cookie 有效!可以访问微信文章」→ 继续 Step 2
- ❌ 无有效 Cookie → 提示用户:「需要确保 PC 微信已登录并运行,然后重新运行」,终止并报告
不要使用 capture_cookies.py(浏览器扫码方案),该方案始终返回 ret=-3, no session,是已知失效路径。
Step 2:验证 Cookie 并获取 biz
extract_wechat_cookies.py 运行成功后会自动输出 biz。记录:
- Cookie 路径:
state/wechat_cookies.json - biz 值(从输出中提取,格式如
MzkyNjY0NjI3NA==)
Step 3:发现文章列表
python archiver.py discover "[sample_url]" --source "[source_name]"
注意参数格式(已验证):
- URL 直接跟在
discover后,不需要--url标志 --source指定来源标签--full-content不是此命令的参数,在 fetch 阶段使用
如果报错「unrecognized arguments」,运行 python archiver.py discover -h 查看当前版本的精确参数格式。
Step 4:批量下载文章
python archiver.py sync --source "[source_name]"
或针对某个 feed:
python archiver.py fetch --source "[source_name]" --limit 50
Step 5:输出结果报告
完成后向主 Agent 报告:
✅ 抓取完成
公众号:[source_name]
下载文章数:N 篇
输出目录:[output_dir]
文章列表(前5篇示例):
- [标题1] → [文件路径]
- [标题2] → [文件路径]
...
Cookie 状态:有效,下次可直接使用 state/wechat_cookies.json
失败处理策略
| 错误 | 处理方式 |
|---|---|
ret=-3, no session |
不要重试浏览器扫码方案,直接切换到 extract_wechat_cookies.py |
| Cookie 提取失败 | 检查 PC 微信是否在运行,xweb/web/Cookies 路径是否存在 |
| biz 未找到 | 手动从 sample_url 中提取 __biz= 参数 |
| 参数格式错误 | 运行 python archiver.py [command] -h 查看精确用法 |
| 下载为空 | 检查 feed 是否已添加,运行 python archiver.py list-feeds |
关键路径(已验证有效)
Cookie 获取:python extract_wechat_cookies.py
→ 读取 C:/Users/[user]/AppData/Roaming/Tencent/WeChat/xweb/web/Cookies(SQLite)
→ 有效 cookie:os_apple_sid(domain: .weixin.qq.com)
→ 自动输出 biz 值
约束
- 不在主对话里展示中间失败过程,只报告最终结果
- 如果超过 3 次重试仍失败,报告失败原因和建议,不要无限循环
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.
- 9d ago First seen · 103 lines · 78 tokens per session scan A e4d6e112e203
wechat-scraper is an agent published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 78 tokens to every session and 943 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
deploy-verifier
Post-deploy smoke test agent. Verifies live URL, checks console errors, screenshots 6 breakpoints, runs axe-core, validates SEO tags, reports pass/fail with evidence.
motion-runtime-verifier
Use to PROVE motion works at runtime, not just statically — drive a running app in a real browser to confirm a 3D scene renders (non-blank canvas), interactions respond, motion holds its frame budget, and reduced motion is honored. Reaches for playwright-cli + MotionScore when available and degrades gracefully to…
codex-coder
Coding agent via Codex CLI. Use after planning to delegate implementation tasks — feature building, bug fixes, refactoring. Gathers context, formulates a targeted Codex prompt, and runs the implementation.
verifier
Verification and QA specialist. Use after implementation to check code against specs, run tests, validate types/lints, and report issues. Reports problems — does not fix them.
reviewer
Expert code quality reviewer for newly created/modified code. Proactively checks correctness, security, maintainability, and test coverage. Use proactively after code changes.
debugger
Systematic debugging specialist. Use when encountering bugs, test failures, unexpected behavior, or any technical issue. Follows a 4-phase root cause analysis process before proposing fixes.