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 a single 'legion' delegation tool with semantic Specialists like quick, deep, and review
- Supports exact LLM model routing with up to eight ordered provider and model route candidates
- Enforces tool filtering, depth limits, persona overrides, and foreground or background execution defaults
- Defines declarative Cohorts and artifact graph Strategies with limits on agents, concurrency, deadlines, and output sizes
- Supports structured foreground result contracts (text, findings-v1, review-v1)
- Integrates with external coding agents via DSH's Agent Client Protocol (ACP) backend
- Includes offline configuration diagnostics and policy verification via 'dsh-legion doctor' and 'explain' CLI commands
- Mounts an optional Web settings card for runtime configuration adjustments
Useful For
- Routing tasks by complexity or type, such as sending summaries to fast models and complex debugging to deep models
- Executing independent code reviews with restricted read-only toolsets and structured findings contracts
- Composing multi-agent plan/execute/review and research fanout workflows under bounded concurrency and execution limits
- Delegating tasks to external ACP-compatible agents (such as Codex, Claude Code, and Copilot CLI) within DSH
Who It Fits
- DeepSeek Harness developers wanting multi-agent delegation without a separate runtime framework
- Deployment owners configuring granular LLM model routing and subagent access policies
Documented Limitations
- Does not provide aggregate token or monetary cost admission controls
- Does not inspect live provider health, credentials, authorization, quota, reachability, or latency (route evaluation uses static facts only)
- Does not retry or switch routes if the selected child subagent or provider fails
- Curated Strategies are hidden from the model by default unless explicitly enabled via enableStrategies
- Cannot override a delegated child subagent's reasoning effort
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.
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 · 2026-09-12
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
- 3GitHub stars
- Forks
- 0
- 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.
Native SQLite-backed local project taskboard plugin and UI for DeepSeek Harness with Agent claim and review flows.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Compatibility bridge and host ABI enabling unmodified Pi plugins to run natively on DeepSeek Harness.
View plugin →