Find the right DSH plugin
for your next workflow

An MC-Fabric-style hook processor.

Loads Claude-style plugins into DeepSeek Harness (dsh): discovers skills, commands and optional SessionStart hooks from Claude plugin directories, with hot command reload and uninstall cleanup.

Freshness gate for the agent's test, typecheck, lint and build claims: each verification run becomes a receipt on tools/post-execute, file edits are tracked, and on agent/turn-stopping a claim whose latest receipt is stale, failed or has no readable result steers one more step naming the receipt and the files edited since.

Performance profiling and LLM cache diagnostics for DeepSeek Harness — context engineering, latency profiling, and cache behavior reports.

Read-only runtime management panel for the official DSH MCP client: connection status, registered tools, errors, and reconnect counts through the /mcp command and a Settings tab, with sanitized display and enable/disable patch suggestions.

Exports the session event stream to OpenTelemetry OTLP and Langfuse as sanitized, buffered traces and metrics, off by default.

Runtime-switchable model output styles with Claude Code outputStyles parity, plus the output.render.* presentation protocol: a /style command, per-session persistence, systemPrompt injection, six built-in styles, a web picker, and a renderer registry with per-session/per-tool rules and /export.

Multi-dimensional quality scoring for DeepSeek Harness plugins that scores a repo or npm package across install success, maintenance activity, documentation completeness, security scan, and protocol compliance using real CLI evidence, and produces a JSON or Markdown leaderboard report.

Runs isolated install-and-smoke test drives for DSH plugins in throwaway profiles, returning structured pass/fail records and batch matrices without touching your real profile.

Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.

Use Kimi Code as the DSH agent loop over ACP, with approvals, slash commands, and local/remote (ssh+tmux) session attach.

Backs up DSH profiles and mints a desktop "revival coin" that restores the harness after a failed boot or install: a boot guard runs a two-phase health check (HTTP 200 plus client render), marks good boots, isolates or rolls back bad ones, and keeps 3 rotating snapshots. Cross-platform.

Skills & MCP section in Settings: browse, create, edit and delete skills with live directory watching, toggle loading of any on-disk skill through frontmatter policy keys, register local folders or GitHub repos as extra skill scan roots, edit the MCP server rows in the profile patch, import MCP config from Claude Code or Codex, and install from a curated market of skill repos and MCP servers.

Real AST-based scan of installed plugins for malicious-intent patterns (dynamic eval, cross-plugin writes, exfiltration-shaped network calls), with an optional periodic schedule and auto-quarantine on critical findings.

Prunes the tool schema to a whitelist and injects a structural preamble on a session's first turn only, then passes every later turn through untouched.

Registers /wrapped, which reads the session's own stats and renders a shareable dark SVG summary card — tool vs. thinking time, decode speed, and a tool/thinking-ratio verdict.

Configurable per-turn budgets for supported file mutations, limiting distinct files, mutation calls, and UTF-8 payload bytes before tool execution.

PWA plugin for DSH — adds offline support, service worker caching, and install-as-app capability.

Edit the host-wide global instructions (~/.dsh/AGENTS.md) from a dedicated Customize page in Settings - every session on this machine applies them.

Claude Code rules.md-style rule prompts: activate rule markdown files by glob-matching the files an agent reads or edits, with prompt injection and ordering support.

Minimal-anchored agent preset: request #1 keeps the real bash + str_replace_editor pair with auto-injected context stripped, then promotion unlocks the full Standard catalog and posts a one-shot background-jobs notice against sleep-polling habits.

Agent2Agent protocol v1.0 for DSH: run a standard A2A server to let other agents call this instance, connect to remote A2A agents as clients, and manage both from a visual settings page.

Loader-independent startup recovery for DSH Web that detects likely broken plugins, temporarily skips them, and restores only Boot Guard-managed changes.

Complement to official Creator mode: stage, validate, live-mount via ctx.plugin, score, and solidify or roll back in-memory tool-plugin trials.