All Plugins

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

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

Codex-style auto-review permission mode: adds an auto-review preset that auto-approves safe sandbox escalations, asks on risky or ambiguous ones, and rejects critical unconfirmed operations.

Automatically fills in reasoning-effort levels for models from unofficial (custom) providers, with data sourced from models.dev.

Connect a sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and global vision/image tools.

Reads assistant replies aloud via Fish Audio API only (bring your own key): per-message read-aloud, auto-read toggle, and a settings page for model, voice reference_id, encrypted API key, and proxy.

Codex Appshots for DSH: capture the frontmost active window via global shortcut and seamlessly mount it into the composer for agent queries.

Headless-browser verification tools so the agent opens the page it just built, reads the rendered DOM and computed styles, checks the console, and screenshots the result; ships a frontend-verify skill.

Browser operation by accessibility refs: navigate, snapshot the page as a ref tree, act on elements, and wait for conditions; the origin policy follows the session approval stance and is enforced by request interception.

RLM Mode for DeepSeek Harness (dsh): one persistent Python kernel per agent session — schema-driven tools.* bindings, sub-agents, harness, and snapshots.

Verifies that Cordis-managed runtime resources return to baseline after isolated plugin teardown, with deterministic cleanup receipts.

Track human decisions for related DSH session branches: keep, discard, or follow up with reasons, labels, and external links.

Adversarial code review — parallel finders inspect a diff through separate lenses (correctness, lifecycle, contract, security), then each finding goes to independent verifiers tasked with refuting it, and one refutation drops it.

DSH project scaffold preset: strict 5-phase init runbook, engineering standards and six runnable starter templates (node-ts / react-vite / python / go / spring-boot / monorepo).

Domi-grade git worktree isolation and delivery: permanent worktrees under .dsh-worktrees, ready-for-review / apply / finish / discard lifecycle with conflict handling and safe cleanup (ported from Domi's production system).

Reuse-first capability evolution for agents: resolve existing tools and skills, discover and review exact-commit DSH plugins, install with one-time approval, verify real tool round trips, and minimally adapt partial matches instead of rebuilding from scratch.

Brings your existing Claude / ChatGPT history into DSH: instant zero-token import of the memories.json inside a Claude export, local Claude Code transcripts with no export needed, and conversations distilled through the model you already configured in DSH. Every memory carries verbatim evidence checked against the source by code — a paraphrase is dropped and counted, and evidence found only in the assistant turns is always routed to review rather than stored.

Evidence-backed Skill self-evolution for DeepSeek Harness: redacted trajectory learning, quarantined proposals, arena validation, canary monitoring, automatic rollback.

Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editing.

PostgreSQL-backed durable memory for DSH agents: MCP memory tools plus a Web panel for reviewing memories and candidates.