dsh-purge
DeepSeek Harness 破甲:所有模型都可破甲,不同模型可换不同提示词;默认提示词面向国模「小码酱」。Jailbreak for every model. 求 Star ⭐
62 results
DeepSeek Harness 破甲:所有模型都可破甲,不同模型可换不同提示词;默认提示词面向国模「小码酱」。Jailbreak for every model. 求 Star ⭐
Declarative Claude Code-style permission rules plus a Codex-style process-level network policy for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), workspace-path, and network-target (domain/ip/port/scheme) matching on the tools/pre-execute waterfall, a built-in local HTTP/CONNECT proxy governing shell subprocess traffic, three network modes mapped onto the official sandbox presets, full session-log audit, HMR rule reload, and a settings page with a rule editor, block counters, and recent interception lists.
Browser desktop notifications when the DeepSeek Harness finishes a turn: configurable per-outcome toggles and include/exclude keyword rules, shown through the browser Notification API.
A professional marketer's operating mindset as a dsh skill — how to think, decide, and prioritize for any marketing or client-acquisition task. Not a tactical template.
DSH (DeepSeek Harness) plugin packaging of the Project Blueprint skill — one-command AI coding conventions (AGENTS.md, docs skeleton, CI/CD, git rules, testing policy) with an autonomous discovery engine (7 languages, 15 frameworks, 70+ components, web fallback).
跨工具(Cursor / WorkBuddy / Claude Code 等)的 SKILL.md 技能管理器与 Rules 规则管理器(含远程规则导入),TypeScript 零运行时依赖实现
Edit ~/.dsh/AGENTS.md (global rules) from the web settings panel.
Security scanner for DSH plugins: static and semantic passes over plugin source, DSH-specific attack-surface rules, npm audit, batch scanning, and an HTML report with per-finding severity and evidence.
dsh-skillport — every skill you already have (Claude Code, Codex, Cursor, Gemini CLI) works in DSH: Agent Skills SKILL.md discovery across .claude/.agents/.dsh/.gemini + extraPaths, Tier-2 conversions (cursor rules, claude commands, context files), find_skill search, and a skills doctor
Environment housekeeper for DeepSeek Harness: toolchain inventory, agent scratch/cache scan with safe one-click cleanup, and the machine rules file (AGENTS.md) view/edit - all in the Web GUI settings. Zero runtime dependencies.
Inject rules when needed, without wasting context. DSH port of opencode-stream-rules.
DSH host plugin — smart outbound HTTP(S) routing: named proxies (http/https/socks4/4a/5/5h), per-host/provider/plugin rules, direct-first fallback with health memory (global fetch + node http/https).
DSH web plugin: a native Settings panel for visualizing and managing MCP servers, skills and rules, with a modular feature registry so future visualizations slot in without touching the shell.
CC-style auto mode for DeepSeek Harness: deterministic deny/allow rules + pre-execute gate + model-agnostic two-stage classifier. Two-state (allow/reject) classifier since 0.8.0. TypeScript rewrite merging dsh-auto-mode v0.4.1 with Nuo-cl/dsh-auto-mode native integration.
Better DSH: archived-session management, task-stop desktop notifications, an update checker, model routing (keyword rules + allowlist-gated model_route), multi-task scheduled triggers (interval heartbeats & fixed-time tasks), and a DeepSeek-style message scroll nav for the dsh web GUI
DSH rules plugin: activate rule prompts / markdown documents by glob-matching the files an agent reads or edits (Claude Code rules.md style).
Archive manager (browse / unarchive / auto-rules) plus a Codex-style left tick rail for jumping between conversation turns. · 归档管理(浏览、取消归档、自动归档规则)与左侧对话刻度栏跳转。
Pack skills, rules, and MCP into .pack.zip and install them into Claude Code, Codex, Cursor, and other harnesses
Deploy the ArchGraph ARGO toolchain, skills, and rules (schema, scripts, argo-init skill, global rule) with one command.
Claude → DeepSeek Harness (DSH) 配置迁移插件:把 .claude/skills、.claude/rules、.mcp.json、CLAUDE.md 拖入插件目录即自动加载为 DSH 能力,内置完整看板(skills / rules / MCP / 连接状态)。
Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.
WeChat Official Account content studio for DeepSeek Harness: anti-homogenization writing methodology, blessing-image visual baseline, gpt-image cover pipeline with OCR acceptance, interaction rules, and the measured xiaolvshu (newspic) draft web API.
Append ambiguity-handling rules to dsh system prompt
Approval Assistant for DeepSeek Harness: approval reminders, auto-approval rules, completion reminders and question popups with per-feature channels (popup / system notification / sound / custom sound). 审批提醒、自动审批、完成提醒与提问提醒。