Dev iconDevSep 10, 2026 ~1 min source read

I tested DeepSeek Harness for a week. I left with a shipped plugin and $0 in API costs

I left with a shipped plugin and $0 in API costs I came to DeepSeek Harness as a reviewer and left as one of its plugin authors, which is a fair measure of how the week went. The hook is on the repo's first line: "Everything is a plugin." Not the usual marketing meaning â€" not a config file with a couple of third-party hooks.

I tested DeepSeek Harness for a week. I left with a shipped plugin and $0 in API costs

Share this story

Send the public story page.

Useful takeaways from this story.

I left with a shipped plugin and $0 in API costs I came to DeepSeek Harness as a reviewer and left as one of its plugin authors, which is a fair measure of how the week went.

The test project: a pricing board inside the harness itself The gap I kept feeling in Settings â†' Models was the two questions I ask before switching providers every time: what does this model actually...

The hook is on the repo's first line: "Everything is a plugin." Not the usual marketing meaning â€" not a config file with a couple of third-party hooks.

Building the complete brief

The page is ready to read now. The fuller skim-friendly version will appear here automatically.

The useful part

I left with a shipped plugin and $0 in API costs I came to DeepSeek Harness as a reviewer and left as one of its plugin authors, which is a fair measure of how the week went. The hook is on the repo's first line: "Everything is a plugin." Not the usual marketing meaning â€" not a config file with a couple of third-party hooks. This one takes it literally, and poking at it turned into the most fun I've had with an agent harness in a while.

Details worth keeping

All of it loaded through manifests over a real extension API. The test project: a pricing board inside the harness itself The gap I kept feeling in Settings â†' Models was the two questions I ask before switching providers every time: what does this model actually cost per million tokens, and is a cheaper route to the same model available?

Keep reading in the app

Open the app view to save this story, compare related coverage, and continue from the same source.

Open in app