Install
$ dsh plugin --profile web add github:wxxb789/dsh-legionPlugin 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
- Provides semantic Specialist profiles (e.g., quick, deep, review) with deployment-owned personas, tool filters, and model routes
- Performs exact LLM model routing across up to eight ordered candidate configurations based on static context and token constraints
- Supports multiple DSH subagent backends including spawn, fork, codex, and claude-code via the Agent Client Protocol (ACP)
- Offers structured foreground result contracts including text, findings-v1, and review-v1
- Enables declarative multi-agent Cohorts and execution Strategies with strict limits on concurrency, deadlines, depth, and output size
- Provides CLI diagnostics and configuration verification via dsh-legion doctor and explain commands
- Integrates a web settings card and live Run Receipt companion for tracking member execution facts
Useful For
- Routing specific coding agent tasks (like summaries or deep debugging) to specialized models according to intent
- Executing read-only, isolated code and security reviews using structured findings contracts
- Orchestrating multi-agent workflows such as plan-execute-review or research panels without running a secondary scheduler
- Delegating subagent tasks to external coding tools like Codex or Claude Code over DSH's ACP backend
Who It Fits
- DeepSeek Harness deployment owners and platform engineers
- Developers building multi-agent or multi-model workflows within DSH
- Teams requiring auditable, constrained subagent delegation and model routing policies
Documented Limitations
- Does not provide its own standalone runtime or agent framework; requires DeepSeek Harness
- Does not retry or switch routes if a chosen subagent candidate fails at runtime due to network, auth, or provider errors
- Point-in-time static route selection does not inspect live provider health, latency, or quota
- Does not support overriding child reasoning effort or aggregate token cost admission limits
- Strategies are disabled by default and require explicit opt-in via enableStrategies
- Durable Strategy runs require host-level capabilities and fail closed if adapters are unavailable
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 4 runtime, 44 development, 11 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
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
- wxxb789/dsh-legion
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 91f0423 · 2026-10-26
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
- 4GitHub stars
- Forks
- 1
- Open issues
- 0
- Last commit
- 2026-09-02
- Last release
- No release detected
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 →Agent skill for DeepSeek Harness that turns ideas, plans, and codebases into interactive architecture diagrams.
View plugin →