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 FrankL1u/liusir-skills --skill ls-wechat-articlegit clone --depth 1 https://github.com/FrankL1u/liusir-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/frankl1u/liusir-skills/ls-wechat-article)<a href="https://agentmods.dev/skills/frankl1u/liusir-skills/ls-wechat-article"><img src="https://agentmods.dev/badge/skills/frankl1u/liusir-skills/ls-wechat-article/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/frankl1u/liusir-skills/ls-wechat-article"><img src="https://agentmods.dev/badge/skills/frankl1u/liusir-skills/ls-wechat-article.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 | $0.00092 | $0.03054 |
| Opus 5 | $0.00046 | $0.01527 |
| Sonnet 5 | $0.00018 | $0.00611 |
| Haiku 4.5 | $0.00009 | $0.00305 |
Grade A, and why
ls-wechat-article scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://ifconfig.me The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .clawhubignore 98 B
- .gitignore 62 B
- AGENTS.md 7.9 KB
- agents/openai.yaml 1.5 KB
- config.example.yaml 1.9 KB
- README_ZH.md 13 KB
- README.md 14 KB
- references/article-archetypes.md 4.1 KB
- references/builtin-themes.json 88 KB
- references/cli-reference.md 4.6 KB
- references/editorial-qa.md 5.0 KB
- references/environment.md 366 B
- references/error-handling.md 782 B
- references/frameworks.md 28 KB
- references/image-style-config.md 3.9 KB
- references/operations.md 3.3 KB
- references/pipeline.md 11 KB
- references/rewrite-examples.md 2.3 KB
- references/seo-rules.md 15 KB
- references/setup.md 603 B
- references/shared-environment.md 741 B
- references/shared-error-handling.md 1.2 KB
- references/skill-maintenance.md 1.1 KB
- references/style-template.md 1.3 KB
- references/theme-dsl.md 38 KB
- references/theme-selection.md 3.4 KB
- references/topic-selection.md 9.3 KB
- references/visual-prompt-system.md 12 KB
- references/visual-prompts.md 7.4 KB
- references/wechat-constraints.md 4.0 KB
- references/writing-guide.md 42 KB
- requirements.txt 98 B
- scripts/fetch_hotspots.py 5.3 KB runs code
- scripts/fetch_trendradar_hotspots.py 8.6 KB runs code
- scripts/seo_keywords.py 5.5 KB runs code
- scripts/test_fetch_trendradar_hotspots.py 3.9 KB runs code
- scripts/validate_skill.py 7.5 KB runs code
- toolkit/package.json 1.4 KB
- toolkit/src/article-bundle.test.ts 1.4 KB runs code
- toolkit/src/article-bundle.ts 2.6 KB runs code
- toolkit/src/article-metadata.ts 1.5 KB runs code
- toolkit/src/build-playbook.ts 4.1 KB runs code
- toolkit/src/cli.ts 19 KB runs code
- toolkit/src/client-style.test.ts 637 B runs code
- toolkit/src/client-style.ts 821 B runs code
- toolkit/src/code-block-processor.ts 5.8 KB runs code
- toolkit/src/converter.test.ts 1.9 KB runs code
- toolkit/src/converter.ts 16 KB runs code
- toolkit/src/cover-assets.ts 1.4 KB runs code
- toolkit/src/cover-workflow.ts 3.2 KB runs code
- toolkit/src/editorial-qa.test.ts 6.6 KB runs code
- toolkit/src/editorial-qa.ts 18 KB runs code
- toolkit/src/fetch-stats.ts 5.9 KB runs code
- toolkit/src/history.ts 5.3 KB runs code
- toolkit/src/illustration-workflow.ts 15 KB runs code
- toolkit/src/image-gen.ts 18 KB runs code
- toolkit/src/image-style-system.ts 7.6 KB runs code
- toolkit/src/index.ts 1.8 KB runs code
- toolkit/src/learn-edits.ts 6.0 KB runs code
- toolkit/src/markdown-it-task-lists.d.ts 289 B runs code
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.
- 11d ago First seen · 284 lines · 92 tokens per session scan A 4f09da1dc9d6
ls-wechat-article is a skill published in the GitHub repository FrankL1u/liusir-skills (2 stars, last pushed 4mo ago), with no licence file. It adds 92 tokens to every session and 3,054 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
aws-wechat-article-images
An image-generation tool for Chinese WeChat public-account articles, making covers and illustrations based on an article’s title and content. It can create several visual options and reuse configured style presets.
aws-wechat-article-main
A coordinator for running a complete Chinese WeChat public-account publishing workflow. It connects separate steps such as choosing a topic, writing, reviewing, formatting, adding images, and publishing.
aws-wechat-article-writing
A writing tool for Chinese WeChat public-account articles, creating a first draft from a topic or outline and revising existing text. It can use a configured language-model service, such as DeepSeek, OpenAI, or Anthropic.
aws-wechat-article-assets
A local library for storing business descriptions, product images, and reusable writing or design presets for WeChat articles. It organizes these materials by product so other article tools can reuse them.
aws-wechat-article-formatting
A local converter that turns Markdown text into HTML formatted for the Chinese WeChat editor. Markdown is plain text with simple symbols for headings, links, and emphasis; the converter puts the resulting styles directly into the HTML.
aws-wechat-article-publish
A publishing tool that connects to the official WeChat public-account API to upload article images and place an article in the draft box or publish it. WeChat is the Chinese platform where public accounts distribute articles to followers.