Scotchloaf

K.Ds burner account #35

[tonbi @tonbistudio]

Today's Hermes Agent Masterclass is the finale! Module 10 covers security, an important topic for running agents to ensure each agent can perform its tasks while minimizing exposure. Hermes has a ton of built-in security features. In this clip, I show how you can set approvals for each profile depending on your needs.

[Miles Deutscher @milesdeutscher]

If you use Hermes agent, you need to install this skill.

There's a free Hermes Agent skill that automatically removes your personal data from every data broker on the internet.

It's called Unbroker. Here's what it does and how to set it up:

What it actually does

Data brokers regularly collect and sell your personal information.

Think: Name, address, phone number, email, relatives - everything.

Unbroker scans every broker site, finds where your data is exposed, and sends removal requests automatically.

It also handles the follow-up verification emails too.

(Think Incogni, but self-hosted, free, and running on your own agent).

How to set it up:

Step 1. Install Hermes Agent

TERMINAL COMMAND

curl -fsSL https://t.co/VjaSh2SnRm | bash

Or download Hermes Desktop for a no-terminal setup ( https://t.co/IOKhCwcDB6 ).

Step 2. Install the Unbroker skill

TERMINAL COMMAND

hermes skills install official/security/unbroker

Or tell Hermes "I want you to install this skill: https://t.co/Mu8y6LdFWC."

Step 3. Run it

Start a new Hermes session and send:

"Use the unbroker skill to remove my data from data brokers. Here is my consent. Run it hands-off and show me the human-task digest at the end."

It's that simple.

[ClaudeDevs @ClaudeDevs]

A few patterns we frequently use with Fable 5:

Use Fable 5 as an "advisor."

An executor (Sonnet 5) calls Fable 5 for guidance.

Most tokens are billed at the lower executor rate.

[Prompter @PromptLLM]

Insane Fable 5 Prompt

[Prajwal Tomar @PrajwalTomar_]

Fable 5 goes pay per use in 2 days. Make it train its replacement before it does.

Have Fable 5 write Skills for the models you'll actually keep using, so its judgment stays even after the model goes behind credits.

The best version from the thread: tell Fable it's "a retiring principal engineer" leaving a complete skill library behind for the team.

→ It audits your repo like an incoming senior engineer
→ Writes 10-16 SKILL files: debugging playbook, change rules, the failure stories that cost real time
→ Opus and Sonnet then run that playbook on cheaper sessions, at Fable's standard

Fair warning from the thread: the run can eat 30% of your weekly Fable usage. Still worth it.

Full prompt in comment 1, my Fable 5 playbook below. Bookmark this.

[Mike Fishbein @mfishbein]

Fable 5 is included in Claude subs until July 7th.

Run these 5 prompts in Claude Code immediately:

1. "Review ROADMAP. md. Write a detailed development task list for building the entire thing. Include tests that will prove to yourself that what you built works. Then run /goal to build our entire roadmap overnight."

2. "Here's the tool I want to build: [idea]. Write the full spec, write the test suite, build it, then use browser control to run every user flow yourself. Loop until every flow passes. Then suggest opportunities for improvement."

3. "Use my browser to go through every page of [SaaS tool we torch budget on]. Write a detailed product requirements document based on what you find so we can build our own custom version of it."

4. "Rebuild our entire codebase from scratch. The old version is your spec. Turn it into a development plan for building a 10x better version. Write tests that capture everything it currently does, then loop until the new version passes all of them."

5. "Review our current codebase. What new features or capabilities would make this 10x more valuable? Create a detailed roadmap for building it out, including clearly defined acceptance criteria for each feature."

[Jonny Lazarus @JLazzy23]

This is the only burner account I’ll ever recommend to follow

[Roan @RohOnChain]

this is f*cking dangerous

build hedge fund using "loop engineering" that prints alpha 24/7 (Full Guide)

if I had this a year ago, I would've built my hedge fund in a week instead of a year

bookmark before someone takes it down

[Roan @RohOnChain]

https://t.co/JRsWSeUfrN

[Khairallah AL-Awady @eng_khairallah1]

this is f*cking gold

How to build your first AI agent (Full guide)

if I had this a year ago, I would've shipped my first app in a day instead of 2 weeks

in the right hands, this changes everything:

[Vox @Voxyz_ai]

stop telling Claude Code/Codex "do this".
stop telling Claude Code/Codex "write code".
stop telling Claude Code/Codex "fix this bug".

you're using a 𝘀𝗲𝗻𝗶𝗼𝗿 𝗔𝗜 like it's a 𝗷𝘂𝗻𝗶𝗼𝗿 𝗶𝗻𝘁𝗲𝗿𝗻.

here are 8 prompts and goals you can copy-paste directly.

[Khusboo Tayal @KhusbooT14835]

COMPLETE CLAUDE CODE COURSE OF 4 HOURS

This is the most comprehensive Claude guide I've seen on the internet.

Bookmark it before you forget it.

4 hours.
Build tools.
Automate your work.

[darkzodchi @zodchiii]

Google CEO, Sundar Pichai:

"If you don't learn to how to orchestrate agents now, you'll spend 2027 catching up to people who started today"

In 30 minutes he explains why the best engineers stopped writing code and started running agents.

Watch the interview, then save the exact setup below 👇

[Movez @0xMovez]

Claude Code creator:

"100% of our pull requests at Anrtopic are run by Claude Code. 80–90% of code review too.

The feature I’m using the most today is /loops. I’m not prompting Claude anymore - I’m building loops"

in 1-hour interview, Boris reveals his setup, which helps him build the #1 coding tool of this year.

Worth more than a $500 vibe-coding course.

[Hamza Khalid @humzaakhalid]

A TWEET WITH 6.5 MILLION VIEWS JUST KILLED THE PROMPT ENGINEER JOB TITLE

Peter Steinberger wrote 8 words that changed how builders think about AI:

"you should be designing loops that prompt your agents."

this is one of the best engineering frameworks i've seen in a long time.

in this cheatsheet I broke down exactly how loop engineering works:

→ layer 1 was context engineering (2024)
→ layer 2 was harness engineering (2025)
→ layer 3 is loop engineering (2026)

the loop needs 6 things: a heartbeat, worktrees, skills, plugins, a checker, and memory

STATE. md, SKILL. md, VISION. md, the files that keep the loop alive between sessions

you don't have a claude problem.
you have a system problem.

instead of another show tonight, read this.

make sure to bookmark it before it gets lost in your feed.

the guide is in the article below.

[SCOTTY BEAM @ScottyBeamIO]

THIS CHINESE GUY MAKES $10,000+/MONTH FROM AN AI INFLUENCER THAT DOESN'T EXIST. HE JUST DROPPED THE FULL BLUEPRINT.

Aitana Lopez. Brand deals with Victoria's Secret and Razer. 10k/month. Not a real person.

He built her with 4 files and Claude Code. Here's the entire system:

–> File 1: persona. md

Full backstory, personality, interests, opinions, how she types, topics she never touches. Done when you can answer 20 questions about her without thinking.

–> File 2: voice. md

$40 voice actress from Fiverr. Clone it on ElevenLabs in 10 minutes. Real sounding voice for reels and stories. Rules for when she sends voice notes and how she sounds human.

–> File 3: flux. md

Pick a base face. Lock 6-8 physical descriptors. Generate 50 variations. Fine-tune a LoRA so every image is the same person. Three lighting setups for variety. ~$80 on rented GPU.

–> File 4: brain. md

Memory file storing every brand, follower, conversation, and content interaction. Claude Code reads all 4 files before every interaction. She never breaks character. Ever.

Total setup cost: ~$120. Monthly income potential: $10,000+.

The AI influencer economy is already here. Most people just haven't started yet.

Bookmark this post. Full step-by-step guide is in the video below.

[Harry Tandy @HarryTandy]

Boris Cherny: "Overnight sub-agents do deeper work"

10-step Fable 5 setup you can copy this week:

1. Write CLAUDE.md
- stack
- commands
- code style
- forbidden files
- review rules

2. Add PROJECT_MEMORY.md
- verified facts
- failed attempts
- last session
- next run

3. Create 1 Skill per repeated workflow
- CI triage
- PR review
- design QA
- deploy check

4. Add eval cases
Put them in:

eval/<workflow>.jsonl

5. Split maker and verifier
Maker writes the chang
Verifier runs the app, tests, screenshots, logs

6. Use worktrees for parallel runs
No shared checkout
No file collisions
No mystery edits

7. Send work by price
Fable 5 plans across days
Sonnet 4.6 does bulk edits
Haiku 4.5 grades
Opus 4.8 handles fallback cases

8. Put UI work behind screenshots
If the task is visual, text logs aren't enough

9. Move long jobs to Routines
CI failed? Run triage
PR opened? Run review
7am? Send digest

10. End every run by writing the lesson back
A fix that stays in chat dies there

The rule:

> Builder makes the change
> Verifier checks the real artifact
> Memory keeps the receipt
> You read the diff

Skip the verifier and you don't have an agent system

You have a very confident intern with shell access

[Frogify @0xFrogify]

https://t.co/eqMgjDvav5

[Alex Finn @AlexFinn]

Loops are clearly the future of AI coding

The issue is, it’s being completely gate kept. And I think I know why

Over the last few days both OpenAI and Anthropic employees have been vague posting about loops. None have explained how they’re actually doing it

That’s because loops are the last moat

If everyone has the same level super intelligence, then using the AI no longer gives you an advantage

But if you come up with a system that allows your AI to work autonomously, giving 1000x leverage to each person in your org, then you have a legit moat again

If Anthropic shared their internal loop system with the world and stopped gatekeeping, their team would no longer have any advantage over any other lab

That’s why every frontier lab employee is gate keeping right now. That’s why everything on your timeline is a vague post. Loops are true technical IP.

This is why it’s so critical you start developing your own automated loops with your agents. Like literally right now.

Fable 5 leveled the playing field. Anyone can now build anything they want. Loops are what give you the high ground in the playing field again. Your competition isn’t building this.

If you and your competitor are building the same product, but you are using a loop and they aren’t, you’ll destroy them. You’ll be able to build 24/7/365 while they can only ship while they are at their keyboard.

You need to RIGHT NOW drop what you’re doing and start developing this system. Even if you’re just talking to your Hermes Agent or your Claude app on your phone

The game pieces moved. The battlefield shifted. Just using AI is no longer an advantage. Fable has made it too easy.

Now you need to automate.

3 days ago I thought loops were impossible. Now I think they’re mandatory.

I’d do this:

1. Go to your agent
2. Explain what you’re building
3. Ask what system you can build and which tools do you need to create an automated loops that continuously ships and reviews code.
4. Use the latest models. Ideally Fable 5, but GPT 5.5 if you need to.
5. Build out whichever plan they give you. Use it over and over. Each time you use it, find a part of it to tweak, fix, or improve.
6. The more you use the loop, the better it will get.

Most important AI project you can be implementing right now. Will 1000x the work you do moving forward. Will also give you a leg up on the battlefield.

Time to act.