Plugins

Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.

Quantitative R&D toolkit for DeepSeek Harness — 46 tools across six domains covering market data, indicators, factor evaluation, walk-forward ML validation, risk, options, bonds and fund simulation, with an end-to-end research pipeline.

Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.

Evaluierungs-Harness für DSH-Plugins: YAML-Fälle steuern echte Headless-Agent-Läufe, prüfen Tool-Aufrufe, Argumente, Ergebnisse und Token-Nutzung, mit einem Baseline-Gate gegen CI-Regressionen.

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

PR evaluation and improvement consultant: assesses PR success probability based on historical anti-patterns and success patterns, with one-click scoring and actionable suggestions.

Evidence-first self-evolution controller: bounded Cordis candidate generation, one-shot real-Loader admission, Harbor evaluation, and a crash-resumable journaled lineage.

Ein modell-natives Meta-Agent-Plugin für DeepSeek Harness: Das Modell synthetisiert zur Laufzeit aufgabenspezifische Workflows aus fünf agentischen Workflow-Mustern (Prompt Chaining, parallele Worker, Router, Supervisor, Evaluationsschleife) und koordiniert Tools und Subagent

Check which DeepSeek Harness plugins actually loaded, and look up public evaluation boards on trapstreet.run

Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.

CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.

Evaluationsplattform für Agenten: Benchmark-YAML, Headless-Ausführungsorchestrierung, Trace-basierte Metriken und Laufberichte