# bowenliang123/dsh-context

The best DeepSeek Harness plugin for context insight and management, with context dashboard / browser and context command, for context statistics, composition, breakdown, evolution details, understanding how the context is made of, and how it evolves. 一站式 DeepSeek Harness 上下文可视化插件，Context 面板及浏览器与 Context 命令，透视上下文组成、演进、压缩、剪枝等事件与动作。

Repository: https://github.com/bowenliang123/dsh-context
Canonical: https://ross.abutalabs.com/products/dsh-context
Homepage: https://www.npmjs.com/package/dsh-context
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: dsh-external, dsh-plugin, dsh-plugins, cordis-plugin, deepseek-harness, deepseek-harness-plugin
Last push: 2026-09-02T10:12:53+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 88, longevity 1
- inputs: {"age_days": 19, "days_push": 0, "days_rel": 0, "gap_med": 0.0, "n_releases_24m": 81}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1248, forks 33 (observed 2026-09-03T02:15:09.648609+00:00)

## What it is
A DeepSeek Harness plugin that provides context insight and management for AI agent sessions. It offers a Context dashboard tab and a /context slash command to visualize context composition, statistics, and evolution including compaction and pruning events.

## Use cases
- visualize what is inside my LLM agent's context window
- track how agent context evolves across turns and steps
- debug why context compaction or pruning happened
- see token breakdown of system prompt, tool schemas, and messages
- monitor context window usage and remaining headroom
- inspect what any past request was assembled from

## When to choose
- you use DeepSeek Harness and want visibility into agent context composition
- you need to debug context growth, compaction, or pruning in agent sessions
- you want a UI dashboard plus slash command for token/context analytics

## When to avoid
- you use a different agent framework than DeepSeek Harness
- you need context management rather than insight for a non-LLM application
- you cannot run the DeepSeek Harness web UI

## Facets
- artifact type: plugin
- maturity: active
- function: monitoring, analytics, data-visualization, developer-tools
- domain: developer-tools, large-language-models, analytics
- platform: cli
- tags: deepseek-harness, context-management, context-window, token-usage, llm-debugging, dashboard, slash-command, cordis-plugin, ai-agents, nodejs, web-server

## Member repositories
- bowenliang123/dsh-context (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:09.648609+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:56:43.580901+00:00, confidence not recorded.
  - readme: https://github.com/bowenliang123/dsh-context (fetched 2026-09-03T02:15:09.648609+00:00, sha faac91214f30)
  - registry_npm: https://registry.npmjs.org/dsh-context (fetched 2026-08-29T12:58:15.169938+00:00, sha 3d753502c35e)
- Data as of 2026-08-30T08:39:29.467469+00:00.