Claude Code plugins
6 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 6 plugins that match these filters. Clear filters
Context persistence, restoration, and long-running conversation management
Turn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task plan (refusing vague goals with forcing questions), and a JSON-backed loop controller drives execute->verify->close with retry caps, controller-run verification (no verification theater), human escalation on exhausted budgets, and a close gate that refuses while any task is unverified or unwaived. Ships 3 stdlib Python tools, 18 committed per-domain harness manifests + JSON schema, 3 references citing the 2024-2026 agent-harness canon (Anthropic long-running harnesses, verifier's law, SWE-agent, Ralph loop, Cognition), harness-runner agent + /cs-harness command. Use when an agent or subagent should pick up a goal, define its tasks, complete and verify them, and close the loop.
Stop being the switchboard between your AI agents — direct a team. The Workshop puts long-running AI agents (desks) in the same room, on the same work, each with its own memory and history, sharing one workspace so you direct the work instead of relaying it.
The five-skill discipline loop for long-running agent work: freeze a task's scope into a workorder, gate sensory output behind human review, log decisions so they survive a context reset, hand off state when work changes hands, and close out with evidence instead of claims.
productivity
Ten skills forming a documentation chain: AGENTS.md entry point, PRD, technical specs, ADRs, implementation plans, status tracking with crash recovery, a git workflow with evidence-carrying PRs, an independent verification gate, gated documentation maintenance, and a brownfield onboarding on-ramp — plus a bundled verifier agent and router + run-loop drivers shipped as both commands and skills (works in Claude Code, GitHub Copilot CLI, and Codex). The harness layer for long-running, loop-driven development.
workflows
Acumatica ERP assistant: REST integration development against the contract-based REST API from a bundled extraction of Acumatica's Integration Development Guide (2026 R2) — sign-in and OAuth 2.0/OIDC, endpoint and contract versions, JSON record shape, query parameters per contract version, CRUD, actions and long-running operations, custom fields, files, license limits, push notifications and webhooks, with a catalogue of 187 documented example requests, and exact entity, field and action names from a snapshot of the Default/25.200.001 contract (2025 R2); OData data access — DAC-based and generic-inquiry-based OData v4 reads (URLs, auth and licence, $filter/$expand, deleted-record tracking, CORS, Excel and Power BI) from the Reporting Tools Guide (2026 R2), with a DAC $metadata snapshot of a clean 2026 R2 instance for exact DAC, field and navigation names. More capabilities to follow.
