Install
$ dsh plugin --profile tui add \Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Bundles TUI, shell execution, and granular permission controls into DeepSeek Harness profiles
- Supports Claude Code-style subagents (.claude/agents), SKILL.md files, and project memory (CLAUDE.md)
- Provides custom slash commands including /mcp, /provider, /skills, /tasks, and /commit-split
- Enables model alias mapping (opus, sonnet, haiku, etc.) to arbitrary LLM providers and models
- Includes reversible tool-output compression (context-crusher) and MCP server integration
- Offers optional plugins for task shunting, Codex/Grok bridging, and VWA evidence-based document review
Useful For
- Running terminal-centric coding agent sessions within DeepSeek Harness
- Porting Claude Code agent definitions, prompts, and skills to open or alternative LLM endpoints
- Executing multi-agent workflows with specialized reviewer, executor, or marathon subagents
- Performing evidence-backed document drafting and structured argument validation
Who It Fits
- Developers utilizing DeepSeek Harness for terminal and web-based AI coding workflows
- Teams looking to migrate Claude Code project configs and skills to custom LLM deployments
- Power users requiring granular tool execution permissions and MCP protocol support
Documented Limitations
- Parity with Claude Code is functional rather than exact; some hooks and background IDE features remain partial
- Requires DeepSeek Harness runtime (minimum dsh >= 0.2.0-rc.2 for recent versions)
- Status line customization is limited to three rows of stdout
- Experimental semantic argument review in VWA adds significant token usage and inference latency
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 9 development, 0 peer, and 0 optional dependencies.
GitHub reports the repository license as Apache-2.0.
A root package.json was captured and can be inspected by the registry.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- dsh-cc/dsh-cc
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 6c7aea2 · 2026-10-21
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 5GitHub stars
- Forks
- 2
- Open issues
- 3
- Last commit
- 2026-10-21
- Last release
- 2026-10-17
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed security.
View plugin →Comprehensive long-term memory, self-evolution, skills, task management, and multi-agent dispatch bundle for DeepSeek Harness.
View plugin →