Havuz

FailproofAI, farklı AI agent harness’lerindeki çalıştırmaları izleyen ve tehlikeli tool çağrılarını yürütülmeden önce policy ile engelleyebilen bir araçtır.

Neden yükseliyor · 175 günlük bir repo için 5.166 yıldız ve son 28 günde 84 commit ile 8 farklı yazar, hem belirgin ilgiye hem de yakın dönem geliştirme faaliyetine işaret ediyor. Çok sayıda harness için ortak observability ve enforcement sunma iddiası, agent araçlarının çeşitlendiği dönemde dikkat çekici; yıldızlar tek başına benimseme veya kalite kanıtı değil.

Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky

Full-lifecycle wiring between Claude Code and the Clawd on Desk pet — all 15 hook events, with permission prompts answered straight from the

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injectio

Profile-based coding runtime for Claude Code and Codex. Lean core; opt-in quality, context, memory, orchestration and dashboard.

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

The one place for the skills, keys and memory of every agent you use. Formerly OMNI.

A free Agent Skill for writing short-form hooks, scripts, and carousels for TikTok, Reels, and YouTube Shorts.

aisync — AGENTS.md, but for live coordination between AI tools. One standup for all your AI coding tools: shared rules, a hash-chained journ

Cost control for long Claude Code sessions on Windows, macOS and Linux: tiered context ceilings, a blocking handoff gate, and effort gears.

An engineering team in a box for Claude Code — 12 specialized agents, 15 automation hooks, and the P7/P9/P10 methodology.

Stop hooks that stop AI coding agents (Claude Code, Codex) from claiming "done" without proof. A Lean quality system: every defect becomes a

Track the carbon footprint of your Claude Code sessions, in the terminal and the Claude desktop app

Builds up to a goal in a field you have no expertise in: splits it into the foundations that goal actually needs, mobilizes what you already

AGENTS.md contract for AI coding agents + zero-dependency linter + SessionStart hook. Works with Claude Code, Codex, Cursor, Copilot.

Blocks Claude Code and Codex from ending a turn when code changed and no test passed after the last change.

Auto AI improver. Cost and token burn reducer, turn saver, and focus keeper for Claude Code, Codex, Copilot, Gemini, and more: surgical read

Claude Code mod: Clawd acts out what Claude is doing, above the prompt

Run many Claude Code sessions on one machine safely: no killed dev servers, port clashes, RAM or disk freezes, or mixed-up commits. Zero-dep

Antigravity 破甲工程：二进制提示词补丁 / 规则技能 / 生命周期钩子 / IDE 等长补丁 / 模型后端改道

Local-first, evidence-aware memory and project continuity for AI coding agents. Checkpoints, context packs and auditable receipts without te

The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via

Claude Code plugin that plays a Mr. Meeseeks voice line whenever Claude is waiting for you.

Your AI coding assistant can finally see what you're doing. Local-first screen context for Claude Code, Codex, Gemini CLI and Muse Code.

DeepSeek Harness port of Claude Code Game Studios (CCGS v1.1.2, MIT) — one-package install: hook bridge (9 events), studio status line, self

Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses

Execution posture harness for Claude Code. Your coding agent stops one step early; Castra is the step.

Deja de usar Claude Code como venía en la caja. Semáforo de contexto, modo conciso, 4 hooks que bloquean comandos destructivos y secretos, e

Контроль качества 1С-разработки для Claude Code: стандарты, принципы ООП и паттерны, XML метаданных, блокирующие гейты и проверяемый след пр

Keep Claude Fable 5 in the chair all day without draining your usage limit — token-frugal multi-agent orchestration plugin for Claude Code:

Local traffic visibility and privacy controls for coding agents. See what Claude Code, Codex and Copilot send to the model; mask secrets and

Show local time on every Claude Code message, and let Claude know when each prompt was sent. Zero-config plugin, cross-OS, graceful degradat

Run multiple Claude Code accounts as one. Auto-switches on rate limits and resumes your session no lost context, no logout dance.

Spotify's 90% Claude Code routing setup, rebuilt for plain Claude Code and measured on 4 real tasks. A cheap model does the reading and the

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any sc

Let TypeSafe Jev decide whether a message you send mid-turn should steer, queue, or interrupt your coding agent. Claude Code plugin; Codex C

Approve Claude Code from your Mac's notch. A native SwiftUI menu-bar app that surfaces Claude Code permission prompts, questions, cost and c

AI agent orchestration kit for Windows, Linux/MacOS with Codex skills, hooks, routing rules and profiles for Claude, OpenCode, Cursor, Gemin

The Claude Code harness I run every day, published under this name since day one and now the same repository as ucsandman/Agnostic-AI: guard

Hook-driven multi-agent CLI — one prompt to specs, code, tests, and a shipped release.

A battle-tested, framework-agnostic reference architecture for Claude Code. Beginner-friendly with graduated adoption (minimal / standard /

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deter

When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deeds; fakes blocked, not warned.

Your AI coding harness, ported to every client you use. Capture Claude Code (or Codex) rules, hooks, skills, subagents, commands and MCP ser

Audits the .claude/ ecosystem — skills, commands, hooks, agents, settings, plugins, memory — for dead references, weak triggers, token bloat

Project continuity for Claude Code and Codex: a roadmap beside your code, grounded handoffs, and clear task status.

Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).

Linux, macOS ve Windows için kaynaklı ikinci beyin. Claude Code, Codex ve Antigravity adaptörleri; yerel Markdown kasa, ayrı hafıza inceleme

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done cla