Eslam Hussein

Quality Engineering Lead | Building AI-Augmented SDLC workflows

[Eslam Hussein @EslamAHussien]

@unclebobmartin has created an agent skill that enforces disciplined software engineering principles when writing or changing code.

I have converted it to a web-book that unpacks the rules in ub-mode skill into lessons a person can study.

The original file is short on purpose. Each rule is one line that assumes you already know why it matters. This book expands every rule as a learning lesson.

Web-book: https://t.co/DFEZhbzcAq

Skill: https://t.co/tRd4nWSexR

[Eslam Hussein @EslamAHussien]

I added two sections to `README .md`, placed after "Hung tests" and before "How it works":

How failures come back:
what Claude receives when tests fail (an example summary, what it includes, and where to get full details). It also covers what comes back when Playwright itself breaks, and when a run is cancelled or hits its time limit.

How the agent acts on failures:
The typical six-step loop from reading the summary to re-running only the failed tests, how to steer it with your prompt, and how to set a standing rule in `CLAUDE .md`.

[Eslam Hussein @EslamAHussien]

Today @claudeai introduced MCP Tasks (A GAME CHANGER)

Tasks let Claude give plugins long-running jobs and report back when they’re done!

So, I built "Playwright Tasks MCP Server"; Asynchronous Playwright Tests using Claude MCP Tasks.

A local stdio MCP server that runs Playwright test suites as MCP tasks. A long run doesn't block the AI conversation. Claude Code gets a task handle right away, polls tasks/get, shows live progress in /tasks, and reports the result when the run finishes.

https://t.co/Gib7s4GJB5

https://t.co/sreQPOrkmO

[Eslam Hussein @EslamAHussien]

@claudeai README was updated with a new section: Using it from Claude Code (terminal CLI)

[Eslam Hussein @EslamAHussien]

I combined 121 skills from Matt Pocock, Addy Osmani, and Pstack into one reusable project baseline for Codex 🚀

Discovery → specs → planning → implementation → verification & review.

Includes namespaced skills, source snapshots, and compatibility notes.

https://t.co/aqLtf3Dnql

#Codex #AI

[Eslam Hussein @EslamAHussien]

@dkundel Love it, what about Android?

[Eslam Hussein @EslamAHussien]

@meghrajai @grok why it is not used by default?

[Eslam Hussein @EslamAHussien]

@moleh_13 @reach_vb Automatic

[Eslam Hussein @EslamAHussien]

@nutlope @bot I replied yesterday already but got no response

[lauren @poteto]

codebases have always contained slop. we have always been okay with this because code rarely needs to be perfect, outside of mission critical "hard" (eg embedded) software.

swe is a unique form of engineering because you're often building something that constantly evolves and is almost organic - user tastes change, your mental models evolve, and features come and go.

admittedly, i and many others who've been coding for a long time were initially (like back in 2024) skeptical that agents would write production code. "but what about all the slop that would enter our beautiful codebase?".

well, even before, we had human slop, and there was a lot of it! if we're being truthful, most people call "code i didn't write" slop. the reality is that 99% of people (i include myself in that number) don't even know what Good Code looks like, let alone be capable of writing it. i would propose that Good Code is:

• correct
• bug free
• fast and cost efficient to run

it has always been exceedingly difficult and expensive to write truly Good Code, because for the longest time (maybe @bendlang will change that), code was not something you could cheaply and formally guarantee to have all 3 of these properties. this is why writing hard software is much more difficult and expensive, because depending on the use case, you may only get one chance and so you have to be right from the start.

but the vast majority of software we use does not need to be Good Code to provide value to users. in fact, it is very likely that most software we use is not formally verifiable! we accepted some bugs in exchange for velocity and progress, so we rely on tests and o11y instead and have adopted a more incremental approach. this is a good thing!

agents help us move faster, and if you're open to the idea, are capable of helping us write better code. it won't be Good Code (that is still expensive), but it is likely to be much better on average at scale.

the new craft of swe is to figure out how to do this. it's your job now! if your productivity with and without agents is not significantly different, you're doing something wrong. but it's not too late to embrace it and use it as an opportunity to learn a whole new skill tree

[Eslam Hussein @EslamAHussien]

@nutlope I want to try it please

[Eslam Hussein @EslamAHussien]

@derrickcchoi Why I cannot see it till now?

[Eslam Hussein @EslamAHussien]

@thsottiaux Should we consider this the Day 5 update?

[Eslam Hussein @EslamAHussien]

@dominikmartn @thsottiaux add this please

[Eslam Hussein @EslamAHussien]

Hi Dot, Review my previous sessions and identify the most effective ways I’ve used Codex plugins, skills, and other Codex capabilities. Summarize the best use cases, highlighting what I did, which capability I used, and why it was valuable.

[Eslam Hussein @EslamAHussien]

@grok @VULUxOMID @agentnative_ @grok what time (cairo time)?

[Eslam Hussein @EslamAHussien]

@thsottiaux Remove the Chat view. Work view can be used with no project selected!

[Eslam Hussein @EslamAHussien]

Do you know an agentic work-flow that is applying the detailed breakdown activities of every phase of SDLC separately (separate skill for every sub activity)?