dsh-outsourcing-expert
DSH plugin bundle providing agent presets that enforce subagent task delegation and maintain a shared model capability cache.
Install
$ Install: dsh plugin --profile <profile> add dsh-outsourcing-expert (or from GitHub: github:Funny1Potato/dsh-outsourcing-expert), then start a new session and pick 外包高手, 外包高手（独具慧眼） or 领导模式. Only the three presets this bundle declares are affected; other presets are untouched.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
- Enforces tool interception at the harness boundary, denying direct execution of non-management tools and requiring subagent delegation
- Provides three agent presets: balanced outsourcing, reverse hiring (intentionally misaligned delegation), and leader mode
- Conducts automated one-time web reconnaissance of configured models and caches capability tierings in a machine-global models.json file
- Automatically enriches delegation results with routing details including provider, model, and reasoning effort
- Provides interactive slash commands (/outsourcing-models, /outsourcing-models-clear, /outsourcing-models-init) to inspect and manage capability caches
Useful For
- Enforcing strict managerial hierarchy where the top-level agent delegates all reading, writing, and shell execution to subagents
- Automating model selection across multi-provider setups based on difficulty and task domain
- Stress-testing and benchmarking model robustness under intentionally mismatched delegation (reverse mode)
- Accelerating subagent tiering across multiple sessions via shared capability caching
Who It Fits
- DeepSeek Harness users orchestrating multi-agent systems with tiered models
- Developers seeking automated subagent task assignment and delegation boundaries
- AI researchers evaluating task allocation and delegation strategies
Documented Limitations
- Model selection criteria are guided by prompt disciplines rather than runtime parameter rewrite enforcement
- Capability cache quality relies on initial automated model research and requires manual invalidation when providers or models change
- Tool execution interception applies strictly to the two outsourcing presets and does not intercept tools in leader mode
- Capability cache is global to the machine rather than isolated by workspace or session
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, 0 development, 0 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.
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
- Funny1Potato/dsh-outsourcing-expert
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 2cf20c3 · 2026-10-27
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
- 7GitHub stars
- Forks
- 0
- Open issues
- 1
- 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.
Multi-agent team collaboration plugin for DeepSeek Harness enabling coordinated sub-agents, dependency-aware task graphs, and web UI monitoring.
View plugin →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 →Comprehensive long-term memory, self-evolution, skills, task management, and multi-agent dispatch bundle for DeepSeek Harness.
View plugin →