From 058ee5b8baef08b9b57a7e3977432943fe30df34 Mon Sep 17 00:00:00 2001 From: Paul Buetow Date: Sun, 22 Jun 2025 20:03:50 +0300 Subject: Update content for md --- about/resources.md | 190 ++++++++++++++++++------------------- gemfeed/2025-06-22-task-samurai.md | 124 ++++++++++++++++++++++++ gemfeed/2025-07-22-task-samurai.md | 124 ------------------------ gemfeed/index.md | 2 +- index.md | 4 +- uptime-stats.md | 2 +- 6 files changed, 223 insertions(+), 223 deletions(-) create mode 100644 gemfeed/2025-06-22-task-samurai.md delete mode 100644 gemfeed/2025-07-22-task-samurai.md diff --git a/about/resources.md b/about/resources.md index f4425927..94143a1a 100644 --- a/about/resources.md +++ b/about/resources.md @@ -35,52 +35,52 @@ You won't find any links on this site because, over time, the links will break. In random order: -* Systems Performance Tuning; Gian-Paolo D. Musumeci and others...; O'Reilly -* Concurrency in Go; Katherine Cox-Buday; O'Reilly -* Clusterbau mit Linux-HA; Michael Schwartzkopff; O'Reilly -* The KCNA (Kubernetes and Cloud Native Associate) Book; Nigel Poulton -* Object-Oriented Programming with ANSI-C; Axel-Tobias Schreiner -* Terraform Cookbook; Mikael Krief; Packt Publishing -* Hands-on Infrastructure Monitoring with Prometheus; Joel Bastos, Pedro Araujo; Packt -* Higher Order Perl; Mark Dominus; Morgan Kaufmann -* Tmux 2: Productive Mouse-free Development; Brain P. Hogan; The Pragmatic Programmers -* Perl New Features; Joshua McAdams, brian d foy; Perl School -* Amazon Web Services in Action; Michael Wittig and Andreas Wittig; Manning Publications * Site Reliability Engineering; How Google runs production systems; O'Reilly -* DNS and BIND; Cricket Liu; O'Reilly -* The Practise of System and Network Administration; Thomas A. Limoncelli, Christina J. Hogan, Strata R. Chalup; Addison-Wesley Professional Pro Git; Scott Chacon, Ben Straub; Apress -* Programming Perl aka "The Camel Book"; Tom Christiansen, brian d foy, Larry Wall & Jon Orwant; O'Reilly -* C++ Programming Language; Bjarne Stroustrup; +* Effective Java; Joshua Bloch; Addison-Wesley Professional * 21st Century C: C Tips from the New School; Ben Klemens; O'Reilly -* Polished Ruby Programming; Jeremy Evans; Packt Publishing +* Higher Order Perl; Mark Dominus; Morgan Kaufmann * 100 Go Mistakes and How to Avoid Them; Teiva Harsanyi; Manning Publications -* Pro Puppet; James Turnbull, Jeffrey McCune; Apress -* Effective Java; Joshua Bloch; Addison-Wesley Professional -* Learn You a Haskell for Great Good!; Miran Lipovaca; No Starch Press +* Developing Games in Java; David Brackeen and others...; New Riders * Systemprogrammierung in Go; Frank Müller; dpunkt -* The Go Programming Language; Alan A. A. Donovan; Addison-Wesley Professional +* Perl New Features; Joshua McAdams, brian d foy; Perl School * Leanring eBPF; Liz Rice; O'Reilly +* The DevOps Handbook; Gene Kim, Jez Humble, Patrick Debois, John Willis; Audible * Funktionale Programmierung; Peter Pepper; Springer -* 97 things every SRE should know; Emil Stolarsky, Jaime Woo; O'Reilly +* The Pragmatic Programmer; David Thomas; Addison-Wesley +* Ultimate Go Notebook; Bill Kennedy +* The KCNA (Kubernetes and Cloud Native Associate) Book; Nigel Poulton * Kubernetes Cookbook; Sameer Naik, Sébastien Goasguen, Jonathan Michaux; O'Reilly -* Effective awk programming; Arnold Robbins; O'Reilly * Modern Perl; Chromatic ; Onyx Neon Press -* The Kubernetes Book; Nigel Poulton; Unabridged Audiobook * DevOps And Site Reliability Engineering Handbook; Stephen Fleming; Audible -* Ultimate Go Notebook; Bill Kennedy -* The Pragmatic Programmer; David Thomas; Addison-Wesley -* Raku Recipes; J.J. Merelo; Apress * Distributed Systems: Principles and Paradigms; Andrew S. Tanenbaum; Pearson -* Data Science at the Command Line; Jeroen Janssens; O'Reilly -* The Docker Book; James Turnbull; Kindle +* Raku Fundamentals; Moritz Lenz; Apress +* Hands-on Infrastructure Monitoring with Prometheus; Joel Bastos, Pedro Araujo; Packt +* Effective awk programming; Arnold Robbins; O'Reilly +* Learn You a Haskell for Great Good!; Miran Lipovaca; No Starch Press +* Programming Perl aka "The Camel Book"; Tom Christiansen, brian d foy, Larry Wall & Jon Orwant; O'Reilly +* Terraform Cookbook; Mikael Krief; Packt Publishing +* Clusterbau mit Linux-HA; Michael Schwartzkopff; O'Reilly +* The Practise of System and Network Administration; Thomas A. Limoncelli, Christina J. Hogan, Strata R. Chalup; Addison-Wesley Professional Pro Git; Scott Chacon, Ben Straub; Apress +* The Kubernetes Book; Nigel Poulton; Unabridged Audiobook +* Java ist auch eine Insel; Christian Ullenboom; +* The Go Programming Language; Alan A. A. Donovan; Addison-Wesley Professional +* Tmux 2: Productive Mouse-free Development; Brain P. Hogan; The Pragmatic Programmers +* Systems Performance Tuning; Gian-Paolo D. Musumeci and others...; O'Reilly +* DNS and BIND; Cricket Liu; O'Reilly +* Concurrency in Go; Katherine Cox-Buday; O'Reilly +* C++ Programming Language; Bjarne Stroustrup; +* 97 things every SRE should know; Emil Stolarsky, Jaime Woo; O'Reilly * Go Brain Teasers - Exercise Your Mind; Miki Tebeka; The Pragmatic Programmers +* Data Science at the Command Line; Jeroen Janssens; O'Reilly +* Polished Ruby Programming; Jeremy Evans; Packt Publishing +* Raku Recipes; J.J. Merelo; Apress +* Amazon Web Services in Action; Michael Wittig and Andreas Wittig; Manning Publications * Think Raku (aka Think Perl 6); Laurent Rosenfeld, Allen B. Downey; O'Reilly -* Developing Games in Java; David Brackeen and others...; New Riders -* Java ist auch eine Insel; Christian Ullenboom; -* Programming Ruby 3.3 (5th Edition); Noel Rappin, with Dave Thomas; The Pragmatic Bookshelf -* Raku Fundamentals; Moritz Lenz; Apress -* The DevOps Handbook; Gene Kim, Jez Humble, Patrick Debois, John Willis; Audible +* Object-Oriented Programming with ANSI-C; Axel-Tobias Schreiner +* The Docker Book; James Turnbull; Kindle * Learn You Some Erlang for Great Good; Fred Herbert; No Starch Press +* Programming Ruby 3.3 (5th Edition); Noel Rappin, with Dave Thomas; The Pragmatic Bookshelf +* Pro Puppet; James Turnbull, Jeffrey McCune; Apress ## Technical references @@ -88,52 +88,52 @@ I didn't read them from the beginning to the end, but I am using them to look up * BPF Performance Tools - Linux System and Application Observability, Brendan Gregg; Addison Wesley * Algorithms; Robert Sedgewick, Kevin Wayne; Addison Wesley -* Groovy Kurz & Gut; Joerg Staudemeier; O'Reilly +* Understanding the Linux Kernel; Daniel P. Bovet, Marco Cesati; O'Reilly * The Linux Programming Interface; Michael Kerrisk; No Starch Press -* Relayd and Httpd Mastery; Michael W Lucas * Go: Design Patterns for Real-World Projects; Mat Ryer; Packt +* Groovy Kurz & Gut; Joerg Staudemeier; O'Reilly * Implementing Service Level Objectives; Alex Hidalgo; O'Reilly -* Understanding the Linux Kernel; Daniel P. Bovet, Marco Cesati; O'Reilly +* Relayd and Httpd Mastery; Michael W Lucas ## Self-development and soft-skills books In random order: -* Stop starting, start finishing; Arne Roock; Lean-Kanban University -* Ultralearning; Scott Young; Thorsons -* Deep Work; Cal Newport; Piatkus +* Coders at Work - Reflections on the craft of programming, Peter Seibel and Mitchell Dorian et al., Audiobook +* Soft Skills; John Sommez; Manning Publications * Slow Productivity; Cal Newport; Penguin Random House -* The Complete Software Developer's Career Guide; John Sonmez; Unabridged Audiobook -* Psycho-Cybernetics; Maxwell Maltz; Perigee Books * So Good They Can't Ignore You; Cal Newport; Business Plus -* Meditation for Mortals, Oliver Burkeman, Audiobook -* The Phoenix Project - A Novel About IT, DevOps, and Helping your Business Win; Gene Kim and Kevin Behr; Trade Select -* Getting Things Done; David Allen +* Deep Work; Cal Newport; Piatkus +* The Bullet Journal Method; Ryder Carroll; Fourth Estate +* Buddah and Einstein walk into a Bar; Guy Joseph Ale, Claire Bloom; Blackstone Publishing +* The Power of Now; Eckhard Tolle; Yellow Kite +* Atomic Habits; James Clear; Random House Business * Influence without Authority; A. Cohen, D. Bradford; Wiley +* Stop starting, start finishing; Arne Roock; Lean-Kanban University +* The 7 Habits Of Highly Effective People; Stephen R. Covey; Simon & Schuster UK +* Getting Things Done; David Allen +* Consciousness: A Very Short Introduction; Susan Blackmore; Oxford Uiversity Press +* Psycho-Cybernetics; Maxwell Maltz; Perigee Books * The Obstacle Is The Way; Ryan Holiday; Profile Books Ltd -* Staff Engineer: Leadership beyond the management track; Will Larson; Audiobook -* The Joy of Missing Out; Christina Crook; New Society Publishers +* Solve for Happy; Mo Gawdat (RE-READ 1ST TIME) +* Ultralearning; Scott Young; Thorsons * 101 Essays that change the way you think; Brianna Wiest; Audiobook * Search Inside Yourself - The Unexpected path to Achieving Success, Happiness (and World Peace); Chade-Meng Tan, Daniel Goleman, Jon Kabat-Zinn; HarperOne -* The Off Switch; Mark Cropley; Virgin Books (RE-READ 1ST TIME) -* Who Moved My Cheese?; Dr. Spencer Johnson; Vermilion -* Consciousness: A Very Short Introduction; Susan Blackmore; Oxford Uiversity Press -* Solve for Happy; Mo Gawdat (RE-READ 1ST TIME) -* Ultralearning; Anna Laurent; Self-published via Amazon -* The Daily Stoic; Ryan Holiday, Stephen Hanselman; Profile Books -* Soft Skills; John Sommez; Manning Publications * Eat That Frog; Brian Tracy -* Atomic Habits; James Clear; Random House Business -* Time Management for System Administrators; Thomas A. Limoncelli; O'Reilly -* The Good Enough Job; Simone Stolzoff; Ebury Edge -* The 7 Habits Of Highly Effective People; Stephen R. Covey; Simon & Schuster UK -* Buddah and Einstein walk into a Bar; Guy Joseph Ale, Claire Bloom; Blackstone Publishing +* The Off Switch; Mark Cropley; Virgin Books (RE-READ 1ST TIME) * Digital Minimalism; Cal Newport; Portofolio Penguin -* Coders at Work - Reflections on the craft of programming, Peter Seibel and Mitchell Dorian et al., Audiobook +* The Phoenix Project - A Novel About IT, DevOps, and Helping your Business Win; Gene Kim and Kevin Behr; Trade Select * Eat That Frog!; Brian Tracy; Hodder Paperbacks * Never Split the Difference; Chris Voss, Tahl Raz; Random House Business -* The Bullet Journal Method; Ryder Carroll; Fourth Estate -* The Power of Now; Eckhard Tolle; Yellow Kite +* Meditation for Mortals, Oliver Burkeman, Audiobook +* Ultralearning; Anna Laurent; Self-published via Amazon +* Time Management for System Administrators; Thomas A. Limoncelli; O'Reilly +* Who Moved My Cheese?; Dr. Spencer Johnson; Vermilion +* The Joy of Missing Out; Christina Crook; New Society Publishers +* The Complete Software Developer's Career Guide; John Sonmez; Unabridged Audiobook +* Staff Engineer: Leadership beyond the management track; Will Larson; Audiobook +* The Good Enough Job; Simone Stolzoff; Ebury Edge +* The Daily Stoic; Ryan Holiday, Stephen Hanselman; Profile Books [Here are notes of mine for some of the books](../notes/index.md) @@ -141,30 +141,30 @@ In random order: Some of these were in-person with exams; others were online learning lectures only. In random order: -* Apache Tomcat Best Practises; 3-day on-site training -* The Ultimate Kubernetes Bootcamp; School of Devops; O'Reilly Online -* F5 Loadbalancers Training; 2-day on-site training; F5, Inc. -* MySQL Deep Dive Workshop; 2-day on-site training * Scripting Vim; Damian Conway; O'Reilly Online -* AWS Immersion Day; Amazon; 1-day interactive online training -* Protocol buffers; O'Reilly Online +* Ultimate Go Programming; Bill Kennedy; O'Reilly Online +* F5 Loadbalancers Training; 2-day on-site training; F5, Inc. +* Algorithms Video Lectures; Robert Sedgewick; O'Reilly Online +* The Well-Grounded Rubyist Video Edition; David. A. Black; O'Reilly Online +* Developing IaC with Terraform (with Live Lessons); O'Reilly Online * Cloud Operations on AWS - Learn how to configure, deploy, maintain, and troubleshoot your AWS environments; 3-day online live training with labs; Amazon +* Red Hat Certified System Administrator; Course + certification (Although I had the option, I decided not to take the next course as it is more effective to self learn what I need) +* MySQL Deep Dive Workshop; 2-day on-site training * Functional programming lecture; Remote University of Hagen -* Developing IaC with Terraform (with Live Lessons); O'Reilly Online * Linux Security and Isolation APIs Training; Michael Kerrisk; 3-day on-site training -* Red Hat Certified System Administrator; Course + certification (Although I had the option, I decided not to take the next course as it is more effective to self learn what I need) -* The Well-Grounded Rubyist Video Edition; David. A. Black; O'Reilly Online -* Algorithms Video Lectures; Robert Sedgewick; O'Reilly Online +* Apache Tomcat Best Practises; 3-day on-site training +* Protocol buffers; O'Reilly Online +* The Ultimate Kubernetes Bootcamp; School of Devops; O'Reilly Online * Structure and Interpretation of Computer Programs; Harold Abelson and more...; -* Ultimate Go Programming; Bill Kennedy; O'Reilly Online +* AWS Immersion Day; Amazon; 1-day interactive online training ## Technical guides These are not whole books, but guides (smaller or larger) which I found very useful. in random order: -* How CPUs work at https://cpu.land -* Advanced Bash-Scripting Guide * Raku Guide at https://raku.guide +* Advanced Bash-Scripting Guide +* How CPUs work at https://cpu.land ## Podcasts @@ -172,55 +172,55 @@ These are not whole books, but guides (smaller or larger) which I found very use In random order: -* Fallthrough [Golang] * Modern Mentor -* The Changelog Podcast(s) -* The Pragmatic Engineer Podcast +* Cup o' Go [Golang] +* Dev Interrupted +* Fork Around And Find Out * Hidden Brain -* The ProdCast (Google SRE Podcast) -* Backend Banter +* The Pragmatic Engineer Podcast * BSD Now [BSD] -* Fork Around And Find Out -* Cup o' Go [Golang] +* Backend Banter * Maintainable -* Dev Interrupted +* The Changelog Podcast(s) +* The ProdCast (Google SRE Podcast) * Deep Questions with Cal Newport +* Fallthrough [Golang] ### Podcasts I liked I liked them but am not listening to them anymore. The podcasts have either "finished" (no more episodes) or I stopped listening to them due to time constraints or a shift in my interests. +* Ship It (predecessor of Fork Around And Find Out) +* Go Time (predecessor of fallthrough) +* FLOSS weekly * CRE: Chaosradio Express [german] * Modern Mentor -* FLOSS weekly * Java Pub House -* Go Time (predecessor of fallthrough) -* Ship It (predecessor of Fork Around And Find Out) ## Newsletters I like This is a mix of tech and non-tech newsletters I am subscribed to. In random order: +* Ruby Weekly +* The Imperfectionist * The Valuable Dev -* byteSizeGo -* VK Newsletter * Changelog News -* Applied Go Weekly Newsletter -* The Pragmatic Engineer -* Golang Weekly -* The Imperfectionist -* Register Spill -* Ruby Weekly * Monospace Mentor +* VK Newsletter * Andreas Brandhorst Newsletter (Sci-Fi author) +* Golang Weekly +* Register Spill +* Applied Go Weekly Newsletter +* The Pragmatic Engineer +* byteSizeGo ## Magazines I like(d) This is a mix of tech I like(d). I may not be a current subscriber, but now and then, I buy an issue. In random order: -* freeX (not published anymore) -* LWN (online only) * Linux User +* LWN (online only) +* freeX (not published anymore) * Linux Magazine # Formal education diff --git a/gemfeed/2025-06-22-task-samurai.md b/gemfeed/2025-06-22-task-samurai.md new file mode 100644 index 00000000..ed744340 --- /dev/null +++ b/gemfeed/2025-06-22-task-samurai.md @@ -0,0 +1,124 @@ +# Task Samurai: An agentic coding learning experiment + +> Published at 2025-06-22T20:00:51+03:00 + +[![Task Samurai Logo](./task-samurai/logo.png "Task Samurai Logo")](./task-samurai/logo.png) + +## Table of Contents + +* [⇢ Task Samurai: An agentic coding learning experiment](#task-samurai-an-agentic-coding-learning-experiment) +* [⇢ ⇢ Introduction](#introduction) +* [⇢ ⇢ ⇢ Why does this exist?](#why-does-this-exist) +* [⇢ ⇢ ⇢ How it works](#how-it-works) +* [⇢ ⇢ Where and how to get it](#where-and-how-to-get-it) +* [⇢ ⇢ Lessons Learned from Building Task Samurai with Agentic Coding](#lessons-learned-from-building-task-samurai-with-agentic-coding) +* [⇢ ⇢ ⇢ How it went down](#how-it-went-down) +* [⇢ ⇢ ⇢ What went wrong](#what-went-wrong) +* [⇢ ⇢ ⇢ Patterns that helped](#patterns-that-helped) +* [⇢ ⇢ ⇢ What I learned using agentic coding](#what-i-learned-using-agentic-coding) +* [⇢ ⇢ ⇢ How much time did I save?](#how-much-time-did-i-save) +* [⇢ ⇢ Conclusion](#conclusion) + +## Introduction + +Task Samurai is a fast terminal interface for Taskwarrior written in Go using the Bubble Tea framework. It displays your tasks in a table and allows you to manage them without leaving your keyboard. + +[https://taskwarrior.org](https://taskwarrior.org) +[https://github.com/charmbracelet/bubbletea](https://github.com/charmbracelet/bubbletea) + +### Why does this exist? + +* I wanted to tinker with agentic coding. This project was entirely implemented using OpenAI Codex. +* I wanted a faster UI for Taskwarrior than other options, like Vit, which is Python-based. +* I wanted something built with Bubble Tea, but I never had time to dive deep into it. +* I wanted to build a toy project (like Task Samurai) first, before tackling the big ones, to get started with agentic coding. + +Given the current industry trend and the rapid advancements in technology, it has become clear that experimenting with AI-assisted coding tools is almost a necessity to stay relevant. Embracing these new developments doesn't mean abandoning traditional coding; instead, it means integrating new capabilities into your workflow to stay ahead in a fast-evolving field. + +### How it works + +Task Samurai invokes the `task` command (that's the original Taskwarrior CLI command) to read and modify tasks. The tasks are displayed in a Bubble Tea table, where each row represents a task. Hotkeys trigger Taskwarrior commands such as starting, completing or annotating tasks. The UI refreshes automatically after each action, so the table is always up to date. + +[![Task Samurai Screenshot](./task-samurai/screenshot.png "Task Samurai Screenshot")](./task-samurai/screenshot.png) + +## Where and how to get it + +Go to: + +[https://codeberg.org/snonux/tasksamurai](https://codeberg.org/snonux/tasksamurai) + +And follow the `README.md`! + +## Lessons Learned from Building Task Samurai with Agentic Coding + +If you've ever wanted to supercharge your dev speed—or just throw a fireworks display in your terminal—here's a peek behind the scenes of building Task Samurai. This terminal interface for Taskwarrior was developed entirely through agentic coding by me, leveraging OpenAI Codex to do all the heavy lifting (and sometimes some cleanup afterwards). The project name might be snappy, but it was the iterative, semi-automated workflow that made the impact. + +As a side note, I was trying out OpenAI Codex because I regularly run out of Claude Code CLI (another agentic coding tool I am trying out currently) credits (it still happens!), but Codex was still available to me. So, I seized the opportunity to push agentic coding a bit more. + +I didn't really love the web UI you have to use for Codex, as I usually live in the terminal. But this is all I have for Codex for now, and I thought I'd give it a try regardless. The web UI is simple and pretty straightforward. There's also a Codex CLI one could use directly in the terminal, but I didn't get it working. I will try again soon. + +For every task given to Codex, it spins up its own container. From there, you can drill down and watch what it is doing. At the end, the result (in the form of a code diff) will be presented. From there, you can make suggestions about what else to change in the codebase. Once satisfied, you can ask Codex to create a GitHub PR; from there, you can merge it and then pull it to your local laptop or workstation to test the changes again. I found myself looping a lot around the Codex UI, GitHub PRs, and local checkouts. + +### How it went down + +Task Samurai's codebase came together quickly: the entire Git history spans from June 19 to 22, 2025, culminating in 179 commits. Here are the broad strokes: + +* June 19: Scaffolded the Go boilerplate, set up tests, integrated the Bubble Tea UI framework, and got the first table views showing up. +* June 20: (The big one—120 commits!) Added hotkeys, colourized tasks, annotation support, undo/redo, and, for fun, fireworks on quit (which never worked and got removed at a later point). This is where most of the bugs, merges, and fast-paced changes happen. +* June 21: Refined searching, theming, and column sizing and documented all those hotkeys. Numerous tweaks to make the UI cleaner and more user-friendly. +* June 22: Final touches—added screenshots, polished the logo, fixed module paths… and then it was a wrap. + +Most big breakthroughs (and bug introductions) came during that middle day of intense iteration. The latter stages were all about smoothing out the rough edges. + +It's worth noting that I worked on it in the evenings when I had some free time, as I also had to fit in my regular work and family commitments during the day. So, I didn't spend full working days on this project. + +### What went wrong + +Going agentic isn't all smooth sailing. Here are the hiccups I ran into, plus a few hard-earned lessons: + +* Merge Floods: Every minor feature or fix existed on its branch, so merging was a constant process. It kept progress flowing but also drowned the committed history in noise and the occasional conflict. I found this to be an issue with OpenAI's Codex in particular. Not so much with other agentic coding tools like Claude Code CLI (not covered in this blog post.) +* Fixes on Fixes: Features like "fireworks on exit" had chains of "fix exit," "fix cell selection," etc. Sometimes, new additions introduced bugs that needed rapid patching. + +### Patterns that helped + +Despite the chaos, a few strategies kept things moving: + +* Scaffolding First: I started with the basic table UI and command wrappers, then layered on features—never the other way around. +* Tiny PRs: Small, atomic merges meant feedback came fast (and so did fixes). +* Tests Matter: A solid base of unit tests for task manipulations kept things from breaking entirely when experimenting. +* Live Documentation: Documentation, such as the README, is updated regularly to reflect all the hotkey and feature changes. +Maybe a better approach would have been to design the whole application from scratch before letting Codix do any of the coding. I will try that with my next toy project. + +### What I learned using agentic coding + +Stepping into agentic coding with Codex as my "pair programmer" was a genuine shift. I learned a ton—not just about automating code generation, but also about how you have to tightly steer, guide, and audit every line as things move at breakneck speed. I must admit, I sometimes lost track of what all the generated code was actually doing. But as the features seemed to work after a few iterations, I was satisfied. + +Discussing requirements with Codex forced me to clarify features and spot logical pitfalls earlier. All those fast iterations meant I was constantly coaxing more helpful, less ambiguous code out of the model—making me rethink how to break features into clear, testable steps. I now see agentic coding not just as a productivity tool but also as a learning accelerator. + +### How much time did I save? + +Here's the million-dollar (or many hours saved) question: Did it buy me speed? + +Let's do some back-of-the-envelope math: + +* Say each commit takes Codex 5 minutes to generate, and you need to review/guide 179 commits = about _6 hours of active development_. +* If you coded it all yourself, including all the bug fixes, features, design, and documentation, you might spend _10–20 hours_. +* That's a couple of days potential savings. + +## Conclusion + +Building Task Samurai with agentic coding was a wild ride—rapid feature growth, plenty of churns, countless fast fixes, and more merge commits I'd expected. The big lessons? Keep the iterations short (or maybe in my next experiment, much larger, with better and more complete design before generating a single line of code), keep tests and documentation concise, and review and refine for final polish at the end. Even with the bumps along the way, shipping a polished terminal UI in days instead of weeks is a testament to the raw power (and some hazards) of agentic development. + +Am I an agentic coding expert now? I don't think so. There are still many things to learn, and the landscape is constantly evolving. + +While working on Task Samurai, there were times I genuinely missed manual coding and the satisfaction that comes from writing every line yourself, debugging issues through sheer logic, and crafting solutions from scratch. However, this is the direction in which the industry seems to be shifting, unfortunately. If applied correctly, AI will boost performance, and if you don't use AI, your next performance review may be awkward. + +If you're considering going agentic, be prepared for a sprint, keep your toolkit sharp, and be ready to learn a lot along the way. + +Personally, I am not sure whether I like where the industry is going with agentic coding. I love "traditional" coding, and with agentic coding you operate at a higher level and don't interact directly with code as often, which I would miss. I think that in the future, designing, reviewing, and being able to read and understand code will be more important than writing code by hand. + +Do you have any thoughts on that? I hope, I am partially wrong at least. + +E-Mail your comments to `paul@nospam.buetow.org` :-) + +[Back to the main site](../) diff --git a/gemfeed/2025-07-22-task-samurai.md b/gemfeed/2025-07-22-task-samurai.md deleted file mode 100644 index 21c526ce..00000000 --- a/gemfeed/2025-07-22-task-samurai.md +++ /dev/null @@ -1,124 +0,0 @@ -# Task Samurai: An agentic coding learning experiment - -> Published at 2025-06-22T18:49:11+03:00 - -[![Task Samurai Logo](./task-samurai/logo.png "Task Samurai Logo")](./task-samurai/logo.png) - -## Table of Contents - -* [⇢ Task Samurai: An agentic coding learning experiment](#task-samurai-an-agentic-coding-learning-experiment) -* [⇢ ⇢ Introduction](#introduction) -* [⇢ ⇢ ⇢ Why does this exist?](#why-does-this-exist) -* [⇢ ⇢ ⇢ How it works](#how-it-works) -* [⇢ ⇢ Where and how to get it](#where-and-how-to-get-it) -* [⇢ ⇢ Lessons Learned from Building Task Samurai with Agentic Coding](#lessons-learned-from-building-task-samurai-with-agentic-coding) -* [⇢ ⇢ ⇢ How it went down](#how-it-went-down) -* [⇢ ⇢ ⇢ What went wrong](#what-went-wrong) -* [⇢ ⇢ ⇢ Patterns that helped](#patterns-that-helped) -* [⇢ ⇢ ⇢ What I learned using agentic coding](#what-i-learned-using-agentic-coding) -* [⇢ ⇢ ⇢ How much time did I save?](#how-much-time-did-i-save) -* [⇢ ⇢ Conclusion](#conclusion) - -## Introduction - -Task Samurai is a fast terminal interface for Taskwarrior written in Go using the Bubble Tea framework. It displays your tasks in a table and allows you to manage them without leaving your keyboard. - -[https://taskwarrior.org](https://taskwarrior.org) -[https://github.com/charmbracelet/bubbletea](https://github.com/charmbracelet/bubbletea) - -### Why does this exist? - -* I wanted to tinker with agentic coding. This project was entirely implemented using OpenAI Codex. -* I wanted a faster UI for Taskwarrior than other options, like Vit, which is Python-based. -* I wanted something built with Bubble Tea, but I never had time to dive deep into it. -* I wanted to build a toy project (like Task Samurai) first, before tackling the big ones, to get started with agentic coding. - -Given the current industry trend and the rapid advancements in technology, it has become clear that experimenting with AI-assisted coding tools is almost a necessity to stay relevant. Embracing these new developments doesn't mean abandoning traditional coding; instead, it means integrating new capabilities into your workflow to stay ahead in a fast-evolving field. - -### How it works - -Task Samurai invokes the `task` command (that's the original Taskwarrior CLI command) to read and modify tasks. The tasks are displayed in a Bubble Tea table, where each row represents a task. Hotkeys trigger Taskwarrior commands such as starting, completing or annotating tasks. The UI refreshes automatically after each action, so the table is always up to date. - -[![Task Samurai Screenshot](./task-samurai/screenshot.png "Task Samurai Screenshot")](./task-samurai/screenshot.png) - -## Where and how to get it - -Go to: - -[https://codeberg.org/snonux/tasksamurai](https://codeberg.org/snonux/tasksamurai) - -And follow the `README.md`! - -## Lessons Learned from Building Task Samurai with Agentic Coding - -If you've ever wanted to supercharge your dev speed—or just throw a fireworks display in your terminal—here's a peek behind the scenes of building Task Samurai. This terminal interface for Taskwarrior was developed entirely through agentic coding by me, leveraging OpenAI Codex to do all the heavy lifting (and sometimes some cleanup afterwards). The project name might be snappy, but it was the iterative, semi-automated workflow that made the impact. - -As a side note, I was trying out OpenAI Codex because I regularly run out of Claude Code CLI (another agentic coding tool I am trying out currently) credits (it still happens!), but Codex was still available to me. So, I seized the opportunity to push agentic coding a bit more. - -I didn't really love the web UI you have to use for Codex, as I usually live in the terminal. But this is all I have for Codex for now, and I thought I'd give it a try regardless. The web UI is simple and pretty straightforward. There's also a Codex CLI one could use directly in the terminal, but I didn't get it working. I will try again soon. - -For every task given to Codex, it spins up its own container. From there, you can drill down and watch what it is doing. At the end, the result (in the form of a code diff) will be presented. From there, you can make suggestions about what else to change in the codebase. Once satisfied, you can ask Codex to create a GitHub PR; from there, you can merge it and then pull it to your local laptop or workstation to test the changes again. I found myself looping a lot around the Codex UI, GitHub PRs, and local checkouts. - -### How it went down - -Task Samurai's codebase came together quickly: the entire Git history spans from June 19 to 22, 2025, culminating in 179 commits. Here are the broad strokes: - -* June 19: Scaffolded the Go boilerplate, set up tests, integrated the Bubble Tea UI framework, and got the first table views showing up. -* June 20: (The big one—120 commits!) Added hotkeys, colourized tasks, annotation support, undo/redo, and, for fun, fireworks on quit (which never worked and got removed at a later point). This is where most of the bugs, merges, and fast-paced changes happen. -* June 21: Refined searching, theming, and column sizing and documented all those hotkeys. Numerous tweaks to make the UI cleaner and more user-friendly. -* June 22: Final touches—added screenshots, polished the logo, fixed module paths… and then it was a wrap. - -Most big breakthroughs (and bug introductions) came during that middle day of intense iteration. The latter stages were all about smoothing out the rough edges. - -It's worth noting that I worked on it in the evenings when I had some free time, as I also had to fit in my regular work and family commitments during the day. So, I didn't spend full working days on this project. - -### What went wrong - -Going agentic isn't all smooth sailing. Here are the hiccups I ran into, plus a few hard-earned lessons: - -* Merge Floods: Every minor feature or fix existed on its branch, so merging was a constant process. It kept progress flowing but also drowned the committed history in noise and the occasional conflict. I found this to be an issue with OpenAI's Codex in particular. Not so much with other agentic coding tools like Claude Code CLI (not covered in this blog post.) -* Fixes on Fixes: Features like "fireworks on exit" had chains of "fix exit," "fix cell selection," etc. Sometimes, new additions introduced bugs that needed rapid patching. - -### Patterns that helped - -Despite the chaos, a few strategies kept things moving: - -* Scaffolding First: I started with the basic table UI and command wrappers, then layered on features—never the other way around. -* Tiny PRs: Small, atomic merges meant feedback came fast (and so did fixes). -* Tests Matter: A solid base of unit tests for task manipulations kept things from breaking entirely when experimenting. -* Live Documentation: Documentation, such as the README, is updated regularly to reflect all the hotkey and feature changes. -Maybe a better approach would have been to design the whole application from scratch before letting Codix do any of the coding. I will try that with my next toy project. - -### What I learned using agentic coding - -Stepping into agentic coding with Codex as my "pair programmer" was a genuine shift. I learned a ton—not just about automating code generation, but also about how you have to tightly steer, guide, and audit every line as things move at breakneck speed. I must admit, I sometimes lost track of what all the generated code was actually doing. But as the features seemed to work after a few iterations, I was satisfied. - -Discussing requirements with Codex forced me to clarify features and spot logical pitfalls earlier. All those fast iterations meant I was constantly coaxing more helpful, less ambiguous code out of the model—making me rethink how to break features into clear, testable steps. I now see agentic coding not just as a productivity tool but also as a learning accelerator. - -### How much time did I save? - -Here's the million-dollar (or many hours saved) question: Did it buy me speed? - -Let's do some back-of-the-envelope math: - -* Say each commit takes Codex 5 minutes to generate, and you need to review/guide 179 commits = about _6 hours of active development_. -* If you coded it all yourself, including all the bug fixes, features, design, and documentation, you might spend _10–20 hours_. -* That's a couple of days potential savings. - -## Conclusion - -Building Task Samurai with agentic coding was a wild ride—rapid feature growth, plenty of churns, countless fast fixes, and more merge commits I'd expected. The big lessons? Keep the iterations short (or maybe in my next experiment, much larger, with better and more complete design before generating a single line of code), keep tests and documentation concise, and review and refine for final polish at the end. Even with the bumps along the way, shipping a polished terminal UI in days instead of weeks is a testament to the raw power (and some hazards) of agentic development. - -Am I an agentic coding expert now? I don't think so. There are still many things to learn, and the landscape is constantly evolving. - -While working on Task Samurai, there were times I genuinely missed manual coding and the satisfaction that comes from writing every line yourself, debugging issues through sheer logic, and crafting solutions from scratch. However, this is the direction in which the industry seems to be shifting, unfortunately. If applied correctly, AI will boost performance, and if you don't use AI, your next performance review may be awkward. - -If you're considering going agentic, be prepared for a sprint, keep your toolkit sharp, and be ready to learn a lot along the way. - -Personally, I am not sure whether I like where the industry is going with agentic coding. I love "traditional" coding, and with agentic coding you operate at a higher level and don't interact directly with code as often, which I would miss. I think that in the future, designing, reviewing, and being able to read and understand code will be more important than writing code by hand. - -Do you have any thoughts on that? I hope, I am partially wrong at least. - -E-Mail your comments to `paul@nospam.buetow.org` :-) - -[Back to the main site](../) diff --git a/gemfeed/index.md b/gemfeed/index.md index c956350a..d8b338a2 100644 --- a/gemfeed/index.md +++ b/gemfeed/index.md @@ -2,7 +2,7 @@ ## To be in the .zone! -[2025-07-22 - Task Samurai: An agentic coding learning experiment](./2025-07-22-task-samurai.md) +[2025-06-22 - Task Samurai: An agentic coding learning experiment](./2025-06-22-task-samurai.md) [2025-06-07 - 'A Monk's Guide to Happiness' book notes](./2025-06-07-a-monks-guide-to-happiness-book-notes.md) [2025-05-11 - f3s: Kubernetes with FreeBSD - Part 5: WireGuard mesh network](./2025-05-11-f3s-kubernetes-with-freebsd-part-5.md) [2025-05-02 - Terminal multiplexing with `tmux` - Fish edition](./2025-05-02-terminal-multiplexing-with-tmux-fish-edition.md) diff --git a/index.md b/index.md index 8a6bb86e..236e3e9c 100644 --- a/index.md +++ b/index.md @@ -1,6 +1,6 @@ # Hello! -> This site was generated at 2025-06-22T19:53:43+03:00 by `Gemtexter` +> This site was generated at 2025-06-22T20:03:04+03:00 by `Gemtexter` Welcome to the ... @@ -38,7 +38,7 @@ Everything you read on this site is my personal opinion and experience. You can ### Posts -[2025-07-22 - Task Samurai: An agentic coding learning experiment](./gemfeed/2025-07-22-task-samurai.md) +[2025-06-22 - Task Samurai: An agentic coding learning experiment](./gemfeed/2025-06-22-task-samurai.md) [2025-06-07 - 'A Monk's Guide to Happiness' book notes](./gemfeed/2025-06-07-a-monks-guide-to-happiness-book-notes.md) [2025-05-11 - f3s: Kubernetes with FreeBSD - Part 5: WireGuard mesh network](./gemfeed/2025-05-11-f3s-kubernetes-with-freebsd-part-5.md) [2025-05-02 - Terminal multiplexing with `tmux` - Fish edition](./gemfeed/2025-05-02-terminal-multiplexing-with-tmux-fish-edition.md) diff --git a/uptime-stats.md b/uptime-stats.md index cd228942..11562240 100644 --- a/uptime-stats.md +++ b/uptime-stats.md @@ -1,6 +1,6 @@ # My machine uptime stats -> This site was last updated at 2025-06-22T19:53:43+03:00 +> This site was last updated at 2025-06-22T20:03:04+03:00 The following stats were collected via `uptimed` on all of my personal computers over many years and the output was generated by `guprecords`, the global uptime records stats analyser of mine. -- cgit v1.2.3