10 плагинов из публичных маркетплейсов Claude Code. Каждый объединяет навыки, слэш-команды, агентов, хуки или MCP server, которые устанавливаются вместе.
Показано 10 плагинов, соответствующих фильтрам.
agent-appCraftOS-dev/Agent-App1
organic-osshalintripathi/organic-os1Отправьте репозиторий с .claude-plugin/marketplace.json, и мы перечислим каждый плагин.
Отправить marketplaceTurn 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.
Disciplined multi-source meta-research for high-stakes questions — the heavyweight alternative to the fast research router. 9-phase pipeline (reframe into falsifiable hypotheses, plan, capability discovery, parallel sub-agent fan-out, score & triangulate, synthesize + adversarial pass, verify, refresh targets). Triangulates every thesis against >=3 independent differently-typed sources; per-source files with verbatim quotes; never fabricates a citation. Auditable, reusable folder + delta-update refresh protocol. Contributed via PR #851.
PreToolUse hook that prevents AI agents from using --no-verify, --no-gpg-sign, and other bypass flags that skip git hooks
Routes each request to one of 27 specialist agent roles, which load only the skills the work needs and verify what they claim.
Review authentication declarations and verify explicit local JWT profiles
Quick smoke test suites to verify critical functionality after deployments
The `/agent-app` launcher command plus the six framework skills (creator, modify, importer, operator, walk-verify, connect) and the CLI conventions. Requires the CLIs `agent-app` and `a2app`, both in one package: `npm i -g agent-app-framework`; from a cloned source tree, `pnpm -r build` then `npm link` in `framework/cli`.
An agentic organic-growth operating system: observe, decide, approve, apply, verify, learn. SEO + AEO/GEO + content + on-page execution with a memory that compounds.
marketingFind and verify current repository/news topics and prepare voice-matched drafts.
Discipline mode (staged planning, receipts, verify-against-source, adversarial review) + plan/kickoff commands + a plan-reviewer agent + an always-on SessionStart discipline injector + a Stop-hook autonomous loop (Layer 1, a deterministic gate) that can arm itself from a committed, content-hash-trusted .claude/tale-mode.json during a kickoff phase + a fail-closed plan-mode auto-approve for provably read-only shell (no more permission-dialog walls during investigation).
productivity
