As an aside, check out Jason's podcast (codewithjason.com) - its pretty good.
The latest one is with "Uncle Bob Martin" who has some interesting takes on coding with AI from .... can I say an oldie?
My Agent Skill for Test-Driven Development
41–50 of 120 posts
Re: My Agent Skill for Test-Driven Development
#42TDD sounds great on paper for agentic development but you quickly realize it balloons the token cost. Often I write some feature and then its repurposed or removed, code is refactored moved around as time goes. With TDD I would be taxed heavily and velocity slow to a crawl. The waterfall approach is better after trying out TDD especially when you have a multi-agent setup. Also I found that in some cases the tests wer…
I was a big proponent of encoding TDD red-green-refactor methodology into my agent workflows until recently when I made the same realization after reading this study: https://arxiv.org/pdf/2602.07900
TLDR; it found test-writing volume only weakly correlates with success and that encoding test-writing principles did not move resolution rates but _did_ materially change cost. Encouraging tests cost +19.8% output tokens for 0% gain; discouraging them saved 33–49% input tokens for ≤2.6pp accuracy loss. Separately, imposing the TDD procedure specifically seems like it can backfire: it actually _increased_ regressions from 6.08% to 9.94%.
IMO, where tests clearly help is primarily as an "oracle" applied after generation. It gives the models a signal that enables them to verify and self-correct if necessary.
Re: My Agent Skill for Test-Driven Development
#43If you don't follow up with a pass of injecting bugs and validating that the tests fail in the presence of bugs... then you've only confirmed that the tests can pass and they may be substantially useless.
Re: My Agent Skill for Test-Driven Development
#44This article would benefit from a date. It looks like it's recent (Internet Archive first grabbed it on May 29th) but it's the kind of information that can quickly become stale as models and agents improve. (I've been getting solid results recently from simply telling Claude Code and Codex "Test with uv run pytest, use red/green TDD".)
fwiw, response headers include: Last-Modified: Fri, 22 May 2026 19:08:09 GMT
Re: My Agent Skill for Test-Driven Development
#45[dead]
Re: My Agent Skill for Test-Driven Development
#46TDD sounds great on paper for agentic development but you quickly realize it balloons the token cost. Often I write some feature and then its repurposed or removed, code is refactored moved around as time goes. With TDD I would be taxed heavily and velocity slow to a crawl. The waterfall approach is better after trying out TDD especially when you have a multi-agent setup. Also I found that in some cases the tests wer…
> With TDD I would be taxed heavily and velocity slow to a crawl. And the code will be good.
not necessarily, TDD has little bearing on output quality
Re: My Agent Skill for Test-Driven Development
#47This article would benefit from a date. It looks like it's recent (Internet Archive first grabbed it on May 29th) but it's the kind of information that can quickly become stale as models and agents improve. (I've been getting solid results recently from simply telling Claude Code and Codex "Test with uv run pytest, use red/green TDD".)
Here's a portion of my AGENTS.md from this week (playing FDE, implementing a custom workflow for a client that 20x their productivity). # Python Tooling - Use `uv` to manage Python environments and dependencies. - Use `uv run` to execute Python scripts and commands. - Use `pytest` for testing your code. - Use the `hypothesis` library for property-based testing when you have complex input spaces or need to test edge c…
[dead]
Re: My Agent Skill for Test-Driven Development
#48This article would benefit from a date. It looks like it's recent (Internet Archive first grabbed it on May 29th) but it's the kind of information that can quickly become stale as models and agents improve. (I've been getting solid results recently from simply telling Claude Code and Codex "Test with uv run pytest, use red/green TDD".)
Every article should include a date!
Re: My Agent Skill for Test-Driven Development
#49One issue that I've run into with codex has been excessive use of fallbacks routines. Perhaps this is good practice in.professional programming in many situations, but for mine (in this case): computing geodesic distances and analysis, a silent bad fallback means the processed data is not what I thought it was..e.g. used an inaccurate geodesic method in place of the accurate one.
Re: My Agent Skill for Test-Driven Development
#50This article would benefit from a date. It looks like it's recent (Internet Archive first grabbed it on May 29th) but it's the kind of information that can quickly become stale as models and agents improve. (I've been getting solid results recently from simply telling Claude Code and Codex "Test with uv run pytest, use red/green TDD".)
Good point! Will add a date.