This looks nice! I tried to tackle the same problem with https://usecontinuo.dev (writing my own translation layer) - but Skillsync looks much more powerful.
This is really cool, especially in a world where you're using Claude as a workhorse, but want to be able to bring the entire session context into Codex so you can draft communications with full context but without Claude-isms. (You can train Claude to spawn e.g. a Codex session, but Codex wouldn't know what to ask for from the broader context, beyond the prompt Claude gives it.)
And shipping sessions to colleagues is critical as well. My team relies heavily on a homegrown /resume-from-transcript skill that forces the harness to read every part of a Claude Code JSONL into context, letting us jump into colleagues' sessions.
What I thought this might be from the title, though, is a separate but related problem. The more semi-technical people in a company who start to use agentic systems, the more likely they are to create a vital playbook as a "skill" - but one not designed for easy tracking in a repository, that relies on local state, references their name repeatedly, references other skills and rules that they've developed for their own work, etc. Cleaning these, figuring out what should be promoted across a team, figuring out when someone makes an update whether that's something that deserves human review, syncing across people who haven't used git/pull requests before - it's a big challenge that's highly context-dependent. If skills are the place where guardrails exist, "who watches the watchmen?"
There's an interesting duality here, because a colleague being able to ship a session where they iterated on such a skill, to a colleague who can understand the context of their change, is incredibly valuable. But it still relies on a human in the loop, and doesn't scale as a result. I think there's a really interesting design space here.
Cool! Over here we mean portability in a different sense: being able to continue a session in another agent as if the entire conversation history was there the whole time. You should not get locked into one agent simply because you built up a conversation history + memory with that agent
Also curious, do you further process the synced files on dropbox at all? how are you using them today?
Since I only support Pi natively, your solution will make it possible for codex/claude/etc. users to discover their conversations in my app. Will definitely include this as workaround for making codex, claude and other sessions available for discovery.
The only thing that seems to be missing is synching but I have a workaround for that but it won't be near realtime. For example, Pi changes are usually a second or less behind the Pi session log.
With txcript, it will probably be 5 seconds which is fine since the use case will mostly revolve around discovery, organizing and inspection.
I was thinking about doing this. If we treat ChatGPT like your local llm server, you basically open up a browser session, intercept all traffic and stick a local OpenAI compatible rest server that mutilates your input upstream through the ChatGPT ui, and then intercepts downstream and pushes it out your server.
API call to server
Then
Server leverages chrome plugin to send your llm call through the plugin , through the ui, wait for response , intercept, repackage and reroute it back out as a server response.
Then that $20 sub stretches to all uses cases for a developer.
That's a clever idea, and a different direction from where we are right now. Today it only goes one way, from chat into your coding agent.
The case I hit all the time is that an idea strikes on my commute, so I pull out my phone and start brainstorming in the Claude app. By the time I'm home I've done the research and chased down the tangents in that conversation. I open my laptop, use Skillsync to continue it in Claude Code, and start on the implementation.
How would they know? Only if you use a coding harness, but one could write their own harness with less obvious system prompts.
I’m not encouraging one do this. I mostly route between the free models on OpenRouter and OpenCode free models, and I mostly write simple apps where I can casually oversee even a small model and get awesome results.
But if you are out there spending 200 dollars a month, consider a few hacks, because that’s just overpriced. We are developers after all, they aren’t supposed to be able to trick us :)
Edit:
Piracy, with the above , would look like a universal server that routes between all provider UIs. That means the end user doesn’t even give a shit which provider it goes to, serious token usage, serious theft.
Someone could make this , I suppose. In a way, commodification is a clean solution to the inevitable theft. It’s better it just be so darn cheap and ubiquitous.
This is good, I like it!! I've been mostly working with Claude and Chatgpt for separate stuff, however sometimes one of them is stuck and I could definitely use this to start a session with the other one and see if it figures it out.
Have you tested to see if there was any degradation happening when switching from one model to the other ? I mean some must be inevitable (maybe not!), but how much?
Nars here, one of the co-founders. With longer sessions, the receiving agent sometimes decides to compact it. But the whole transcript still exists and is accessible
If I were you I would look into maybe like analyzing sessions across harnesses? I’m not sure, some way to leverage this shared schema work that is not syncing
Because syncing is trivially solved by just telling the agent to keep a work journal in markdown
We do that, and it's really the point of the portability work. Once every harness's sessions live in one schema, you can manage and search all of them in one place.
The markdown journal is a fair way to do it, and a popular one. It has a couple of limits though.
A journal comes out of a prompt, so it records one way of looking at the session. Whatever that prompt didn't ask about is gone, and you usually find out which detail you needed much later. But the raw session still has it.
Being able to unify the schema lets you do things notes can't. You can continue a teammate's session on your own machine, or pick up a claude.ai conversation in Claude Code or Codex. The new agent gets the transcript: all the decisions in the trajectory, not a summary of it.
To say what the author said in another way- thats a garbage approach and completely misses the point. Sure, you can completely destroy the session by distilling it into a markdown- but thats like explaining what you did yesterday, vs having an immutable log of what you did yesterday.
Any word on when you'll add support for antigravity? I often switch between harnesses and models and subscriptions, both for work and personal stuff, this is an awesome idea. One thing I do that I don't think you have support for is running sessions on different machines. Do you have support for, or do you plan on adding support for, syncing across machines?
This looks nice! I tried to tackle the same problem with https://usecontinuo.dev (writing my own translation layer) - but Skillsync looks much more powerful.
This is really cool, especially in a world where you're using Claude as a workhorse, but want to be able to bring the entire session context into Codex so you can draft communications with full context but without Claude-isms. (You can train Claude to spawn e.g. a Codex session, but Codex wouldn't know what to ask for from the broader context, beyond the prompt Claude gives it.)
And shipping sessions to colleagues is critical as well. My team relies heavily on a homegrown /resume-from-transcript skill that forces the harness to read every part of a Claude Code JSONL into context, letting us jump into colleagues' sessions.
What I thought this might be from the title, though, is a separate but related problem. The more semi-technical people in a company who start to use agentic systems, the more likely they are to create a vital playbook as a "skill" - but one not designed for easy tracking in a repository, that relies on local state, references their name repeatedly, references other skills and rules that they've developed for their own work, etc. Cleaning these, figuring out what should be promoted across a team, figuring out when someone makes an update whether that's something that deserves human review, syncing across people who haven't used git/pull requests before - it's a big challenge that's highly context-dependent. If skills are the place where guardrails exist, "who watches the watchmen?"
There's an interesting duality here, because a colleague being able to ship a session where they iterated on such a skill, to a colleague who can understand the context of their change, is incredibly valuable. But it still relies on a human in the loop, and doesn't scale as a result. I think there's a really interesting design space here.
I have made simple macos app to export my claude sessions to markdown(plus ordinal jsonl) and i just continuously sync it to dropbox.
i do the same for apple notes and imessage. so very portable
https://apps.apple.com/us/app/exporter-notes-to-markdown/id6...
Cool! Over here we mean portability in a different sense: being able to continue a session in another agent as if the entire conversation history was there the whole time. You should not get locked into one agent simply because you built up a conversation history + memory with that agent
Also curious, do you further process the synced files on dropbox at all? how are you using them today?
This is awesome! You solve an immediate need of mine for:
https://github.com/gitsense/chat/tree/readme-scale-knowledge
Since I only support Pi natively, your solution will make it possible for codex/claude/etc. users to discover their conversations in my app. Will definitely include this as workaround for making codex, claude and other sessions available for discovery.
we publish a npm package of our core library too: https://github.com/skillsynchq/txcript
you can use that internally for this
Unfortunately I won't be able to use the npm as I need it for synching which is managed by https://github.com/gitsense/gsc-cli/tree/staging
The only thing that seems to be missing is synching but I have a workaround for that but it won't be near realtime. For example, Pi changes are usually a second or less behind the Pi session log.
With txcript, it will probably be 5 seconds which is fine since the use case will mostly revolve around discovery, organizing and inspection.
I was thinking about doing this. If we treat ChatGPT like your local llm server, you basically open up a browser session, intercept all traffic and stick a local OpenAI compatible rest server that mutilates your input upstream through the ChatGPT ui, and then intercepts downstream and pushes it out your server.
API call to server
Then
Server leverages chrome plugin to send your llm call through the plugin , through the ui, wait for response , intercept, repackage and reroute it back out as a server response.
Then that $20 sub stretches to all uses cases for a developer.
That's a clever idea, and a different direction from where we are right now. Today it only goes one way, from chat into your coding agent.
The case I hit all the time is that an idea strikes on my commute, so I pull out my phone and start brainstorming in the Claude app. By the time I'm home I've done the research and chased down the tangents in that conversation. I open my laptop, use Skillsync to continue it in Claude Code, and start on the implementation.
Good way to be banned
How would they know? Only if you use a coding harness, but one could write their own harness with less obvious system prompts.
I’m not encouraging one do this. I mostly route between the free models on OpenRouter and OpenCode free models, and I mostly write simple apps where I can casually oversee even a small model and get awesome results.
But if you are out there spending 200 dollars a month, consider a few hacks, because that’s just overpriced. We are developers after all, they aren’t supposed to be able to trick us :)
Edit:
Piracy, with the above , would look like a universal server that routes between all provider UIs. That means the end user doesn’t even give a shit which provider it goes to, serious token usage, serious theft.
Someone could make this , I suppose. In a way, commodification is a clean solution to the inevitable theft. It’s better it just be so darn cheap and ubiquitous.
isn't that what they did to opencode? when they were using the subs by reverse engineering their APIs
This is good, I like it!! I've been mostly working with Claude and Chatgpt for separate stuff, however sometimes one of them is stuck and I could definitely use this to start a session with the other one and see if it figures it out.
Have you tested to see if there was any degradation happening when switching from one model to the other ? I mean some must be inevitable (maybe not!), but how much?
Nars here, one of the co-founders. With longer sessions, the receiving agent sometimes decides to compact it. But the whole transcript still exists and is accessible
In some cases, harnesses try to obfuscate reasoning, but almost everything goes through.
If I were you I would look into maybe like analyzing sessions across harnesses? I’m not sure, some way to leverage this shared schema work that is not syncing
Because syncing is trivially solved by just telling the agent to keep a work journal in markdown
We do that, and it's really the point of the portability work. Once every harness's sessions live in one schema, you can manage and search all of them in one place.
The markdown journal is a fair way to do it, and a popular one. It has a couple of limits though.
A journal comes out of a prompt, so it records one way of looking at the session. Whatever that prompt didn't ask about is gone, and you usually find out which detail you needed much later. But the raw session still has it.
Being able to unify the schema lets you do things notes can't. You can continue a teammate's session on your own machine, or pick up a claude.ai conversation in Claude Code or Codex. The new agent gets the transcript: all the decisions in the trajectory, not a summary of it.
btw we also have an agent in the mac app that lets you analyze your sessions in all kinds of ways
To say what the author said in another way- thats a garbage approach and completely misses the point. Sure, you can completely destroy the session by distilling it into a markdown- but thats like explaining what you did yesterday, vs having an immutable log of what you did yesterday.
Any word on when you'll add support for antigravity? I often switch between harnesses and models and subscriptions, both for work and personal stuff, this is an awesome idea. One thing I do that I don't think you have support for is running sessions on different machines. Do you have support for, or do you plan on adding support for, syncing across machines?
Yes you can also ssh into your machines and sync all of those sessions too. Check out the + icon on the left side bar on the desktop app!
we do support antigravity!