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 HsiangNianian/wechat-publisher-mcp --skill publish-wechat-remotegit clone --depth 1 https://github.com/HsiangNianian/wechat-publisher-mcpWrote 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/hsiangnianian/wechat-publisher-mcp/publish-wechat-remote)<a href="https://agentmods.dev/skills/hsiangnianian/wechat-publisher-mcp/publish-wechat-remote"><img src="https://agentmods.dev/badge/skills/hsiangnianian/wechat-publisher-mcp/publish-wechat-remote/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/hsiangnianian/wechat-publisher-mcp/publish-wechat-remote"><img src="https://agentmods.dev/badge/skills/hsiangnianian/wechat-publisher-mcp/publish-wechat-remote.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 | $0.00075 | $0.00741 |
| Opus 5 | $0.00037 | $0.00370 |
| Sonnet 5 | $0.00015 | $0.00148 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
publish-wechat-remote 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 12d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish WeChat Remote
Use the remote MCP server as the only WeChat API execution surface. Keep account secrets out of prompts and tool arguments.
Safety rules
- Default ambiguous requests such as “发公众号” or “发布文章” to creating a draft.
- Call
wechat_publish_draftonly after the user explicitly requests formal publication and the target account plus draftmedia_idare known. - Set
confirmed=trueonly for that explicit request. Never infer confirmation from an earlier draft request. - Never ask for or pass
AppSecret,access_token,.envcontents, or MCP bearer tokens through tools. - Reuse the same idempotency key when retrying an uncertain result. Never invent a new key just to bypass a prior call.
Workflow
- Call
wechat_list_accountsand resolve the target alias. Ask only when multiple accounts remain plausible. - For first use or credential diagnosis, call
wechat_check_account. Stop on an IP-white-list or interface-permission error. - Resolve the article title, author, summary, body, cover, source URL, comment policy, and target account.
- Convert Markdown or plain text to clean WeChat-compatible HTML. Remove scripts, forms, iframes, event handlers, and unsupported interactive markup.
- For every non-WeChat inline image:
- Read the local file and base64-encode its bytes.
- Call
wechat_upload_content_imagewith the true MIME type and plain filename. - Replace the corresponding HTML
srcwith the returned HTTPS URL.
- Upload the cover through
wechat_upload_coverand retain itsmedia_id. - Derive a stable key such as
draft:<account>:<content-sha256-prefix>. Callwechat_create_draftwith one to eight articles. - Report the account alias and draft
media_id. Do not formally publish unless the safety rules are satisfied. - For an explicitly approved formal publication:
- Derive
publish:<account>:<media-id>as the stable key. - Call
wechat_publish_draftonce withconfirmed=true. - Query
wechat_get_publish_statususing the returnedpublish_id; report submission separately from final success.
- Derive
What ships with it
2 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.
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.
- 12d ago First seen · 52 lines · 75 tokens per session scan A 214377669420
publish-wechat-remote is a skill published in the GitHub repository HsiangNianian/wechat-publisher-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 741 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 2026-08-31.
Other skills, from other repositories
agent-reach-channels
Use when multi-platform e-commerce and messaging channel extraction (Shopee, TikTok Shop, WeChat).
wechat-article-api
A tool for preparing WeChat Official Account article drafts through WeChat's official server API. It validates an article package, uploads its images, creates a draft, and reads the draft back for checking.
wechat-image-api
A Windows PowerShell skill for using WeChat's official server API to check image packages, upload permanent images, and create image-message drafts for a public account.
kevin-xhs-minitool-publisher
A workflow for turning a web page, game, or interactive project into an offline Xiaohongshu Builder Hub mini-tool. It covers checking platform rules, building a phone preview, preparing a ZIP, and submitting it for review.
wechat-article-format
A macOS workflow for formatting the body of a WeChat public-account article using inline styles while keeping its wording unchanged. WeChat public accounts are channels for publishing articles in the WeChat app.
wechat-computer-use
Fast, token-efficient, context-aware control of macOS WeChat through verified FastBridge MCP tools with Computer Use fallback. Use when Codex must read, monitor, or reply in WeChat; understand a long-running chat; send text, emoji, stickers, or files; run an authorized customer autopilot; or resolve an imperfect chat…