100 results
Diff cards in the DeepSeek Harness web chat for recognizable file mutations — MCP filesystem calls (edit_file, write_file), built-in edit/write, and file-mutating bash commands (heredoc replaces, sed -i, cat/tee/redirect writes).
OmicOS as a deepseek-harness (dsh) plugin — Mode A: omicos bioinformatics tools + background jobs + login commands for the dsh agent (DSH-PLUGIN.md).
Chinese-thinking system-prompt section for DeepSeek Harness: make your dsh agent think and answer in simplified Chinese (code/commands stay verbatim).
DeepSeek Harness plugin: Claude-Code-style lifecycle hooks for DSH. Configure shell commands that run automatically before/after model tool calls (pre-tool / post-tool) with a JSON payload on stdin; pre-tool non-zero exits block the call.
Kubernetes (kubectl) integration for DeepSeek Harness: inspect clusters, get/describe resources, read logs, port-forward and run one-off commands — with structured JSON output that agents parse reliably.
极简常用片段/命令工具箱 for DeepSeek Harness: JSONL-backed, five tools, no UI, no deps beyond the harness SDK. Save frequently used commands, code, URLs and prompts, then search them back in any session.
DSH plugin: expose rtk (Rust Token Killer) token-optimized commands as model-callable Tools (9 wide categories + doctor), saving 60-90% tokens on shell output.
RTK command rewriting suggestions + tool output compaction for DSH. Suggests rtk-rewritten bash commands (deny-mode under rewrite) and compacts noisy tool output (bash/grep/read) to reduce context usage. Port of pi-rtk-optimizer for the Pi coding agent.
Voice assistant plugin for dsh web: hands-free wake phrase, dictation, voice edit commands, and Chinese TTS.
A middle permission tier for DeepSeek Harness between workspace-write and danger-full-access: auto-approves harmless commands and operations targeting configured trusted areas, beyond the current workspace.
Claude Code compatibility layer for DeepSeek Harness: load .claude skills/commands/agents and install plugins from Claude Code marketplaces as native dsh skills.
Slash commands to delete sessions and workspaces (projects) in DSH
Local SSH bridge for the DeepSeek Harness (DSH): user types the router password in a browser page, agent runs commands via a localhost API — the password never enters the chat.
DSH plugin: block dangerous shell commands and secret leakage before execution (tools/pre-execute veto)
Dependency-installation guard for DeepSeek Harness: classifies package-manager commands as ALLOW, ASK, or BLOCK before execution.
A collapsible in-conversation interactive terminal: each tab is a live host PTY (xterm.js over WebSocket) with per-project persistent quick commands
Model-facing environment probe tool for DeepSeek Harness: runtime environment, PATH commands, software versions, and host resources on demand
DeepSeek Harness plugin: cross-session memory for the model. Full-text search all past sessions (SQLite FTS5 via ctx.sessionQuery) and bring the strongest matching excerpts back into the current context — recall earlier decisions, commands, and mistakes.
DSH adapter for everything-wp — WordPress plugin dev AI toolkit. Phase 3: 18 commands + 5 agents with mode gating and inline rules.
Run commands on the Windows host's Git for Windows Bash from DeepSeek Harness. WSL-aware, auto-detects the git-bash install path, zero runtime dependencies.
AI coding delivery trust layer for governance-aware coding agents — zcode plugin packaging. The plugin surface lives in skills/ and commands/; this file only provides the npm package identity expected by the zcode plugin host.
Unified DeepSeek Harness plugin: role-based subagent routing + per-agent evolution — prefercmd/memory as knowledge allow/deny lists, so repeated tasks start from proven commands and save tokens
Mention a server with @ in a DeepSeek Harness session and run commands on it over SSH, behind a two-tier approval gate that fails closed.
dsh profile bundle: workspace-switching one-shot CLI mode — dsh --profile cli -w <workspace> -c <task>, plus `ws` management subcommands.