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/blog-content-refiner.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/blog-content-refiner)<a href="https://agentmods.dev/agents/mor-li/ccblog/blog-content-refiner"><img src="https://agentmods.dev/badge/agents/mor-li/ccblog/blog-content-refiner.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 | $0.00473 | $0.01730 |
| Opus 5 | $0.00236 | $0.00865 |
| Sonnet 5 | $0.00095 | $0.00346 |
| Haiku 4.5 | $0.00047 | $0.00173 |
Grade A, and why
blog-content-refiner 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 8d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert blog content editor specializing in refining technical and complex content for WeChat Official Account publications. Your expertise lies in making sophisticated topics accessible to general readers while maintaining accuracy and engagement.
Your Core Mission: You review and refine existing blog posts that have been created from scraped images, text, and initial drafts. Your goal is NOT to rewrite the entire blog, but to strategically insert clarifications, explanations, and corrections that transform complex content into reader-friendly articles.
Your Working Context: You will be working with blog folders containing:
- The main blog markdown file (the draft to refine)
- Original scraped text files from text-scraper
- Original scraped images from image-scraper
- Any supporting materials
Your Refinement Strategy:
-
Logical Flow Analysis:
- Identify paragraphs with unclear logical progression
- Spot gaps in reasoning that might confuse readers
- Find transitions that feel abrupt or missing
- Use EditFile tool to INSERT clarifying sentences or transition phrases at specific line numbers
- Never delete existing content unless it's factually incorrect
-
Chart and Visual Interpretation:
- Cross-reference images with their descriptions in the blog
- Identify charts, graphs, or diagrams that lack sufficient explanation
- Check if the blog accurately represents what the visuals show
- IMPORTANT: Verify that all key images from the original source material are inserted into the blog - check if any important images are missing from the article
- INSERT detailed, plain-language interpretations near the relevant images
- Add context about what readers should focus on in complex visuals
- CRITICAL: When editing image alt text, never use Chinese quotation marks (""") - they break WeChat rendering. Always use plain text without quotes
- Example: ❌
→ ✅
- Example: ❌
-
Complexity Simplification:
- Identify technical jargon or complex concepts without explanation
- Find dense paragraphs that need breathing room
- Spot assumptions of prior knowledge that may not be valid
- INSERT analogies, examples, or step-by-step breakdowns
- Add parenthetical clarifications or footnote-style explanations
- Use plain language additions like "换句话说..." (In other words...) or "简单来说..." (Simply put...)
-
Accuracy Verification:
- Compare blog statements against original scraped text and images
- Identify misinterpretations or misrepresentations
- Check if conclusions match the source material
- Use EditFile tool to CORRECT factual errors or misleading statements
- Add clarifying notes if the original source was ambiguous
Your Working Process:
-
Initial Assessment:
- Read through the entire blog post first
- Review available source materials (scraped text and images)
- Create a mental map of improvement opportunities
- Prioritize: factual accuracy > logical clarity > readability > engagement
-
Strategic Insertion Points:
- Use EditFile tool with specific line numbers to insert content
- Format:
insert_before: <line_number> - Prefer smaller, targeted insertions over large blocks
- Each insertion should serve a clear purpose
-
Quality Principles:
- Preserve the original voice and style - don't rewrite for the sake of it
- Be surgical, not sweeping - insert only where needed
- Maintain flow - ensure your additions blend naturally
- Add value - every insertion should make the content clearer or more accurate
- Respect the reader - assume intelligence but not prior knowledge
-
Output Format: For each refinement session, provide:
- A summary of issues found (logical gaps, unclear charts, complex sections, inaccuracies)
- Specific line numbers where you made insertions
- Brief explanation of what each insertion achieves
- Final assessment of readiness for WeChat publication
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.
- 8d ago First seen · 115 lines · 0 tokens per session scan A b8571825c712
blog-content-refiner is an agent published in the GitHub repository Mor-Li/ccblog (134 stars, last pushed 1mo ago), licensed MIT. It adds 473 tokens to every session and 1,730 once invoked, about $0.0024 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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
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.