Плагины
Находите, фильтруйте и устанавливайте плагины DeepSeek-Harness.
Найдено плагинов: 9
dsh-atomgit
xiongjiamu/dsh-atomgit
Бандл плагинов AtomGit для DeepSeek Harness (dsh): workflow'ы atomgit-skills + CLI ag + инструменты MCP GitCode, размещённые на платформе.
dsh-rss
stardustlc666/dsh-rss
RSS/Atom subscription management and parsing (rss_list/add/remove/fetch/check), persisted to settings.
dsh-turn-fork
ruby1304/dsh-turn-fork
Turn-atomic message editing, retry, reroll and version-tree navigation for DeepSeek Harness conversations
dsh-agent-preset-recommender
leemancheung/dsh-agent-preset-recommender
Локальный сканер метаданных сессий/рабочих процессов Codex, Claude Code, WorkBuddy и CodeBuddy, безопасный для конфиденциальности; сохраняет агрегированные данные и рекомендует встроенные пресеты агентов DSH без сохранения содержимого, обращения к сети или изменения пресетов.
iterate-plugin
jingzhao-l/iterate-plugin
Turns the iterate skill into an autonomous closed-loop harness — plan, parallel review, atomic fixes, validate, loop, auto-stop — plus a dry-run review-only mode and a meta-review that audits the report and emits a final review report.
dsh-plugin-kit (rss)
hyzyn/dsh-plugin-kit
Daily RSS/Atom news digest for DSH: built-in channels plus a curated awesome-rsshub-routes catalog and custom feeds (validated on save), aggregated into one "今日值得读" Markdown digest each day and injected into the system prompt; Web GUI settings card and sidebar reader.
dsh-layered-memory
junnanlys/dsh-layered-memory
Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.
dsh-argp
yoza10635/dsh-argp
Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.
iterate-skill
jingzhao-l/iterate-skill
dsh plugin that turns the iterate skill into an autonomous closed-loop harness: plan -> parallel review xN -> atomic fixes -> validate -> loop -> auto-stop, plus a dry-run pure-review mode with multi-round convergence and a meta-review that audits the rep