dsh-stream-rules injects steering rules into a DeepSeek Harness agent only when a pattern matches, so guidance arrives without permanently consuming system context. The rule is delivered as a steering notice and the agent retries from that point. Similar in spirit to oh-my-pi's time-traveling stream rules, with a compact implementation.
Copy the command below and run it in your DeepSeek Harness terminal.
dsh plugin add github:jiesou/dsh-stream-rules Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety →
A rule fires when its match returns true, against: the tool call — tool name + flattened arguments (numbers included, e.g. timeoutMs), before dispatch.
Learn how to choose, install, and use tools & capabilities plugins.
dsh-stream-rules is a tools & capabilities plugin maintained by jiesou. dsh-stream-rules injects steering rules into a DeepSeek Harness agent only when a pattern matches, so guidance arrives without permanently consuming system context. The rule is delivered as a steering notice and the agent retries from that point. Similar in spirit to oh-my-pi's time-traveling stream rules, with a compact implementation.
Run dsh plugin add github:jiesou/dsh-stream-rules in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:jiesou/dsh-stream-rules#commit.
dsh-stream-rules is a community open-source project released under the MIT license. You can inspect its source and install it for free.
The first vision plugin for DeepSeek Harness, and a vision bridge for text-only coding agents. Paste an image and receive structured JSON evidence back — OCR, layout, and semantic understanding — ready for any agent to act on.
View plugin → 
liustack
Native Harness surface — Design and PPT appear as dedicated conversation views; the iPolloWork desktop app is not required.
View plugin → 
Devin-AXIS
Model-Driven Incremental Hierarchical Compression: Training-Free Multi-Generational Context Management for Long-Lived Coding Agents (English, v0.2) 📝 The paper itself is…
View plugin → 
ranxianglei