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

A developer built and shipped dsh-model-pricing, a plugin for DeepSeek Harness that adds per-million-token cost comparisons and cheapest-route badges to the harness's Settings page, after testing the tool for a week. The plugin was developed entirely inside DeepSeek Harness driven by Qwen3.8-Flash via a free API promotion, producing 28 commits and roughly 2,300 lines of code at $0 in LLM costs. The author says the harness's 'everything is a plugin' architecture, including its web UI and settings screen, is assembled from plugin contributions.

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 — not a config file with a couple of third-party hooks. In DSH the agent hosts its own web UI as plugin packages; the settings screen where you pick and configure models is assembled from plugin contributions this is the part I verified the hard way ; even the optional subagents — Codex, Claude Code — ship as plugins you can add or drop. All of it loaded through manifests over a real extension API. I've poked at a lot of "extensible" tools. This one takes it literally, and poking at it turned into the most fun I've had with an agent harness in a while. The gap I kept feeling in Settings → 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? DSH tells you which models exist. It doesn't tell you what they cost. dsh-model-pricing closes that, and it lives inside the harness's own Settings page — because that's the point of testing the plugin system: cheapest badge: GLM-5.2, say, runs from $3.08 to $4.84 per 1M output tokens depending on the gateway — the same model, 57% apart It installs through the harness's own plugin manager — I never forked anything: npx -y @deepseek-ai/dsh plugin --profile web add dsh-model-pricing Here's the part I didn't expect. I built the whole thing using DeepSeek Harness, driven by Qwen3.8-Flash through B.AI's current promotion — the one Eight records shipped on day one; one of them describes the free model that wrote this plugin's UI. | priced rows / providers | 7,178 / 213 | | harness-catalog overlaid rows | 788 30 disagreements flagged, not averaged | | plan rows grouped & excluded from ranking | 175 | | promo records at launch | 8 each with source URL + verification date | | commits / files / LOC | 28 / 18 / ~2,300 | | wall-clock | ~22h, incl. overnight autonomous rounds | | LLM cost | $0 — free API promotion, re-verify date 2026-10-10 | | UI languages | en + zh platform , ru plugin | If you're curious about DeepSeek Harness the way I was: run it, then break into its settings page. The architecture is the product; the agent is very good at both jobs, even on a model that costs nothing. npx -y @deepseek-ai/dsh plugin --profile web add dsh-model-pricing Repo docs, feature map, the promotion contribution rules — all public : github.com/vitas/dsh-model-pricing https://github.com/vitas/dsh-model-pricing · npm: dsh-model-pricing https://www.npmjs.com/package/dsh-model-pricing · Apache-2.0.