Fragmented - AI Developer Podcast

AGENTS.md is becoming the common language for AI coding tools, but keeping repo

rules, personal rules, and tool-specific files in sync is still messy. In this

episode, Kaushik and Iury break down the sync problem, compare their own setups,

and unpack what the latest AGENTS.md research actually says.

Full shownotes at fragmentedpodcast.com.

Show Notes

The sync problem

AGENTS.md - Official spec

Custom instructions with AGENTS.md -

Open AI

Keep your AGENTS.md in sync - Kaushik's post

Rulesync - What Iury uses

Tweet by Ryan Carson and Claude frustrations

Other links

Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?

Harness engineering - Check the section about using AGENTS.md as a table of contents

OpenCode

Get in touch

We'd love to hear from you. Email is the

best way to reach us or you can check our contact page for other

ways.

We want to hear all the feedback: what's working, what's not, topics you'd like

to hear more on.

Contact us

Newsletter

Youtube

Website

Co-hosts:

Kaushik Gopal

Iury Souza

[!fyi] We transitioned from Android development to AI starting with
Ep. #300. Listen to that episode for the full story behind

our new direction.

Subagents are becoming a core primitive for serious AI-assisted development. In this episode, Kaushik and Iury disambiguate "agent" terminology, unpack plan mode vs subagents, and explain how parallel, scoped workers improve research quality without polluting the main thread.
Full shownotes at fragmentedpodcast.com.
Show Notes
Resources & Documentation
Official Documentation
Agents, Modes, Subagents: official harness docs
Claude Code Subagents
Gemini CLI Subagents
Opencode Subagents
Cursor Subagents
Antigravity Agent Modes
AOE Scouting
Research Papers & Articles
Introducing Claude Opus 4.5
Deep-Research Agents Paper
Post: GPT-5 System Card by Alex
Xu
Self-Driving Codebases Blog -
multi-agent systems making 1,000 commits/hour
Get in touch
We'd love to hear from you. Email is the
best way to reach us or you can check our contact page for other
ways.
We want to hear all the feedback: what's working, what's not, topics you'd like
to hear more on.
Contact us
Newsletter
Youtube
Website
Co-hosts:
Kaushik Gopal
Iury Souza
[!fyi] We transitioned from Android development to AI starting with
Ep. #300. Listen to that episode for the full story behind
our new direction.

Agent Skills look simple, but they are one of the most powerful building blocks
in modern AI coding workflows. In this episode, Kaushik and Iury break down when
to use skills, how progressive disclosure works, and how skills compare with
commands, instructions, and MCPs.
Full shownotes at fragmentedpodcast.com.
Show Notes
Main References
Progressive Disclosure -
how skills are loaded into context
Agent Skills Open Specification
AAIF (Agentic AI Foundation) -
Linux Foundation initiative for AI interoperability
Needle in a Haystack Problem - original
"Lost in the Middle" paper
Agent-Invokable vs User-Invokable -
merging skills and commands in Claude Code
Creating Skills
Skill Creator -
Anthropic's skill for creating new agent skills
Claude Code frontmatter referencesee model: * & context: fork

Using other Skills
Anthropic Skills GitHub Repository -
official collection of Claude skills and examples
Clawdhub - Clawdbot's skill hub. All versions are
archived here
SKILLS.sh - Vercel's skills hub
Warnings before installing random skills
[!warning] Don't install from hubs blindly.
Inspect the repo code before adding anything to your agent.
Prompt Injection Attacks -
OWASP guide to LLM prompt injection vulnerabilities
OpenClaw
OpenClaw Security Analysis -
analysis of prompt injection risks in open agent frameworks
Malware found in a top-downloaded Clawhub skill -
incident report thread
Additional resources
Few-Shot Prompting -
improving outputs with examples
.agents/skills - proposal
to standardize the skills folder path
Vercel: AGENTS.md vs Skills -
comparison of agent instruction methods
Get in touch
We'd love to hear from you. Email is the
best way to reach us or you can check our contact page for other
ways.
We want to hear all the feedback: what's working, what's not, topics you'd like
to hear more on.
Contact us
Newsletter
Youtube
Website
Co-hosts:
Kaushik Gopal
Iury Souza
[!fyi] We transitioned from Android development to AI starting with
Ep. #300. Listen to that episode for the full story behind
our new direction.

Ever get asked "how do LLMs work?" at a party and freeze? We walk through the full pipeline: tokenization, embeddings, inference — so you understand it well enough to explain it. Walk away with a mental model that you can use for your next dinner party.
_Full shownotes at fragmentedpodcast.com.
Show Notes
Words -> Tokens:
OpenAI Tokenizer visualizer -
Visualize how text becomes tokens
Tokens -> Embeddings:
RGB Color model - wikipedia
Word2Vec technique - wikipediaEfficient Estimation of Word Representation -
original Word2Vec paper by Mikolov et al.

Embeddings -> Inference:
Word embedding
Temperature, Top-k, Top-p samping
Get in touch
We'd love to hear from you. Email is the
best way to reach us or you can check our contact page for other
ways.
We want to hear all the feedback: what's working, what's not, topics you'd like
to hear more on. We want to make the show better for you so let us know!
Contact us
Newsletter
Youtube
Website
Co-hosts:
Kaushik Gopal
Iury Souza
[!fyi] We transitioned from Android development to AI starting with
Ep. #300. Listen to that episode for the full story behind
our new direction.

MCPs are everywhere, but are they worth the token cost? We break down what Model Context Protocol actually is, how it differs from just using CLIs, the tradeoffs you should know about, and when MCPs actually make sense for your workflow.
Full shownotes at fragmentedpodcast.com/episodes/302.
Show Notes
MCP - Model Context Protocol
Remote MCP server example - Glean
AAIF -
Agentic AI Foundation setup by Linux foundation
Github MCP
Github gh CLI
Playwright MCP
Context7 MCP
Anthropic's announcement on
Advanced Tool Use
Tips
Iury: use ast-grep to structurally
search code faster
KG: use agent-browser by Vercel to give browsing
power to your agent
Get in touch
We'd love to hear from you. Email is the
best way to reach us or you can check our contact page for other
ways.
We want to hear all the feedback: what's working, what's not, topics you'd like
to hear more on. We want to make the show better for you so let us know!
Contact us
Newsletter
Youtube
Website
Co-hosts:
Kaushik Gopal
Iury Souza
We transitioned from Android development to AI starting with
Ep. #300. Listen to that episode for the full story behind
our new direction.