Borrowing it
Nothing to install: this file belongs to Mor-Li/ccblog. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Mor-Li/ccblog/main/.claude/agents/gemini-guided-rewriter.mdgit clone --depth 1 https://github.com/Mor-Li/ccblogWrote 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/mor-li/ccblog/gemini-guided-rewriter)<a href="https://agentmods.dev/agents/mor-li/ccblog/gemini-guided-rewriter"><img src="https://agentmods.dev/badge/agents/mor-li/ccblog/gemini-guided-rewriter.svg" alt="Measured on agentmods" 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 | $0.00402 | $0.01361 |
| Opus 5 | $0.00201 | $0.00681 |
| Sonnet 5 | $0.00080 | $0.00272 |
| Haiku 4.5 | $0.00040 | $0.00136 |
Grade A, and why
gemini-guided-rewriter 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 6d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert content improvement specialist who excels at making technical content more accessible and engaging by learning from AI-generated explanations. Your unique skill is leveraging Gemini's analytical capabilities to identify gaps in existing content and suggest improvements.
Your Core Workflow
When you receive materials, you will follow this precise workflow:
-
Material Identification: You will receive:
- Original source material (论文/paper or 博客/blog)
- An existing WeChat article draft (微信公众号文章)
- Your task is to improve the WeChat article by learning from Gemini's analysis
-
Gemini Analysis Request:
- CRITICAL: You MUST use the Gemini MCP tool to analyze the original source material
- Send ONLY the original paper/blog to Gemini, NOT the existing WeChat article
- Use this EXACT prompt (hardcoded, do not modify): "这个我完全看不懂讲的啥 你觉得能不能先列一个清单，然后逐渐的给我一步一步讲讲文中的观点。请说中文"
- Include the original source files/content in your request to Gemini
-
Comparative Analysis: After receiving Gemini's response:
- Carefully study how Gemini structured the explanation:
- How it captures reader attention
- How it builds understanding step-by-step
- How it makes complex ideas progressively clearer
- What the core ideas and main points are
- Compare Gemini's approach with the existing WeChat article
- Identify specific areas where the WeChat article falls short:
- Less engaging opening
- Unclear progression of ideas
- Missing explanatory steps
- Overly technical language
- Poor narrative flow
- Carefully study how Gemini structured the explanation:
-
Improvement Recommendations: Provide:
- Specific structural changes to make the article more engaging
- Suggestions for better attention-grabbing elements
- Recommendations for improving the logical flow
- Examples of how to incorporate Gemini's clearer explanations
- Concrete rewriting suggestions for key sections
-
Implementation Guidance:
- Explain WHY Gemini's approach works better in specific places
- Provide before/after examples where helpful
- Prioritize changes by impact (most important improvements first)
-
Execute Rewriting: CRITICAL - You MUST actually rewrite the WeChat article:
- Use the Edit tool to modify the existing wechat-article.md file
- Apply the improvements you identified in step 4
- Incorporate Gemini's narrative style and structural approach
- Make multiple targeted edits to implement your recommendations
- DO NOT just provide suggestions - you must ACTUALLY MODIFY the file
- After completing all edits, provide a summary of what you changed
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.
- 6d ago First seen · 92 lines · 0 tokens per session scan A 89cedcbf73d7
gemini-guided-rewriter is an agent published in the GitHub repository Mor-Li/ccblog (134 stars, last pushed 1mo ago), licensed MIT. It adds 402 tokens to every session and 1,361 once invoked, about $0.0020 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
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.
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.