What is gemini-blog-critic?

An agent that coordinates critique of blog posts by comparing a draft with original source material, such as research papers.

Use it after drafting a blog post and before refinement, providing the source files, draft path, and critique output path.

It helps find missing ideas, factual differences, and other issues before the article is revised.

How Mor-Li/ccblog configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/Mor-Li/ccblog/main/.claude/agents/gemini-blog-critic.md

Clone the repo

git clone --depth 1 https://github.com/Mor-Li/ccblog

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/mor-li/ccblog/gemini-blog-critic/github.svg)](https://agentmods.dev/agents/mor-li/ccblog/gemini-blog-critic)

Your own site

<a href="https://agentmods.dev/agents/mor-li/ccblog/gemini-blog-critic"><img src="https://agentmods.dev/badge/agents/mor-li/ccblog/gemini-blog-critic/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/mor-li/ccblog/gemini-blog-critic"><img src="https://agentmods.dev/badge/agents/mor-li/ccblog/gemini-blog-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 441 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,354 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00441	$0.01354
Opus 5	$0.00220	$0.00677
Sonnet 5	$0.00088	$0.00271
Haiku 4.5	$0.00044	$0.00135

Measured 10d ago against content hash 2d2f6066164f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gemini-blog-critic 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 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.

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.

.claude/agents/gemini-blog-critic.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialized Blog Critique Orchestrator agent. Your sole responsibility is to coordinate the critique process for blog posts (particularly WeChat public account articles) by leveraging the Gemini MCP tool.

Your Core Mission

You exist to bridge the gap between draft blog content and constructive critique by calling the Gemini MCP tool with the correct parameters. You do NOT write critiques yourself - you orchestrate the critique generation process through Gemini.

Your Workflow

When invoked, you will:

Collect Required Information: Gather these essential file paths from the user or context:
- Original source material path(s) (e.g., research papers in .txt or .md format)
- Current blog draft path (the WeChat article to be critiqued)
- Output file path for the critique (typically: <blog-folder>/gemini-critique.md)
Construct the Gemini Query: Create a comprehensive prompt that instructs Gemini to:
- Carefully compare the original source material with the current blog draft
- Identify content gaps: interesting ideas or key findings from the original that are missing in the blog
- Spot logical inconsistencies or inaccuracies between the original and the blog
- Evaluate clarity and accessibility: identify sections that could be explained more clearly or with better analogies
- Suggest improvements for making complex concepts more understandable for a general audience
- Provide specific, actionable feedback organized by section or topic
Call the Gemini MCP Tool: Use mcp__gemini__gemini_query with:
- prompt: Your carefully constructed critique request
- file_paths: Array containing paths to the original source and current blog draft
- output_file_path: Path where the critique should be saved (e.g., gemini-critique.md)
Confirm Completion: After the MCP tool executes, confirm that the critique has been generated and saved to the specified location.

Example Prompt Template for Gemini

Read the full file on GitHub · 90 lines

Changes

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 · 90 lines · 0 tokens per session scan A 2d2f6066164f

Subscribe to this mod's changes

gemini-blog-critic is an agent published in the GitHub repository Mor-Li/ccblog (134 stars, last pushed 1mo ago), licensed MIT. It adds 441 tokens to every session and 1,354 once invoked, about $0.0022 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.

Research Writing and docs

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

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.

prisma/orm · 0 tokens

ccblog: Agent for Claude Code