hooks

Switchable output styles for Codex and Claude Code, enforced by hooks and switched from the chat with ::

Agent Plugins、Claude Code、Codex向けの品質支援プラグイン。コードと文書を扱う作業、計画やバグ調査の指針を示し、フックで入力と操作を確かめる。

Claude Code and Codex hook: before a GitHub issue write (gh issue create/edit/close/comment, gh api on issues, GitHub…

Shared AGENTS.md standards (via andes-init), PRD generation, technical writing with CHANGELOG ownership, the Microsoft…

Behavioral drift detection for autonomous AI agents.

Automatically prefix Codex task titles with a model-specific colour marker.

Intelligent permission gate for Claude Code shell, file, search, Skill, and MCP tool surfaces. AST-parses Bash…

Stateful integrity verification for every Codex tool call: argument classification, output scanning, sensitive-data…

Enterprise React 19 migration toolkit with specialized agents and skills for upgrading React 18 codebases to React 19.…

Queue a prompt now; it is sent when your rate-limit window reopens.

Enterprise React 19 migration toolkit with specialized agents and skills for upgrading React 18 codebases to React 19.…

Scaffold AI-agent config for a repo: instructions, guard hooks, frontend/backend skills, git-reconciler sub-agent,…

CLAUDE.md または Codex AGENTS.md を分析し、必須指示・階層指示・スキル・既存チェックを適切に整理する。ホスト固有の paths とツールを混同しない。

Finds secrets and personal data locally, in your prompts and in the tool results the agent reads, and tells you what it…

Enterprise React 19 migration toolkit with specialized agents and skills for upgrading React 18 codebases to React 19.…

Receipt-bound completion rail for Claude Code: SessionStart injects the completion contract, Stop runs the cached fast…

Offline installer for the DeepSeek V4 Flash custom subagent for Codex

Developer plugin for Heyra engineers, installable in Claude Code, GitHub Copilot CLI, VS Code and the Copilot cloud…

Local test plugin for validating Codex-compatible hook behavior in Owls.

AnchorMind long-term memory hooks: session start memory injection and session end reflection

Portable AI agent harness — curated review/build/test agents, secret-hardening + worktree + plan-gate hooks, and…

Asks TypeSafe's Jev which bulky tool results the session still needs, and replaces the rest with a bounded head plus a…

Golden Path: help people express business intent as reviewable engineering acceptance, then connect it to the controls…

Prompt-injection and dangerous-action guard for coding agents, powered by Jev.

AGT governance hooks for the OpenAI Codex CLI

A minimal Plugin that demonstrates one Skill and one experimental io.minimax.mcode Hook entry for the Agent Plugins 1.0…

Checks the infrastructure commands Copilot wants to run (kubectl, terraform/tofu, aws/az/gcloud, helm, argocd, git,…

React Router harness tools, skills, and agent customizations for Codebridge workflows.

Trust over speed for coding agents — the router (AGENTS.md + WORKFLOW.md), 11 discipline skills, and the mechanical…

Enterprise React 19 migration toolkit with specialized agents and skills for upgrading React 18 codebases to React 19.…

Run a detected project test suite when a Copilot CLI session ends.

損害控制 (Damage Control) 安全系統 - 透過 PreToolUse 鉤子封鎖危險指令並保護敏感檔案

Road signs for coding agents: a PreToolUse hook that reports when the file you're about to touch is in a git checkout…

Agent Plugins package with a skill, MCP server, and hooknostic-compiled lifecycle hooks

Token plane: PreToolUse hooks that keep whole-file reads of large files and unbounded repo-wide searches out of the…

Onboard to any codebase in minutes: an onboarding-guide agent, a codebase-tour skill that writes ONBOARDING.md, a…

Compaction that continues without a break: a handoff card written before the context is compacted, a pointer to it…

A local desk note that helps Codex resume the right job after context compaction.

React skills for scaffolding, configuring, and hardening React and React Native apps in TypeScript and JavaScript.

Universal agent plugin for Google developer documentation style. Skills, a custom output formatter, and hooks for…

Portable Agent Skills for AI-harness diagnosis, AGENTS.md guidance, prompt design, IDE-native agents, hooks, slash…

Blocks unsafe git subtree invocations: URL fetch, missing --squash, missing -S/--gpg-sign, and subtree push.

Harness for spec-driven development: a deterministic triage decides how much process each change needs, hooks enforce…

Personal agent plugins

Geist tools and workflows for GitHub Copilot and OpenAI Codex.

Desktop notifications for agent lifecycle events on WSL.

Baseline maintainer dev flow as config-driven skills: create-pr (opens PRs only after running the repo's…

CLAUDE.md / .claude/rules または Codex AGENTS.md / .agents/skills を監査する。既存リマインダー hooks は Claude 用として保持。

Blocks a Claude Code turn when a local Little Canary server rejects the submitted prompt. Also installs on Codex CLI,…

A minimal Plugin that demonstrates one Skill and one inline Hook entry under the mcode 0.4.0+ plugin format. The…

Recoverable deletion for coding agents: move files to trash, list them, and restore them with agent-trash.

Security guardrails for AI agents: blocks destructive commands and secret access with hooks, scans for secrets and…

Lints every agent edit with oxlint (PostToolUse) and blocks edits that weaken the oxlint config (PreToolUse).

Agent Plugin that provides Kiro agent orchestration via delegation.

Windows 桌面灵动岛 (Dynamic Island) 状态窗口：让 mcode agent 把工作状态（idle/thinking/working/waiting/done/error）实时推送到屏幕顶部悬浮 pill，agent…

Blocks permanent-delete shell commands in Claude Code and redirects agents to a recoverable trash workflow.

Receipt-bound completion rail for Claude Code: SessionStart injects the completion contract, Stop runs the cached fast…