#hooks

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.

A discipline plugin for Claude Code + OpenAI Codex — plan first, verify against the real code, receipts on every decision, independent adversarial review, and a self-armed loop that keeps going until a real check passes. Built by Fable to make any Claude work like a careful senior engineer.

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done claims, patch sprawl, and tool loops in your Claude Code session.

Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents

"Done" means nothing — a menhera-style completion gate for Claude Code that blocks empty completion claims until tests actually ran green and no TODOs are left behind.

Umbrella for the LLM Dark Patterns Hooks suite — single-purpose Claude Code Stop hooks that suppress sycophancy, paternalism, false-success, permission-loops, training-cutoff confidence at the textual boundary.

The hook control center for AI coding agents

Codex App templates for long autonomous project runs with reviewer agents, learning loops, and narrow safety hooks.

Bridge Claude Code → Grok Build: shared rules/skills, hook adapter hard-gates, optional memory mirror

Turns working with Claude Code into a system that finishes goals: what you teach, verify, and solve once stays in use — session after session.

Your Claude Code session sees the 5-hour limit coming, checkpoints its work, and resumes itself when the window resets. Hook-based, stdlib-only, macOS/Linux/Windows.

Compile CLAUDE.md rules into trigger-bound hooks — a Claude Code plugin that delivers each rule at the moment it matters.

Deterministic fake of the claude and codex CLIs. Test hooks and orchestrator integrations locally and in CI without an API key.

AI 코딩 비서(Claude·Codex·Gemini)가 확인도 안 하고 '다 됐어요' 하는 걸 자동으로 막아주는 품질 안전장치 — 비개발자·바이브코더를 위한 한국어 우선 하네스.

Claude Code plugin that timestamps every message, shows how long each turn took, and tells Claude when your prompt was sent.

A governance harness for Claude Code with blocking enforcement hooks, routed standards, and multi-project trackers with resume points. Free, MIT.

AI Content Guard 2026: Adversarial Fact-Check Gate for Error-Free Code & Copy

Nokori (残り) — behavioral memory layer for Claude Code and Cursor. Turns your corrections into rules that come back when it counts. 经验留下的痕迹，比记忆更深。

Evidence router & policy engine for coding agents — enforces source choice and proof-of-use through Claude Code hooks, including routes to MCP tools. Local-first; no LLM in the hook loop.

🚀 Master Claude Code Skills 2026: AI-Powered PR Reviews & Security Audits

JM's Claude Code workflow as a redistributable plugin: rules, hooks, agents, commands, and tweakcc patches packaged for less-advanced CC users.

Music while Claude works. Silence means it's your move. Fades Spotify up while your Claude Code sessions are busy, pauses the moment one needs you — and logs where the day went.

Voice, desktop & webhook notifications for CLI coding agents (Claude Code, Codex, Gemini, Copilot, Cursor & more) — calls out the moment your agent finishes or needs you.

Commit-reveal + timing-batching privacy primitive for AI agent intents on Arbitrum. Not a ZK system - see README.

Installer for Claude Code per-model commands, agents and skills

⚔️ Turn your real Claude Code session into a turn-based RPG — a statusline HUD + PixiJS arena where your goals are bosses, your todos are minions, and your tokens are your resource. Fight and win, with zero impact on the session.

Telegram reply-enforcement hooks for Claude Code — never get a silent terminal-only answer on your phone again.

Reusable guard-rail hooks for Claude Code (cost cap, destructive-op block, config protection, memory/learning)

Jarvis for Claude Code — spoken summaries, milestone sounds, and failure cues so you know by ear what every terminal tab just did (macOS)

Готовая система агентов / хуков / Obsidian-vault для Claude Code на macOS. Smart installer сканирует твои проекты и собирает рабочую среду под ключ. 23 агента, 22 хука, 4-tier memory, VoiceInk free build.

An installable Claude Code setup: self-healing TypeScript hook, context-surviving PreCompact snapshot, statusline, typed memory, and a safe component installer.

Deploy a Full AI Engineering Team 2026 - Claude 12-Agent System with Automated Quality Hooks

A shareable kit of Claude Code assets — skills, agents, hooks, and rules.

Practice project migrating prose-based AI enforcement rules into real, blocking Claude Code hooks — covers PreToolUse guards, Stop-hook content verification, LibreOffice hang prevention, and robust pass/fail parsing, each with a working test suite.

Reliable click-to-focus desktop notifications for Claude Code in Apple Terminal — clicking jumps to the exact tab (fixes terminal-notifier's dead click handling on modern macOS)

Battle-tested Claude Code project template: self-protecting hook suite w/ CI-run test battery, secret scanning, deploy/backup workflow templates, and the process docs for safe agentic development. MIT.

Ten Claude Code skills that fix bugs Anthropic closed as 'not planned'.

Claude Code 후크(Stop/Notification)를 Slack·Telegram·Discord로 중계하는 경량 FastAPI 릴레이

Connects local memory sources to coding-agent lifecycle hooks: remind, clue, or local search with selected hits. No network requests, no host config changes.