dsh-docs-adr
Run the following command in DeepSeek Harness:
dsh plugin install satan9394/dsh-docs-adr
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install satan9394/dsh-docs-adr in DeepSeek Harness to install this plugin; the source repository is available at https://github.com/satan9394/dsh-docs-adr.
About this plugin
In long-running projects, architectural decisions often scatter across chat logs, emails, or one-off code reviews. Once the context is lost, teams end up re-litigating the same trade-offs. dsh-docs-adr brings Architecture Decision Records into the memory layer of DeepSeek Harness, giving every technical choice a persistent, retrievable home.\n\nAs a memory-class plugin, its core capability is to provide structured document memory for Harness sessions: ADRs capture the context, alternatives considered, and the final decision, allowing subsequent conversations to reference existing choices directly instead of re-debating settled questions.\n\nIt suits small and medium development teams that maintain a living ADR log, or individual developers who prefer documenting technical selections, offering lightweight decision memory within the Harness workflow.
Use Cases
- Persist technical design decisions as ADR entries within a Harness session
- Reference existing architectural decisions in follow-up conversations to avoid re-debating
- Maintain a structured, searchable log of architecture decisions for a project
Best For
- Developers who prefer documenting technical choices with ADRs
- Small and medium teams that need persistent architecture memory in Harness
- Tech leads who want to minimize repeated decision debates
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.