@dingyi222666/dsh-agents-md
opencode-style custom agents for dsh: define agents as markdown files with their own system prompt and model, then call them from chat with an @mention — each mention dispatches a subagent
425 results
opencode-style custom agents for dsh: define agents as markdown files with their own system prompt and model, then call them from chat with an @mention — each mention dispatches a subagent
Todo-backed turn-stop gate and prompt plugin for DeepSeek Harness: blocks stop on unfinished work and prompts on no-todo or stale-todo streaks, configurable in the settings page.
Queue Consolidation for DeepSeek Harness: when the agent is busy and you queue several follow-up messages, the next turn runs with ONE consolidated formal prompt — the model rewrites the batch into a single prompt and executes once, instead of piecemeal one-message-per-turn rework.
Read-only, offline-first security scanner plugin for DeepSeek Harness plugins.
dshX live model working-status line (fork of dsh-working-activity): standard enterprise copy, running tool, turn elapsed — for the dshX TUI prompt.
DSH plugin that injects a system-prompt rule block for assisting with DeepSeek Harness plugin development: what you CAN / SHOULD / MUST NOT / SHOULD NOT do.
Tune the conversation area: font, width, line height, paragraph spacing, and Cursor-like sticky user prompts. 对话区界面设置:字号 / 字体 / 行距 / 段距 / 宽度 / 滚动钉住本轮用户消息。
把 git 状态与仓库规范动态注入 system prompt:分支/脏文件数/最近提交 + 仓库规范指引(官方 system-prompt section/context/variable 缝隙插件)
Mixture of Agents (MoA) tool plugin for DeepSeek Harness — run several models in parallel on the same prompt, then have a stronger aggregator model synthesize a final answer. On-demand tool, zero cost when unused.
DSH plugin: adapts DashScope/闂傚倸鍟锟犲闯闁垮顩查柟瀵稿У椤忋儵鏌?DeepSeek endpoints that lack native tool calling by converting tool definitions to prompt text and parsing model responses for tool calls.
A safe, native prompt polishing button for the DeepSeek Harness composer.
提示词模板库 + 任务完成提醒 (prompt templates + task completion alerts) for DeepSeek Harness Web GUI — static Cordis plugin bundle (host + client halves)
Persistent cross-session memory plugin for DeepSeek Harness: workspace-scoped durable facts with model-facing memory_write/list/search/forget tools and bounded prompt injection
Model-facing describe_image + extract_text tools for the DeepSeek Harness web GUI: gives a text-only model reliable image understanding and OCR through an OpenAI-compatible vision endpoint, with critical-inspection prompts, auto-preprocessing, retries, and a persistent answer cache.
Extra prompt slots (${provider} ${thinking} ${time} ...) for the official turtle-ui TUI of DeepSeek Harness
DeepSeek Harness plugin: cron-driven scheduled items. Each item carries a title, a prompt, and a croner expression; executions spawn a fresh agent session in a bound workspace (or the default cwd) and run on schedule or on demand. Includes a full-page management UI.
DeepSeek Harness plugin: injects an [IMPORTANT] chain-of-thought rule block at the very top of the system prompt of every model request (English CoT starting with I'm, no 'Let me', direct verbs).
docgen — document workshop skill pack: pure-prompt Agent Skills for README generation, PR descriptions, changelogs and code review, installable into dsh (DeepSeek Harness).
DeepSeek bills peak hours at 2x, and peak is 09-12 and 14-18 Beijing time. npx dsh-lean audit shows what your session paid and what it costs off-peak. DeepSeek 峰时按 2 倍计费,峰时正好是上班时间。
只读参考库插件:UI 交互式管理(应用内目录浏览器/系统选择器/手动路径直加)+ systemPrompt 注入 + per-session sidecar 持久化
DSH composer plugin: ↑/↓ prompt-history navigation — browse the current session's sent prompts right in the input box, with a "历史 x/y" badge.
DSH plugin: compress verbose voice-dictation text into token-efficient prompts, fully local.
DSH Agent 上下文浸泡器:System Prompt 注入五维认知图鉴(宪法+速览常驻,全文技能化按需),末尾 HTML 注释快照提取链演化状态,历史快照滑窗保留与漂移自愈回路
Adaptive task and risk routing, loop budgets, and progressive tool-result pruning for DeepSeek Harness