dsh-plugin-sentinel
DSH 插件安检机 — install-time static security auditor for DeepSeek Harness plugin bundles. Zero dependencies, zero install scripts, zero build step.
110 results
DSH 插件安检机 — install-time static security auditor for DeepSeek Harness plugin bundles. Zero dependencies, zero install scripts, zero build step.
DSH arch-doc skill plugin: analyze a codebase and generate architecture documentation (module responsibilities, dependencies, entry points and run methods).
Local-first, evidence-backed session retrospectives for DeepSeek Harness
Model-facing analyze_image tool for the DeepSeek Harness: multi-modal image understanding via any OpenAI- or Anthropic-compatible vision API, with 8 analysis modes, local path / http(s) URL / data URL input, and a Web UI hint that guides image-incapable models to the reliable local-path route.
Data analysis toolkit for DeepSeek Harness — CSV profiling, anomaly detection, and data summarization
Real-time code feedback for DeepSeek Harness — LSP, linters, formatters, type-checking, and structural analysis.
Plug-and-play proteomics analysis bundle for DeepSeek Harness: auto-managed R 4.4 runtime, step-wise traceable pipeline (normalize / PCA / batch / DEA / enrichment / GSEA), cached GO-KEGG annotation backgrounds.
DeepSeek Harness plugin for evidence-backed repository analysis and reviewable, bounded change proposals.
Read-only TypeScript and JavaScript change-impact analysis for DeepSeek Harness
DSH bundle: Xiaohongshu (RED) viral-note agent skill — hot-note research, note generation/rewrite, verification, authorized account analysis, QR login and controlled publishing, shipped as a bundled skill provider. Zero-dependency.
Pre-install supply-chain poison scanner for DeepSeek Harness plugins: AST analysis (NodeSecure JS-X-Ray) + deobfuscation decoder + regex heuristics to catch credential exfiltration, dynamic code execution, obfuscated imports, and install-time scripts.
Agent-agnostic skill that turns task input files into reusable structural briefs and a per-task searchable index (OpenAI Codex, Claude Code, DeepSeek Harness)
DSH arch-doc skill plugin: analyze a codebase and generate architecture documentation (module responsibilities, dependencies, entry points and run methods).
Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval
DSH 代码图谱可视化插件 - 打通 dsh-codegraph/dsh-tool-lens 数据源 → 聚合转换 → 交互式代码图谱
Parallel contradiction analysis for DSH conversations: a 0-100 coherence score badge with commentary, manual trigger, and auto-analysis on by default (interval editable, off per conversation or globally). Reuses the conversation's exact prefix so the provider KV cache stays warm.
Static and runtime security guard for the DeepSeek Harness: scans plugins and workspaces for malicious code, context injection and token waste (block/warn/clean), intercepts dangerous runtime tool calls and prompt steps, and exposes /scan, plugin_scan, the scan web panel and a user-managed allowlist. Fully static analysis — never executes scanned code.
DeepBrain (深脑) plugin for DeepSeek Harness: give your agent an organization's second brain — judgments with evidence chains, verbatim-verified quotes, people's historical positions, and 200+ analysis methods it can borrow
DeepSeek Harness 原生视觉 Bundle:粘贴或拖入图片,通过托管的 deepseek-vision-mcp 调用 OpenAI 兼容视觉模型。
DeepSeek Harness plugin bundle: graphlint dead-code detection tools for agents (graphlint_query / graphlint_build / graphlint_config + graphlint skill).
DSH plugin: stock market intelligence for DeepSeek Harness — quotes, financial statements, filings, earnings, economic data and more, dynamically synced from the stockmcp.net remote MCP server as model tools (with a settings page for your API key).
Document and image analysis tools for agent harnesses, powered by a local OpenAI Codex CLI.
Model-facing accurate_vision tool: precise image spatial reasoning via a vision model
Pre-write reuse firewall for DeepSeek Harness: before the agent writes a new helper/service, surface the existing implementations that already cover that intent. Deterministic retrieval (no LLM) backed by the Auto_code_audit capability channel.