deepseekplugins

DeepSeek Harness plugin

xuanling

Recommended DeepSeek Harness bundle: add the complete XuanLing Memory v2 profile while retaining DSH's native tools.

Memory
Jump to install

Source facts

Repository
umbrella22/xuanling
Latest update
Aug 21, 2026
Category
Memory
GitHub stars
3
Format
plugin
Package path
integrations/deepseek-harness/xuanling-memory
Catalog evidence
Upstream dsh.bundle evidence
Evidence path
integrations/deepseek-harness/xuanling-memory/package.json#dsh.bundle
Checked against
0.1.0-rc.8
Upstream check date
2026-08-21

This evidence comes from the upstream catalog. This site has not installed, run, or security-reviewed the plugin.

Install

Start with a prompt that asks an agent to review the GitHub repository and source. Switch to the command if you want to install it yourself.

Copy this prompt into DSH, Codex, or another agent and ask it to review the GitHub repository and source first.

Do not install or run any commands yet. Read this plugin's GitHub repository, README, and relevant source code. Then answer the questions below clearly and directly so I can decide whether it fits my needs:

1. What is this plugin, and what problem does it solve?
2. Who is it for, and what are its typical use cases?
3. How is it used after installation? Include one minimal example.
4. What known limitations or privacy, security, compatibility, or maintenance risks does it have?
5. Give a clear recommendation: recommend, conditionally recommend, or do not recommend, with reasons.

Distinguish statements documented by the repository, inferences from source code, and unknowns. If evidence is insufficient, say so explicitly. Do not guess or simply repeat the README.

GitHub: https://github.com/umbrella22/xuanling/tree/HEAD/integrations/deepseek-harness/xuanling-memory
Plugin: xuanling
Author: umbrella22

Check the source files

Read the README and other files from this plugin directory before installing.

File explorer4 files
README.mdSource · read only
README language

xuanling-dsh-memory

English | Simplified Chinese

Recommended DeepSeek Harness bundle for XuanLing Memory v2. It adds the full nine-tool proposal, review, recall, archival, and feedback profile while retaining every Harness-native tool.

dsh plugin --profile web add @xuanling-rs/xuanling-dsh-memory@0.2.6

This command augments DSH's shipped Web profile. Use --profile headless for the shipped Headless profile. Unknown profile names start with the base bundle only and do not provide a runnable Web or Headless application by themselves.

The bundle installs @xuanling-rs/xuanling-mcp@0.2.6 inside the selected profile. Its schema adapter and JS launcher are resolved from that profile, and the launcher verifies the selected native package before startup. No global package or install-time binary download is required.

The result adapter also applies the DSH projection contract: repeated text blocks that exactly duplicate structuredContent are reduced to one complete text block, while the structured value remains available to Code Mode and output validation.

The schema adapter validates child JSONL frames and request settlement. A malformed frame or an unresolved tools/list/tools/call at clean child exit returns a nonzero status; a child ignoring host termination is force-terminated after a 500 ms grace.

Use @xuanling-rs/xuanling-dsh-skills@0.2.6 alongside this bundle for the proposal-first Memory workflow and strict whole-file overwrite policy. Do not combine this bundle with another XuanLing tool bundle in the same profile because both register the xuanling-tools row.

Node.js 22.14 or newer is required. Supported native targets are macOS ARM64, Linux x64 glibc 2.35+, and Windows x64 MSVC. Licensed under the MIT License.

Back to searchOpen GitHub repository

More related plugins

View category