Show HN: Specification First Agentic Development Plugin and Prove
spec-first.devImplemented agent smith since start 2026 with over 1000 specifications which lead to about 500k lines of code. The procedure with that spec-first works well. How do you do it?
Always reminds me of this meme.
Some day we won't even need coders any more. We'll be able to just write the specification and the program will write itself.
Oh wow, you're right! We'll be able to write a comprehensive and precise spec and bam, we won't need programmers any more!
Exactly!
And do you know the industry term for a project specification that is comprehensive and precise enough to generate a program?
Code It's called code.
Two things about that. On the one hand, I couldn't believe coding would be replaced when I started Agent Smith in January 2026. On the other hand, I wanted proof.
After 500k lines of code in Agent Smith, none of which I wrote by hand, I have to admit it: coding is more or less solved. That doesn't mean architects, developers, DevOps people and everyone else aren't needed anymore. I think they're needed more than ever.
Just implementing something isn't good enough. The spec has to point to sensible approaches and procedures, and the code has to be well structured (in my view, at least). Then the specs can simply run in parallel all night.
So my actual work on Agent Smith isn't coding at all. It's deciding what the right thing to build is, and how, in terms of design and architecture. I don't even review the code. But I do test it: 10k tests, a harness, a commit hook that blocks a spec while the suite is red, the whole story.
And unfortunately, that works pretty well. I also think last year's programming was more romantic :-D
> And unfortunately, that works pretty well.
Why unfortunately?
Because I loved writing code myself, and that feels kind of outdated now. Who's going to pay me to code "slowly" when AI does it a lot faster?
But people do unpaid painting, horseback riding, calligraphy, etc. which are outdated because they love it. Why is it so unfortunate for you?
Don't take it too seriously. But anyway:
I work as a freelancer and started programming at 12. I've been doing it for 40 years now.
I guess I'm ambivalent. On one hand these are crazy times, really stunning. Everything is changing, and AI takes over a lot of stuff I never wanted to do, but also parts of what I loved doing.
This year the time I spend actually programming dropped to 5–10%. Last year it was still 80%. That's a big change for a professional life. It means developers and architects spend their time on design and on proving the code works, not on writing it.
Agent Smith and all the other stuff is one of my side projects. So I'm just being a little nostalgic here, I guess. Nothing too serious ;-)
Very confidently wrong.
Do you know why it's easier to specify theorems than it is their proofs? Or why ACSL != C?
You can go ahead and make a more specific argument, e.g. that mainstream UX-centric software development may not be amenable to current paradigms of formal verification, but to insinuate that a complete spec reduces to source code itself is naive.
EDIT: Possibly I have responded too acutely to the points you care less about. I agree that "in the future we won't need programmers" is questionable since good spec-writing and spec-vetting requires at least as much expertise, if not more, than ordinary coding work, and that is fair to call comprehensive spec work "code" in that it is technical and formal. But it is decisively not source code.
A couple of decades ago coding was "solved" by just writing UML diagrams. The nonsense never ends.
I think both can be true: as coding languages go from lower to higher level, they go from being more implementation-like (e.g. assembly, C) to being more spec-like (e.g. Rust, Haskell). It then follows that writing a good spec could be considered coding if your compiler (or agent) can reliably turn that spec into your desired output.
So the main challenge I see with this approach is getting the spec right. Too little detail and the output is uncontrolled, too much detail and you're adding too many constraints (and you may be better off just writing code). From my experience, agents haven't been the best at writing good specs. But maybe this project can help with that?
If your specs are not executable or are editable by the agent, they are as non-deterministic as any code that comes out of them.
the agent creates and maintains the specs, doing this manually doesn't make sense. The specs are written for the agents. after execution of create-spec, review-spec skill will check against the code and add evidence of the spec's aims. Only when the aims fits to the evidence, the specs is going to be validated successful. after that apply and deliver skills can be executed. finally there is commit hooks and tests that shall ensure quality and functionality. have a look at https://github.com/holgerleichsenring/agent-smith for the quality gates.
I have not seen spec first development work well in real world environments at all. The problem is that you typically don't know what you don't know upfront for most product based decisions. Going back and forth in the spec to fix problems is a huge mistake, it just leads to contradictory sets of requirements for the agent.
What does work well is using AI to generate a quick and dirty prototype ala vibecoding, and then using that as a basis to regenerate the final code. Some might say it's still spec driven development, but the spec is a working prototype.
they do work well in production. have a look at https://github.com/holgerleichsenring/agent-smith. While writing that the methodology had been created. Obviously, I didnt know upfront what I wanted to generate here. Also features are changed or removed on the way. that's not a problem, when the specifications are part of the git repository as it is done here. Actually it's the other way around: it is an advantage as the agent can have a look at everything that had been done previously and can understand what, why and how it had been implemented. give it a try :-)
Your silly software factory is not proof that SDD works well in production. It is proof that it can produce software, and that’s a very low bar.
We’ve been using SDD at $workplace for more than a year and we’ve started to actively remove all spec documents so agents don’t get stuck reviewing out of date context for 20 minutes, burn through token budgets, and give disproportionate focus to legacy patterns and business directions we’ve pivoted from.
Models are RLHF’d to work on non-historical documentation and iterative design, and that’s what yields the best overall results.
Specs-as-history is rapidly becoming an antipattern as teams actually try to scale SDD. We're already putting guardrails in agents.md (non-normative in all caps), some teams are actually offboarding them - to Rally (which I find the height of hilarity).
Spec docs - at least in all the other things like this thing - aren't a living representation of truth, instead they are a collection of snapshots in time of feature deliverables. Layer 500 of these on top of each other and they quickly become not just useless but actively harmful. Archive them, compile them, whatever your plugin does, it still doesn't help. Nobody is going to pay for tokens just to keep the specs time-coherent, when the agent can just read the code.
Don't get me wrong, a spec is a useful bit of kit for development, just like Jira and Rally, but also like Jira and Rally they aren't the source of truth because there's already a better one which you just paid for.
What is the difference between having the agent create a spec and having the agent create a plan?
How does this differ to Spec Kit / BMAD / etc?
its crazy how capable the agents are becoming so quickly