Haven’t we moved on from these things? Most recent LLMs have been trained on enough long context tasks to have become pretty good at planning. Perhaps with contributions from the harness. In either case, I wouldn’t bother if I were using Codex or Claude Code.
scosman 1 hours ago [-]
They can plan, but no guarantee it will produce what you want. Sometimes most of the work is aligning on what to build. And I'm not handing over technical planning to it yet.
I use this skill and it makes the specing process progressive. Human driven for the "what", 50/50 for higher level technical planning, only where it has questions in the low level details: https://github.com/scosman/vibe-crafting
Wazzymandias 32 minutes ago [-]
> been trained on enough long context tasks to have become pretty good at planning
This is absolutely not true
alexjplant 33 minutes ago [-]
I bother because Claude Code does wacky nonsense unless I use OpenSpec (or something similar) to explicitly research, scope, persist, then implement in a brand-new context. Even Opus will do ridiculous nonsense like throw its hands up when asked to start a Docker container, ignore explicit architectural instructions, write verbose make-work documentation riddled with inaccuracies, etc. Using OpenSpec keeps things as constrained as possible with the side effect of recording what your system does.
OpenCode and various open models do not exhibit this tendency nearly as much in my experience. My recent experiences with GPT-5.6 were also very positive in this regard. Alas for regulatory reasons this stack is a non-starter at $DAYJOB so I'm stuck working around Anthropic's capacity optimizing shenanigans.
6 minutes ago [-]
virgil_disgr4ce 56 minutes ago [-]
specifying is not planning
nullbio 25 minutes ago [-]
I just have it write a checklist file in /tmp (or a todo folder if I want to keep it), and check off items as it finishes them. Seems to work fine. Is this really needed?
trollbridge 22 minutes ago [-]
/tmp? What happens when you reboot?
recroad 29 minutes ago [-]
I use this to produce the task list which I then feed into a Ralph loop using a bash script. I save a lot of tokens since each tasks context is so small.
wyum 3 hours ago [-]
This is my first time seeing openspec, and it seems to share a similar philosophy to what I've been working on this year.
If you like this / SDD, I'd appreciate your feedback:
Similar iterative specs philosophy. Ours is a bit different because we focus on declarative specs and installable agent skills. We chose Go for simplicity and minimal requirements (single binary).
passive 2 hours ago [-]
I've also been building something like this, and browsing spekk-cli, it's interesting to see that we ended up with similar roles. Might be fun to compare and contrast a couple of these systems. :)
I think they might be in the process of re-designing the site and/or moving docs because it all used to work not that long ago, but the site design was completely different last time I checked.
jmathai 2 hours ago [-]
I have a super simple spec-based workflow. It works amazingly well. I’m amazed how well coding agents can work through what I consider large features.
Last week, I gave a 471 line spec to implement a major feature and it didn’t flinch. I wrote about it here.
I am sorry but 471 lines is nothing in 2026. Come back when it has executed a 5000-10,000 line spec flawlessly, although the threshold keeps getting higher as the models get better. You're right though about a simple spec based workflow going far.
jeremyjh 3 hours ago [-]
This looks like exactly what I've been thinking I needed. I've tried Superpowers, GSD and oh-my-claude/openagent and mostly they burn more tokens.
Lately I've been using stock OMP and its close to the right balance but not quite enough of the brainstorming and spec maintenance built in. I've tried to layer some simple stuff on myself but with mixed results.
grohan 32 minutes ago [-]
how are people currently evaluating between the different spec writing frameworks out there?
evaltoken 57 minutes ago [-]
Spec-driven workflows really seem to be where agent tooling is heading
8cvor6j844qw_d6 2 hours ago [-]
What are people using for this nowadays?
There seems to be a spectrum from fluid, iterative workflows like OpenSpec to more up-front alignment and control like Matt Pocock skills.
Curious what people have settled on.
kaurimu 7 minutes ago [-]
I settled on lat.md [1] at the beginning of this year and never looked back.
Its design offers a compellingly simple surface for weaving natural-language intent into the codebase itself, without overcomplicating things:
---
Key Ideas
* Plain markdown: readable by humans, parseable by agents
* Wiki links connect concepts into a navigable graph
* // @lat: and # @lat: comments tie source code to specs
* lat check ensures nothing drifts out of sync
* lat search for semantic vector search across all sections
---
For me it strikes the right balance between structure and flexibility. It gives agents enough context-efficient grounding to reduce functional and architectural drift [2], while remaining malleable enough to evolve with new requirements.
Admittedly I haven't run any evals, and I'm sure there are even better systems out there... but if I still had the problem I was trying to solve when I found it, I wouldn't be talking about it right now.
Of course it's likely that my problem has only migrated to a higher order of complexity, but surfacing it again through building increasingly complex things is an interesting enough challenge in itself.
[2] 100% auto-eliminating drift is an unrealistic goal -- that's where you come in.
chrismarlow9 1 hours ago [-]
Symlink the global MD files to a single file I control that is versioned. Define my own general spec and workflow terminology using markdown files in this universal MD.
```
~/.config/opencode/AGENTS.md
~/.claude/CLAUDE.md
~/.codex/AGENTS.md
~/.copilot/copilot-instructions.md
~/.gemini/GEMINI.md
```
Define it as a graph and iterate. I use more tokens, but I can also use more tools without disruption. Delegating markdown to folders/smaller repos can solve the tokens/context issue.
Mugshelf 2 hours ago [-]
Tired of wrestling JIRA for AI project specs. If this actually streamlines things, I'm definitely giving it a look.
slowmovintarget 3 hours ago [-]
I've been using this, or more pointedly, I built an agent fleet (bespoke harness) where the planner agent uses OpenSpec to generate the plan. Then turns the tasks into a ticket graph.
It works fairly well, and it is definitely less heavy than SpecKit.
wyre 2 hours ago [-]
It's just a bundle of skills and md files...
Why does it need to have an entire CLI?
iamjfu 2 hours ago [-]
The CLI is actually useful. It gives the skills a way to deterministically interact with the spec. For example, it can validate the shape without having to spend tokens reading the files.
wyre 37 minutes ago [-]
Compared to including shell scripts with the skills?
Not trying to say that it's not useful, but it seems excessive and potentially bloated.
etoxin 27 minutes ago [-]
I use the cli tool outside of the agent session. e.g. `openspec view` to see all the specs and what's pending.
honkycat 2 hours ago [-]
LOVE. LOVE. LOVE. Openspec.
Easily my favorite spec driven development framework.
It scored really well in our internal evals as well.
I think it has the most sane ceremony and its model fits my mental model really well.
I've also been working on a TUI that will automatically generate "phases" with each one being a openspec spec.
I would highly recommend trying out SpecDriven development. I found it to be the most productive way to work with LLMs for larger tasks, and I have found that it improves performance on larger tasks.
To me, this is where LLMs should go. Collaborating on shared documents that serve as a contract that then gets evaluated post-implementation
I've made multiple attempts to write domain-specific languages for LLMs to use to guide software architecture so that I can have higher-quality software architecture and also so that it can communicate ideas to me in a more terse way.
One thing that I think LLMs are lacking right now is information density. I'm a guitarist, and I like this game called Rocksmith, but I think that its user interface kind of sucks. It's fun to play along with the songs, and it's fun that it scores me on the songs and gamifies playing guitar. For dense notes, the user interface just isn't very good.
That kind of made me think more about information density. A sheet of notes is very dense, but it takes a little more time to process. Guitar tablature is slightly less dense, but I think it strikes a better balance between treble clef and Rocksmith. Really, I'd rather have all three of those presented to me.
This is really where I'd like to go with how I'm writing software now. LLMs: I'd love to be able to just create a specification that is very dense and describes domain-driven design concepts to the LLM, and then have a workflow that will do adversarial review to evaluate those concepts after implementing a phase.
This also kind of solves part of the problem with design decisions and artifact storage and all those things that we kind of see LLMs scatter around a codebase. If it exists in the spec, then it can be referenced later, and you can document changes, etc. Also, if you do the spec right, it could be language-agnostic.
I use this skill and it makes the specing process progressive. Human driven for the "what", 50/50 for higher level technical planning, only where it has questions in the low level details: https://github.com/scosman/vibe-crafting
This is absolutely not true
OpenCode and various open models do not exhibit this tendency nearly as much in my experience. My recent experiences with GPT-5.6 were also very positive in this regard. Alas for regulatory reasons this stack is a non-starter at $DAYJOB so I'm stuck working around Anthropic's capacity optimizing shenanigans.
If you like this / SDD, I'd appreciate your feedback:
https://github.com/spekk-ai/spekk-cli
Similar iterative specs philosophy. Ours is a bit different because we focus on declarative specs and installable agent skills. We chose Go for simplicity and minimal requirements (single binary).
Concepts links here: https://github.com/Fission-AI/OpenSpec/blob/main/docs-lab/gu...
All the docs here are the templates rather than the actual file (I presume: https://github.com/Fission-AI/OpenSpec/blob/main/docs/concep...)
Somehow not very confidence inspiring...
Last week, I gave a 471 line spec to implement a major feature and it didn’t flinch. I wrote about it here.
https://jaisenmathai.com/articles/sojourn-for-ios-was-45-one...
Lately I've been using stock OMP and its close to the right balance but not quite enough of the brainstorming and spec maintenance built in. I've tried to layer some simple stuff on myself but with mixed results.
There seems to be a spectrum from fluid, iterative workflows like OpenSpec to more up-front alignment and control like Matt Pocock skills.
Curious what people have settled on.
Its design offers a compellingly simple surface for weaving natural-language intent into the codebase itself, without overcomplicating things:
---
Key Ideas
* Plain markdown: readable by humans, parseable by agents
* Wiki links connect concepts into a navigable graph
* // @lat: and # @lat: comments tie source code to specs
* lat check ensures nothing drifts out of sync
* lat search for semantic vector search across all sections
---
For me it strikes the right balance between structure and flexibility. It gives agents enough context-efficient grounding to reduce functional and architectural drift [2], while remaining malleable enough to evolve with new requirements.
Admittedly I haven't run any evals, and I'm sure there are even better systems out there... but if I still had the problem I was trying to solve when I found it, I wouldn't be talking about it right now.
Of course it's likely that my problem has only migrated to a higher order of complexity, but surfacing it again through building increasingly complex things is an interesting enough challenge in itself.
[1] https://github.com/vercel-labs/lat.md
[2] 100% auto-eliminating drift is an unrealistic goal -- that's where you come in.
```
~/.config/opencode/AGENTS.md
~/.claude/CLAUDE.md
~/.codex/AGENTS.md
~/.copilot/copilot-instructions.md
~/.gemini/GEMINI.md
```
Define it as a graph and iterate. I use more tokens, but I can also use more tools without disruption. Delegating markdown to folders/smaller repos can solve the tokens/context issue.
It works fairly well, and it is definitely less heavy than SpecKit.
Why does it need to have an entire CLI?
Not trying to say that it's not useful, but it seems excessive and potentially bloated.
Easily my favorite spec driven development framework.
It scored really well in our internal evals as well.
I think it has the most sane ceremony and its model fits my mental model really well.
I've also been working on a TUI that will automatically generate "phases" with each one being a openspec spec.
I would highly recommend trying out SpecDriven development. I found it to be the most productive way to work with LLMs for larger tasks, and I have found that it improves performance on larger tasks.
To me, this is where LLMs should go. Collaborating on shared documents that serve as a contract that then gets evaluated post-implementation
I've made multiple attempts to write domain-specific languages for LLMs to use to guide software architecture so that I can have higher-quality software architecture and also so that it can communicate ideas to me in a more terse way.
One thing that I think LLMs are lacking right now is information density. I'm a guitarist, and I like this game called Rocksmith, but I think that its user interface kind of sucks. It's fun to play along with the songs, and it's fun that it scores me on the songs and gamifies playing guitar. For dense notes, the user interface just isn't very good.
That kind of made me think more about information density. A sheet of notes is very dense, but it takes a little more time to process. Guitar tablature is slightly less dense, but I think it strikes a better balance between treble clef and Rocksmith. Really, I'd rather have all three of those presented to me.
This is really where I'd like to go with how I'm writing software now. LLMs: I'd love to be able to just create a specification that is very dense and describes domain-driven design concepts to the LLM, and then have a workflow that will do adversarial review to evaluate those concepts after implementing a phase.
This also kind of solves part of the problem with design decisions and artifact storage and all those things that we kind of see LLMs scatter around a codebase. If it exists in the spec, then it can be referenced later, and you can document changes, etc. Also, if you do the spec right, it could be language-agnostic.