DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to see what fills the DSH context window with Awesome DeepSeek Harness

Install a context dashboard that breaks down window use, compression and token stats per request.

Who it is forA developer whose DSH agent gives poor answers on long tasks and who wants to see what is using the context window.

The problemThe context window is a black box, so it is unclear why answers degrade or what is being compressed.

The outcomeA dashboard shows window composition against size, per-request history, compression events and per-message token stats.

What you need first

  • DeepSeek Harness (DSH) installed, with the dsh command available
  • Access to the target plugin repo on GitHub, which should carry the #dsh topic
  • A DSH profile to install plugins into (the examples use the profile name web)

Steps

  1. Run npx @deepseek-ai/dsh web to launch the DSH Web UI.
  2. Confirm the plugin repo at github.com/bowenliang123/dsh-context carries the #dsh GitHub topic.
  3. Run dsh plugin --profile web add "github:bowenliang123/dsh-context#main" to install the plugin. (inferred, check the README)
  4. Run a multi-step task in DSH and open the context dashboard.
  5. Compare window composition with the per-request history to find the largest source of tokens.

Prompt for your agent

Using the DSH list at https://github.com/Dominic789654/awesome-deepseek-harness, install the dsh-context plugin from github.com/bowenliang123/dsh-context. Run <task-description> in DSH and report the three largest parts of the context window with their token counts. Verify by matching the totals against the per-request history.

Caveat. The list describes what the plugin shows, but its exact display and data sources need to be checked in the plugin repo.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page