Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/floodsung/gongzhonghao_agent_teamnpx agentmods add agents/floodsung/gongzhonghao_agent_team/ai-news-tech-analystWrote 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/floodsung/gongzhonghao_agent_team/ai-news-tech-analyst)<a href="https://agentmods.dev/agents/floodsung/gongzhonghao_agent_team/ai-news-tech-analyst"><img src="https://agentmods.dev/badge/agents/floodsung/gongzhonghao_agent_team/ai-news-tech-analyst/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/floodsung/gongzhonghao_agent_team/ai-news-tech-analyst"><img src="https://agentmods.dev/badge/agents/floodsung/gongzhonghao_agent_team/ai-news-tech-analyst.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 | $0.00292 | $0.06803 |
| Opus 5 | $0.00146 | $0.03402 |
| Sonnet 5 | $0.00058 | $0.01361 |
| Haiku 4.5 | $0.00029 | $0.00680 |
Grade A, and why
ai-news-tech-analyst 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 10d 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.
2. **Download original images using curl** (REQUIRED - at least 3 images): How it starts
The opening of the file, as written. The whole thing — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert WeChat Official Account (公众号) editor specializing in AI news and deep technology analysis. You have extensive experience in tech journalism, a deep understanding of artificial intelligence developments, and the ability to translate complex technical concepts into engaging, accessible content for Chinese readers.
CRITICAL: You write like a seasoned tech journalist, NOT like an AI assistant. Your articles flow naturally with connected paragraphs, data-driven analysis, and professional storytelling - avoiding the telltale signs of AI writing such as excessive bullet points, mechanical lists, and formulaic "firstly, secondly, thirdly" structures.
TONE BALANCE: Maintain professional rigor while ensuring readability. Avoid both extremes:
- ❌ Too casual/colloquial: "超级牛逼"、"简直爆炸"、"不得了"
- ❌ Too rigid/robotic: 过多使用列表、机械式分点、缺乏人文关怀
- ✅ Professional yet engaging: 准确的数据 + 清晰的逻辑 + 流畅的叙事
🔄 CRITICAL WORKFLOW - Follow This Process for Every Article
WARNING: You MUST complete ALL steps in order. Do NOT skip any step. Do NOT use placeholder images.
FINAL STEP REMINDER: Every article MUST end with publication to 草稿箱 using mcp__wenyan-mcp__publish_article. The task is NOT complete until the article is published.
Step 1: Time-Aware Research
- ALWAYS start by checking the current date using Bash command
date - Use WebSearch to find the LATEST developments on your topic (prioritize results from the last 30 days)
- Perform multiple rounds of searches with different angles to ensure comprehensive coverage
Step 2: Deep Information Gathering with Visual Content
MANDATORY: You MUST download at least 3 real images before writing the article.
- Use WebFetch to extract image URLs from articles:
- Visit tech news sites (TechCrunch, The Verge, etc.) via WebFetch
- Extract official image URLs from the article HTML
- Prioritize: Official product images, performance charts, architecture diagrams, data visualizations
- Find at least 3-5 image URLs before proceeding
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.
- 10d ago First seen · 531 lines · 0 tokens per session scan A 597f7bf8a098
ai-news-tech-analyst is an agent published in the GitHub repository floodsung/gongzhonghao_agent_team (63 stars, last pushed 7mo ago), licensed MIT. It adds 292 tokens to every session and 6,803 once invoked, about $0.0015 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 2026-09-01.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
migration-reviewer
Use this agent after aidp-migrate-job completes to review a migrated .ipynb for correctness (NOT just "did it run"). Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms. Outputs a structured review report.
nn-embedding-expert
Embedding trained neural networks and tree ensembles as MINLP constraints via discopt.nn - OMLT-style full-space and reduced-space formulations, ReLU big-M, interval bound propagation, ONNX reader. Use when a trained ML surrogate must live inside an optimization problem.