All Plugins

AgentTeams multi-agent teams.

Installs a dedicated AI novel-writing preset and workbench: revisioned local project assets, a compact side drawer, and native approval-gated single-file changes.

UltraCode-style multi-agent orchestration: a generatable, savable, governable, observable, resumable workflow layer.

Scheduled coding runs in fresh agent sessions with auditable history.

Skill-driven harness/loop engineering workflow agent plugin.

Persistent multi-model squads configured in Settings and selected in the Composer, with per-member model/tool policies; the main Agent dynamically plans each send as a bounded DAG with bounded reviewer/repair loops, while Run Center tracks retries and per-member tokens from official Harness usage events.

Local SQLite taskboard as a native overlay page: projects, tasks, comments, relations, attachments and workflow automation, with backlog → todo → in_progress → in_review → done statuses, `taskboard_*` Agent tools that can only submit work to in_review, a headless JSON CLI and a packaged skill.

Adaptive deep-research orchestrator built on the official workflow engine.

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

Condition-driven wakeup: durable file/command/http/process/webhook watches that wake the agent.

Research agent suite: long-horizon goal control with auditable evidence chains, cron scheduling, multi-agent expert teams, self-evolving research memory (FTS5 + RRF recall), project workspaces, and a custom workspace UI.

Plan review with anchored annotations and structured feedback back to the agent.

Embedded task management engine: decision-point protocol, idea capture wall, Linear-style issue store.

Ceelog/dsh-plugins#dsh-plugin-scheduled-tasks: Per-project scheduled prompts run as fresh headless agent sessions, with one-time, interval, and cron schedules plus durable run history. Ceelog/dsh-plugins#dsh-plugin-setting-mcp: Manage MCP servers from the Web settings panel: view, add, edit, remove, enable or disable them, with hot reload on save.

Coordinate independent DSH Sessions and provider-backed members without merging their histories, using persistent native Rooms with identity-bound leading `@` mentions, direct delivery, broadcasts, and leader-scoped controls.

Runtime requirement drift guard that keeps long-running DSH agents aligned with the user's approved goal, constraints, and decisions.

Engineering-discipline guard: requirements grill before the first edit, red/green test-evidence gates, forked adversary review, and a delivery report with a per-dimension verification workflow.

Two-level model circuit breaker with failover: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback.

Evidence-first operating kit: six read-only tools (capability catalog, staged workflow plans, packaged skill reader, bounded local memory search, repository release audit, release checklist) and five packaged skills - plans and audits, never remote writes.

Adds specification artifacts, skills, commands, goal-backed implementation, and task-progress context.