dsh-project-progress
Run the following command in DeepSeek Harness:
dsh plugin install Jolly-J/dsh-project-progress
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install Jolly-J/dsh-project-progress in your DeepSeek Harness terminal; the plugin source lives at https://github.com/Jolly-J/dsh-project-progress — restart dsh web after installing to activate it.
About this plugin
DSH runs session by session, yet a real project rarely finishes in one conversation. Context silently slips away between sessions: the agent has no idea where the last release stood, what the community rules are, or what to do next, and the human ends up re-pasting the same background over and over. dsh-project-progress keeps a single shared PROGRESS.md at the workspace root, split into two zones. The Project Facts zone holds stable information such as release status, repo URL, community rules, and install command; the Timeline zone is append-only, capturing automatic entries (title, turn count, token usage) written when a top-level session ends, or free-form progress notes added at any time. Every new session receives this document injected into its system prompt, so the agent starts with full project awareness. Three model tools—project_status, project_update, and project_facts—give structured, auditable read and write access.
All reads and writes stay inside your local workspace. There are no network calls, nothing is uploaded, and no secrets are read. PROGRESS.md is a plain Markdown file you can edit or delete whenever you like. The plugin suits developers who drive multi-session projects in DSH, especially plugin maintainers who must follow release and sync conventions. It keeps project state living in the repo alongside the code, instead of buried somewhere in a chat log.
Use Cases
- Auto-inject project state into every new session prompt
- Append a structured progress entry when a top-level session ends
- Keep release conventions and community rules in one place
Best For
- Developers driving multi-session projects in DSH
- Plugin maintainers bound by release and sync conventions
- Teams that prefer project state in the repo over chat logs
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
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.