dsh-math-team
Team-oriented mathematical modeling agent presets and workflow bundle for DeepSeek Harness.
Install
No clear install command was found in the current repository evidence.
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
- Provides two DSH agent presets: model-code (modeling & programming) and paper (paper drafting & verification)
- Integrates quality gates including M2 robustness attack testing and P2/W2 completion verification
- Spawns automated vision sub-agents to verify figures and review rendered PDF pages for layout defects
- Implements dual-model cross-auditing for adversarial fact-checking, consistency checks, and reference validation
- Enforces a structured multi-folder Git team collaboration protocol across separate member workspaces
Useful For
- Collaborative mathematical modeling competitions (such as CUMCM or MCM/ICM) using DeepSeek Harness
- Automated code, figure quality inspection, and PDF layout proofreading across distinct specialized agent personas
- Rigorous computational model validation through stress-testing, out-of-sample checks, and adversarial LLM reviewing
Who It Fits
- Mathematical modeling competition teams
- Students and researchers conducting scientific computing and paper drafting with AI agents
- DeepSeek Harness users organizing multi-agent collaborative workflows
Documented Limitations
- Requires DeepSeek Harness 0.2.0 or higher due to preset bundle loading requirements
- Desktop installation links to a local absolute path, requiring the folder to remain in place
- Vision audit capabilities require an environment with at least one image-capable model configured
- Desktop client must be fully restarted for preset configuration updates to take effect
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
- OrinVoss/dsh-math-team
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 341fff2 · 2026-10-11
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
- 2026-09-29
- Last release
- 2026-09-29
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 →Comprehensive long-term memory, self-evolution, skills, task management, and multi-agent dispatch bundle for DeepSeek Harness.
View plugin →An ontology-first agent preset and epistemic loop platform 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 →