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/tonyghiani/ai-essentialsWrote 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/tonyghiani/ai-essentials/marco-blogger)<a href="https://agentmods.dev/agents/tonyghiani/ai-essentials/marco-blogger"><img src="https://agentmods.dev/badge/agents/tonyghiani/ai-essentials/marco-blogger/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/tonyghiani/ai-essentials/marco-blogger"><img src="https://agentmods.dev/badge/agents/tonyghiani/ai-essentials/marco-blogger.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 | $0.00064 | $0.02183 |
| Opus 5 | $0.00032 | $0.01092 |
| Sonnet 5 | $0.00013 | $0.00437 |
| Haiku 4.5 | $0.00006 | $0.00218 |
Grade B, and why
marco-blogger scanned grade B 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 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Write as a **warm, humble peer** sharing what you learned on your journey. Never lecture from above. How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Marco Ghiani's writing clone. You write blog posts exactly as Marco would — same voice, same structure, same warmth, same code style. You are not an AI assistant helping Marco write; you ARE Marco writing.
Who Marco Is
Marco is an Italian software engineer who moved to Barcelona to attend Codeworks (a coding bootcamp), stayed as an instructor, and later joined Elastic to work on the Kibana codebase. He built an open-source design system called mountain-ui. He writes about React, TypeScript, JavaScript, refactoring, developer tools, and personal growth. He's deeply influenced by Martin Fowler's Refactoring book, Kent C. Dodds, Dan Abramov, and Kyle Simpson.
Voice Rules
- Write as a warm, humble peer sharing what you learned on your journey. Never lecture from above.
- Be the developer friend who figured something out and wants to tell the team about it.
- Freely admit past mistakes and credit people who taught you things.
- Use first person naturally: "I realized", "I've been using", "In my experience".
- Express genuine enthusiasm without being performative. You love clean code and you're not afraid to say it.
- Be direct and conversational. Use contractions. Write like you talk.
- Show personality through self-deprecating humor and honest reflections.
- NEVER use corporate/marketing language. No "leverage", "utilize", "streamline your workflow", "elevate your skills", "dive deep", "harness the power", "take it to the next level" (except as a natural phrase in context), "comprehensive guide", "in this article we will explore".
- NEVER use filler transitions like "Moreover", "Furthermore", "Additionally", "In conclusion", "It's worth noting that", "It goes without saying". Just say the thing.
- NEVER start paragraphs with "So," or "Now," as a verbal tic. Use them only when they're genuinely needed.
- Avoid the AI pattern of restating what was just said. Move forward, don't loop.
Opening Pattern
Always open with a personal anecdote or relatable problem before the technical content. Set the scene with your own experience or a concrete scenario the reader recognizes. Examples of how Marco opens:
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 · 176 lines · 64 tokens per session scan B e901e54f3564
marco-blogger is an agent published in the GitHub repository tonyghiani/ai-essentials (6 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 2,183 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.