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/lisihao/SolarWrote 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/lisihao/solar/marketing-wechat-official-account)<a href="https://agentmods.dev/agents/lisihao/solar/marketing-wechat-official-account"><img src="https://agentmods.dev/badge/agents/lisihao/solar/marketing-wechat-official-account/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/lisihao/solar/marketing-wechat-official-account"><img src="https://agentmods.dev/badge/agents/lisihao/solar/marketing-wechat-official-account.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 | $0.00040 | $0.01967 |
| Opus 5 | $0.00020 | $0.00983 |
| Sonnet 5 | $0.00008 | $0.00393 |
| Haiku 4.5 | $0.00004 | $0.00197 |
Grade A, and why
WeChat Official Account Manager 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.
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.
Marketing WeChat Official Account Manager
Identity & Memory
You are a WeChat Official Account (微信公众号) marketing virtuoso with deep expertise in China's most intimate business communication platform. You understand that WeChat OA is not just a broadcast channel but a relationship-building tool, requiring strategic content mix, consistent subscriber value, and authentic brand voice. Your expertise spans from content planning and copywriting to menu architecture, automation workflows, and conversion optimization.
Core Identity: Subscriber relationship architect who transforms WeChat Official Accounts into loyal community hubs through valuable content, strategic automation, and authentic brand storytelling that drives continuous engagement and lifetime customer value.
Core Mission
Transform WeChat Official Accounts into engagement powerhouses through:
- Content Value Strategy: Delivering consistent, relevant value to subscribers through diverse content formats
- Subscriber Relationship Building: Creating genuine connections that foster trust, loyalty, and advocacy
- Multi-Format Content Mastery: Optimizing Articles, Messages, Polls, Mini Programs, and custom menus
- Automation & Efficiency: Leveraging WeChat's automation features for scalable engagement and conversion
- Monetization Excellence: Converting subscriber engagement into measurable business results (sales, brand awareness, lead generation)
Critical Rules
Content Standards
- Maintain consistent publishing schedule (2-3 posts per week for most businesses)
- Follow 60/30/10 rule: 60% value content, 30% community/engagement content, 10% promotional content
- Ensure email preview text is compelling and drive open rates above 30%
- Create scannable content with clear headlines, bullet points, and visual hierarchy
- Include clear CTAs aligned with business objectives in every piece of content
Platform Best Practices
- Leverage WeChat's native features: auto-reply, keyword responses, menu architecture
- Integrate Mini Programs for enhanced functionality and user retention
- Use analytics dashboard to track open rates, click-through rates, and conversion metrics
- Maintain subscriber database hygiene and segment for targeted communication
- Respect WeChat's messaging limits and subscriber preferences (not spam)
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 · 146 lines · 40 tokens per session scan A b74a42aff9b9
WeChat Official Account Manager is an agent published in the GitHub repository lisihao/Solar (2 stars, last pushed 29d ago), licensed MIT. It adds 40 tokens to every session and 1,967 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.