Model-facing `generate_image` tool for text-only models: the model asks for a picture in natural language, Gemini draws it via the Antigravity CLI, the image is saved to a configurable output director

Installs an Orchestrator agent preset that plans and dispatches to model-pinned specialist subagents (explorer, oracle, librarian, designer, fixer, council), with named model profiles switched via an

Self-media workbench plugin: 8-tab dashboard (daily brief, narrative lines, topics, drafts, knowledge-card distill review, sources, publish, advice) with hard guards (48h window, event dedup, card/lin

Whole-report verification for scientific reports: per-claim checks against Crossref, PubMed (retraction scan), ClinicalTrials.gov, UniProtKB, GEO/SRA and PatentsView, URL accessibility and title agree

Minimal prompt x Web PTC capabilities: one-line persona, run_code SDK, subagents, Ralph, web search/fetch, and Windows Git Bash; the general-purpose workflow tool stays hidden.

Plan-and-execute orchestration over ReactLoopAgent — turns a goal into reviewable steps with a web UI plan card.

Per-workspace project kanban board: nine kanban_* model tools for agent-driven planning plus a browser board UI, with disk persistence, undo, templates, and archiving.

Automatically sends "continue" to recover from RATE_LIMIT (429) and QUOTA (insufficient_quota) errors. Per-session consecutive-failure counter (default 20, configurable 1-100), a toolbar on/off switch

Installs two selectable Agent Presets: a shell-restricted general-purpose agent and a repository-focused coding agent.

A DeepSeek Harness Web plugin that runs a user-defined command after the web profile has started successfully.

Auto Mode for DSH: a flash-model router that auto-picks the best agent preset (standard/code/minimal/cordis) for each new session and executes immediately, no confirmation.

Role-based AI swarms for DeepSeek Harness: an architect plans, parallel builders execute, reviewers gate quality, and an integrator ships. Per-role model pinning with fallback chains, review loops, ev

Verifiable issue-to-PR delivery chain: an 11-stage pipeline (analysis, search, code understanding, hypothesis, planning, implementation, patch ledger, tests, review, failure classification, PR build)

Pair a second model that passively reviews each turn and injects notes.

Orchestrates durable multi-agent teams from one DSH session: a captain spawns member subagents, drives a dependency-aware task DAG with quality gates, and coordinates through persistent mailboxes, wit

Cordis-native, evidence-driven full-stack engineering workflow: inspect-first planning, explicit verification evidence, and approval-aware gating for sensitive operations.

Preset workflow template library: 12 reusable orchestration script templates with wf_template_list / wf_template_search / wf_template_run / wf_template_validate tools and static template validation.

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→co

Synchronizes DSH profiles and local plugin source archives through WebDAV and S3-compatible storage, with encrypted snapshots, conflict-aware recovery, and explicit self-updates.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics,

OMC-style multi-agent orchestration for DeepSeek Harness: 29 omd-* skills and 12 /omd-* slash commands over the plan-execute-review-verify pipeline and team/autopilot/ralph modes.

A DeepSeek Harness plugin that periodically detects added, modified, and deleted files in a workspace and reports the changes.

Six-stage WeChat Official Account content-publishing workflow with quality-gate tools and a bundled skill.

by weixshaw

Task Runner 任务拆解模式：主代理拆解任务、子代理（默认本地模型）并行执行再综合结果，并发/模型可按机器配置。Decompose-and-dispatch agent preset for DeepSeek Harness.