Plugins

Stable, editable PPTX generation for AI agents — semantic IR in, native DrawingML out

Claude-Code-style lifecycle hooks: configured shell commands run before/after model tool calls with a JSON payload on stdin; a non-zero pre-tool exit blocks the call.

Bounded, privacy-safe local scanner for Codex, Claude Code, WorkBuddy, and CodeBuddy metadata: atomically aggregates keyed evidence and deterministically advises built-in DSH presets and optional capabilities—without content retention, network access, or preset mutation.

Long-term memory for DeepSeek Harness in Claude Code's format: private, overlay, or shared with Claude Code, with provenance on every file

Task-to-skill pairing meta-skill with a laziness ladder for minimal loading, a user-editable routing table, and a quarantine, SkillSpector scan, human-approval install flow.

Security-audit facts AI coding agents cannot compute, plus a verdict gate: euthyna history attributes deleted lines to commits and flags those from security fixes (--origins finds the first introducer), euthyna coverage reports which changed symbols no test ever invoked, and euthyna gate checks each finding against six gates, downgrading any without evidence to an observation.

Biomedical research plugin for DeepSeek Harness (dsh): biomcp MCP server tools, scientific plotting skills, and deep-research subagent

Canonical project memory for DeepSeek Harness: one governing article per asset, an append-only journal beneath it.

Community skill marketplace for DeepSeek Harness: browse, search, and one-click install skills from awesome-skills-cn and the wider Claude Code / OpenClaw skill ecosystem.

Local-first HTML review and annotation workspace for coding agents: opens an isolated copy of a file in a browser editor, collects text edits, format changes and element/area comments, and returns a durable handoff the agent can claim and resolve.

“What should we build next?” There’s a skill for that.

CodeAct agent loop for the DeepSeek Harness: a persistent IPython session as the model's action space, with harness tools bridged in as a virtual `__dsh__.tools` module.

Agent-agnostic skill that turns task input files into reusable structural briefs and a per-task searchable index (OpenAI Codex, Claude Code, DeepSeek Harness)

Compare DeepSeek Harness, Codex, and Claude Code instruction surfaces for the same workspace.

Branch-role guard for AI coding agents: configurable integration/preview/production/archive roles, blocking direct push, force-push and delete on protected branches and agent merges into production/archive.

DSH plugin: auto-import local AI CLI conversations (Claude Code, Codex CLI, Cursor Agent) as real DSH sessions

Scans MCP servers configured in Claude Code, Codex and CodeBuddy and probes real connectivity via stdio and streamable-http initialize handshakes, with enable/disable toggles and a /mcp control panel.

Subagent delegation provider that runs any Claude-compatible CLI binary pointed at by a configurable executablePath field.

Discovers Codex and Claude project directories and registers them as shared DeepSeek Harness workspaces.

Exposes the DSH dynamic-Cordis toolset to Claude Code over MCP (streamable HTTP on the existing web port, no new listener): ten tools to list, inspect, define, run, stop and permanently remove dynamic plugins in a live DSH session, with the same approval flow the GUI uses for packages that ship a client half. Bearer auth is mandatory — the token is configured on a DSH settings page, the endpoint answers 503 rather than serve without one, accepts loopback only and never emits CORS headers.

The task-center plugin set for DeepSeek Harness in one package: task ledger, model tools, human commands, wake patrol, quota-resume guard, idle-session mining, the reaper, scheduled sends, and the web kanban.

DeepSeek Harness (DSH) plugin that delegates coding tasks to the Claude Code and Codex agent CLIs and streams the whole run live — autonomous control, multi-account, automatic install, git worktrees, and any Anthropic-compatible endpoint.

Honesty guardrails on the tool pipeline: blocks a coding agent from weakening tests, swallowing errors, stubbing type checks, or deleting tests through the shell — nine deterministic hooks, each backed by a planted-failure test proving the guard can fail.

Run Claude Code and Codex as live terminal panes beside dsh: a split view in the web UI, buttons to seat them, and tools that let the dsh agent hand them work and read their screens.