ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A workflow for investigating GitHub Code Scanning alerts, including CodeQL warnings, which are automated findings about possible security problems in source code.
96 tagged plugin-system, measured the same way as everything else here.
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A workflow for investigating GitHub Code Scanning alerts, including CodeQL warnings, which are automated findings about possible security problems in source code.
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A Git commit workflow, where a commit is a saved checkpoint of code changes. It also checks copyright years and updates the related task status.
ModelEngine-Group/fit-framework
Skill Claude CodeCodex
A release-note generator that collects changes from GitHub pull requests, commits, and issues, then groups them into a project-formatted summary.
ModelEngine-Group/fit-framework
Command Claude Code
A Git commit command that reviews local changes, checks files before editing, and creates a commit with a suitable message. It can also hand off to commands that push changes and open a pull request.
ModelEngine-Group/fit-framework
Command Claude Code
A command that gathers pull requests, commits, and issues to produce structured release notes for a specified version, with an option to create a draft GitHub release.
ModelEngine-Group/fit-framework
Settings file Claude Code
Agent settings declaring 37 allowed tools.
ModelEngine-Group/fit-framework
Command Codex
A Git commit workflow command that guides an agent through reviewing changes, checking copyright years, writing a commit message, and creating the commit.
Skill Claude CodeCodex
Automates interactions for iOS simulators/devices and Android emulators/devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, or extracting UI info on mobile targets.
Skill Claude CodeCodex
Run a fixed OTA regression flow for examples/v0.85.0 with agent-device. Use when the caller wants a built-in end-to-end scenario instead of defining one manually: deploy a known-good OTA bundle, verify a visible UI change plus the deployed bundleId, then deploy an intentionally crashing OTA bundle and verify rollback…
Skill Claude CodeCodex
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…
Instructions file CodexOpenCode
AGENTS.md instructions for gronxb/hot-updater, covering repository guidelines, project structure & modules, build, test, and dev commands, skill usage and coding style & naming.
Instructions file
Claude Code instructions for gronxb/hot-updater, covering claude.md, project overview, key architecture, plugin system and core packages.
Skill Claude CodeCodex
A workflow for generating a daily work report.
Instructions file CodexOpenCode
A set of instructions for BokeBox covering agent work practices, required open-source attribution and licensing, prohibited actions, and documentation updates.
Plugin Claude Code
Agentic loop çekirdeği: append-only log, deterministik riskli-komut gate'i, confidence eşik makinesi (0.7/0.85 kodda sabit), critic zorunluluğu, review kuyruğu, kill-criteria, echo/critic ajanları, /start-project skill'i (PRD ingestion + drift-detection çıpası) ve main-edit dedektörü (disiplin dışı kod düzenlemesini…
Agent
Diğer ajanların çıktısını bağımsız olarak denetler. Mantık hatası, tutarsızlık, doğrulanmamış varsayım arar. Kod yazmaz, sadece değerlendirir.
Hook
Runs before the agent uses a tool for Bash, Edit, Write, NotebookEdit, Task and Agent tool calls, running node (2 commands). From boranesn/agentic-base.
Hook
Runs after a tool call finishes for Edit, Write, Bash, Edit, Write, NotebookEdit, Task and Agent tool calls, running node (3 commands). From boranesn/agentic-base.
Hook
Runs when a subagent finishes, running node. From boranesn/agentic-base.
Skill Claude CodeCodex
Bir PRD (ürün gereksinim dokümanı) dosyasını okuyup projeyi agentic-base standardına göre kurar. Hedef/kapsam özetini CLAUDE.md'ye yazar (drift-detection çıpası), gerekli rolleri belirler ve KULLANICI ONAYIYLA ilgili plugin'leri önerir. Kullanıcı "projeyi PRD ile kur", "start-project", "bu PRD'den başla" dediğinde…
Agent
Veritabanı görevlerini üstlenir. Şema tasarımı, migration, sorgu yazımı/optimizasyonu, indeksleme, veri bütünlüğü.
Agent
LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.
Plugin Claude Code
Büyüme rol ajanları: marketing-agent, sales-agent, data-research-agent. Deterministik kaynak-doğrulama (kaynaksız sayısal iddia bitirmeyi engeller) + outbound-send gate'i (dış dünyaya gönderim/yayın komutları insan onayına düşer; imza temellidir, sızdırmazlık garantisi değildir).
MCP server Claude CodeCodexCursor
MCP server "aix-mcp-server" as configured in easyzoom/aix-mcp-server. Runs locally from the aix-mcp-server npm package.
At most 3 mods per repository are shown here — the rest are on their repository pages: