Havuz

See which external pull requests need context before code review. Deterministic, no login, no AI.

8 character-driven AI coding agent skills for Codex: debugging, code review, regression testing, and release checks. Weird, but employed. In

Nine quality-canary skills for AI coding agents - code health, world-class rule completeness, grounding, supply chain, resilience, drift & m

A review desk for your coding agent's output.

Persistent coding intelligence for Codex — project-aware context, adaptive reasoning, scoped changes, and risk-aware verification.

Six Claude Code skills + an unattended build loop, each measured with and without the plugin. 19/19 evals passing.

Local AI security reviews with evidence, severity, and a review UI.

Portable skills for coding agents — self-contained Markdown procedures that run the same under Claude Code, Codex, or any host that reads th

A shared record for AI agents: decisions, completed work, and commitments, with sources. Git-native engineering memory and a self-hosted sta

Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. j

Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper

Code navigator for the terminal: find your way around a project and review the code agents write. Go to definition and usages without a lang

Reads your Terraform plan and Kubernetes changes and posts a plain-English risk summary on every pull request, blocking the dangerous ones

The Council: shared engineering and domain guidance for Claude Code and Codex. On-demand skills, specialist reviews, runtime-specific hooks,

Multi-model review gate for AI coding agents: other vendors' models review the plan before it is built and the diff after, over MCP. Native-

Pi extension that brings Fallow codebase intelligence into Pi as an agent tool and slash command.

A code reviewer that reports only what it can prove: a test that shows the bug, or the data that confirms the risk. Open source, built by a

Practice real coding work in the AI agent era: task challenges and AI PR review drills.

Focused Agent Skills for complete Flutter and Dart app delivery, based on real-world projects.

Local-first repository context for coding agents: codegraph, cited project knowledge, change impact, and evidence-backed workflows.

Zeeq is an agent knowledge layer that surfaces telemetry that let's teams build better software with AI

Run a team of AI coding agents, such as Claude Code and Codex, on one project. They hand work to each other and review it across AI companie

Turn one ZCode conversation into a restartable multi-agent workflow with persistent memory, isolated coding agents, real-result checks, and

AI coding agent harness. Five modes: practice to playoffs. Stop your AI from over-engineering. Code like a man. Elbow out bloat. Score clean

Broccoli turns Linear tickets into shipped PRs — powered by Claude and Codex, running on your own Google Cloud or Blaxel containers.

Cheaper and better Greptile alternative runs on your own github actions.

Open-source mission control for coding agents. Run cross-vendor workers in isolated worktrees, audit every submission, and revert an entire

AI-powered CLI for reviewing GitHub pull requests, detecting potential bugs, security risks, regressions, and missing tests, with structured

Let your AI Agent review your iOS/Android apps for appstore policy & security bugs with ipaShip's web app, cli, mcp or claude-skill with sa

Agentic code review with structural graph intelligence — PR gate + branch stewardship. Self-hosted. Apache-2.0.

A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run. Plus vision and BlockRun's full model cat

The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of

Simple Reviewer: a Codex skill for AI-assisted coding and Vibe Coding. Explain code, visualize workflows, and verify goals with evidence. |

Click any React UI element, jump to its exact JSX/TSX source, inspect proven API data flow, and prepare reviewable AI patches. Local-first a

Codex-native, spec-driven AI Agent workflow with Claude Code compatibility, independent review, QA, fixes, and refactors.

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit)

Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, own

Free, AI PR reviewer that runs entirely in GitHub Actions. No hosting required.

Local AI PR workbench — Claude/Codex review in isolated git worktrees, human-gated GitHub comments

Turn a security or performance exposure into a reviewable decision

Verifiable multi-agent patch evaluation infrastructure

Opt-in dual-agent workflow: Claude Code plans and reviews, Codex implements, deterministic gates verify, and you decide what merges.

Ghost personas review your code before it ships. Find edge cases, race conditions, and business logic bugs before production.

DSCODE, macOS üzerinde kalıcı shell ve paylaşılan oturum runtime'ı kullanan, DeepSeek Harness tabanlı bir terminal coding agent aracıdır.

Neden yükseliyor · 16 günde 675 yıldız, kısa sürede belirgin ilgi gördüğünü gösteriyor. Oturumlar arası görev devri ve paylaşılan runtime, coding agent'larda dikkat çeken bir ihtiyaca yanıt veriyor; ancak ilginin kaynağı veya gerçek kullanım düzeyi verilen verilerden anlaşılamıyor. Son 28 günde 123 commit'e karşın tek farklı yazar, geliştirme temposunun bağımsız katkıcılarla doğrulanmadığını gösteriyor.

A public, evidence-first agent skill for open-source maintainers: AI-assisted issue triage, PR review, release notes, automation guardrails,

Slash commands and MCP servers for AI agents, written once and compiled everywhere.

Local-first Git diff triage. Turn patches into actionable review checklists in your browser, CLI or GitHub Actions. Zero dependencies, no AI

Project housekeeping for DeepSeek Harness: 12 /logi-* commands, seven specialist review subagents, health score, and a baseline gate.

A focused GitHub desktop workspace for notifications, issues, pull requests, Actions, repository discovery, and an optional repository-aware

MCP-сервер для книжной типографики (алгоритм Кнута — Пласса) и визуального аудита вёрстки для AI-агентов на базе Justif и Playwright.