dsh-super-code
Task-focused coding workflow plugin for DeepSeek Harness with agent presets, durable memory, and execution monitoring.
Install
$ dsh plugin --profile web add dsh-super-codePlugin 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
- Declarative 'Super Code' agent preset with autonomous delegation to specialist agents
- Persistent task memory and experience retention across multi-turn sessions
- Right-hand sidebar showing task status, circular agent execution trees, and memory management
- Configurable token and context compression budgets with legacy budget fallbacks
- Three-tier deletion protection modes for safeguarding critical project files
Useful For
- Tackling complex software engineering tasks and benchmark suites like SWE-bench within DeepSeek Harness
- Reducing token consumption and model turn latency during extended coding workflows
- Inspecting multi-agent subtask execution trees and inspecting step-level progress in real time
Who It Fits
- Software engineers using DeepSeek Harness for code generation and refactoring
- AI researchers benchmarking LLM software engineering performance
- Developers needing persistent context and structured agent workflows
Documented Limitations
- Requires DeepSeek Harness host versions between 0.1.5-alpha.1 and 0.2.1-rc.2
- CLI and Web deployments require Node.js 22 or later
- Task performance and pass rates may vary depending on model family, reasoning settings, and host budget parameters
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 2 runtime, 11 development, 15 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as Apache-2.0.
A root package.json was captured and can be inspected by the registry.
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
- ArtlexYoung/dsh-super-code
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 1dfa173 · 2026-10-24
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
- 16GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-23
- Last release
- 2026-10-23
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools 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 →