JointJS-powered interactive playground skills — (1) code map visualizations for library/codebase architecture (supports local codebase analysis), (2) data explorer diagrams for database schemas and entity models (supports local schema files), both on a shared graph-explorer framework — (3) canvas builder for…
Universal channel plugin for Claude Code with 21+ platform adapters. Connect via WebSocket (default) or use built-in adapters for Telegram, Discord, Slack, WhatsApp, Signal, iMessage, IRC, Google Chat, LINE, Feishu, Matrix, Mattermost, MS Teams, and more. Full hook event forwarding, permission relay, and bidirectional.
★not rated 6 5mo agoA
tokens not measured
originalMIT
Automatically selects one of five Claude Code effort levels while preserving claude.ai subscription billing. Learn more at https://www.promptrail.ai/plugins.
★not rated 6 1mo agoA
tokens not measured
originalMIT
Multi-agent orchestration system for software development with human-in-the-loop checkpoints. Implements the QRSPI pipeline: Questions, Research, Structure/Design, Plan, Implement + Review, Pull Request.
★not rated 6 17d agoA
tokens not measured
originalMIT
Summon OpenAI Codex as an adversarial reviewer of specs/plans and branch diffs, then debate it to convergence. Codex is the hard gate; it never commits.
★not rated 6 2mo agoA
tokens not measured
originalMIT
Local-first evidence-based career decision support for Japan job seekers: confirmed facts, conflicts, unknowns, verification, and user-controlled next actions.
★not rated 6
changed 4d agoA
tokens not measured
originalMIT
Claude Code plugin for the Marketing Manager platform — 37 Link Platform MCP tools for strategy, pages, links, analytics, tracking, routing, and deployment on 10x.in. Includes 25+ skills, 7 agent roles, and 5 slash commands.
Audits whether an agent actually did what it was asked. Catches the false 'Done' on Stop: missed subtasks, stubbed/no-op work, false 'tests pass', a method silently dropped in a refactor (dangling reference), and — uniquely — a standing project rule that was in context and overridden anyway. Runs on Stop, pre-commit…
★not rated 6 1mo agoA
tokens not measured
originalMIT
Build apps with Supabase as the backend. Equips AI agents with schema-driven workflows, RPC-first data access, edge functions, auth, RLS, and multi-tenancy.
★not rated 6 2mo agoA
tokens not measured
originalMIT
Your agent's memory, in a repo you own: the tome CLI, skills (capture, query, ingest, retrospect, write-a-plan, pickup-task), a SessionStart hook that points every session at the vault, a scoped Stop sync reminder, a no-build browse frontend (tome serve), and tome init to scaffold a fresh vault.
★not rated 6 1mo agoA
tokens not measured
originalMIT
Loop Engineering portable: bucle autónomo que revisa un proyecto por flujos de ejecución (GitNexus), escribe tests (test-first), arregla lo seguro en worktrees aislados, lo verifica con un evaluador adversarial independiente y abre PRs — nunca auto-mergea. Incluye la skill /forja y 4 subagentes…
★not rated 6 2mo agoA
tokens not measured
originalMIT
Create stunning, animation-rich exploratory visual web pages from text content.
★not rated 6 7mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: