Coding agents & developer tools

Claude Code, Codex & Cursor extensions

8,960 agents · most starred first

Claude Code, Codex & Cursor extensions, page 73 of 90

claude-harness★ 2

Portable, self-adapting Claude Code harness: advisor agents, profile-driven /pr and /ticket skills, enforcement hooks, and /harness-init that tailors any repo.

ai-dotfiles★ 2

Cross-machine AI coding settings (Mac + Linux)

glyphdown★ 2

Lossless, on-device token-cost reduction for Claude Code and LLM coding agents. Free plugin: compresses tool-result output, dedups context, compacts the system prompt — stacks on Anthropic prompt caching. Rust hot path, Python fallback, fail-open. PolyForm Noncommercial.

Ouroboros.skill★ 2

🐍 让 agent 一直干活到完成的递归 Skill

VSOpenCode★ 2

A Visual Studio extension that integrates OpenCode into Visual Studio.

SnapBack★ 2

Attention manager for Claude Code - pauses your media, focuses your IDE, and snaps you back when done

claude-md-patterns★ 2

Practical CLAUDE.md and AGENTS.md patterns that make AI coding agent rules testable and enforceable.

claude-skills-templates★ 2

Five production-ready Claude Skill templates: one-pager writer, code reviewer, brand voice keeper, CSV cleaner, decision-doc generator. Each demonstrates a different SKILL.md pattern. Drop into Claude Code or Claude.ai. MIT licensed.

weir★ 2

Claude Code wrote `grep` 4,575 times and `rg` zero times across 25,216 Bash calls in one user’s transcripts. weir is the hook that fixes that — tells the model what shell tools you actually have, suggests rewrites for the antipattern cluster, refuses to run the unambiguously-broken ones (`cat FILE | grep`, `which CMD`).

mnb-claude-skills★ 2

open-source skills that make Claude & AI agents genuinely useful — Indian legal docs, GST, startup compliance, pitch decks, cold outreach, content, interviews, data cleaning & more

opencode-sessions-explorer★ 2

OpenCode plugin for recall and analysis of past OpenCode sessions: search, grep, and cost/usage insights across your session history via 18 LLM tools over the SQLite database.

socle★ 2

Méthode et garde-fous pour travailler avec un agent de code sur un projet qui dure. Extrait de trois projets réels et de leurs incidents.

smart-subagents★ 2

Quota-aware subagent routing for Claude Code. Reads live rate limits across codex/grok/kimi, dispatches to the CLI with headroom, isolates in a git worktree, and verifies the diff before reporting.

aegis-method-lite★ 2

Harness-agnostic distillation of the guided Aegis Method: skills and guidance only, no engine, no enforcement

generic-agent-runtime★ 2

Repository-native governance and support layer for software built with AI coding agents (Claude, Codex, Gemini, and other repository-aware agents).

agents-teamwork★ 2

Universal multi-IDE agent teamwork skills: one team-orchestrator skill + per-tool role configs for 12 coding tools (Claude, Codex, Copilot, Cursor, Windsurf, Trae, Qoder, Antigravity…)

skills★ 2

Public Agent Skills library exported from skill-graph. Install: npx skills add jacob-balslev/skills

report-annotator★ 2

Claude Code skill that annotates Markdown reports with plain-language explanations after every paragraph and table, verifies nothing was lost, and bundles them into one self-contained HTML digest.

agent-modpack★ 2

Download a ready-to-run AI-agent team you own. Works across Claude Code, Cursor, Codex and more, with no lock-in.

letstalk-master★ 2

隐私优先的 Codex Skill:把用户明确提供的偏好整理成可复用、可审计的 AI 助手配置。

claude-skills★ 2

Agent Skills for Claude Code: Figma-to-code pipeline, git workflow, doc hygiene automation, and design-engineering tools, built from real use.

agent-session-bridge★ 2

Coding-agent trajectory portability: Claude Code to ATIF v1.7 with fidelity accounting, redaction, and historical observability projection.

akc-cycle★ 2

Keeps the rules and skills in a Claude Code setup from piling up and going stale: a Claude Code plugin of audit and upkeep skills plus an optional always-loaded rules file, the installable form of the Agent Knowledge Cycle (AKC).

remix-me-skill★ 2

Cross-platform Agent Skill for comparing repos, papers, docs, and web references with a project then safely adapting approved ideas with explicit checkpoints.

dsh-auto-continue★ 2

Auto-resume failed/stalled turns for DeepSeek Harness (DSH) — dual-chain auto-continue + anti-repetition plugins, install scripts, bilingual docs, 47 tests

maestro★ 2

Skill orchestrator for Cursor, Claude Code & Codex. BM25 routing, editable subagent graphs, skill runbooks, and skills.sh discovery.

code-director★ 2

Claude Code directs, Codex executes. A skill plus a forwarding agent that hand code reading, debugging, implementation and review to Codex, one persistent Codex thread per problem, so Claude spends its context on judgment instead of on reading files.

gjc-plugin★ 2

Plugins for gajae-code (gjc) that make an agent's work checkable: test receipts, loopback UI assertions, plan validation, advisory delegation checks and a self-improvement ledger.

thats-a-wrap★ 2

Every AI session ends — usually with a wasted paragraph or silence. /wrap closes it with the outcome instead: tell the model how its work turned out, get one emoji back, and the record carries into the next session. Visible in memory, never a training reward. Open spec + prompts for every major tool. MIT.

loop-eng★ 2

loop-eng — 迭代闭环交付 skill:先红后绿、独立校验、冻结回流

AGENTS-template★ 2

Drop-in AGENTS.md template for Claude Code, Cursor, Codex, and other AI agents — with .agents/ for rules, personas, and workflows.

vibe-agentic-coding-llm-council-skill★ 2

Make your AI coding agent argue with itself before writing code. A model-agnostic SKILL.md for engineering decisions.

agent-supervisor-multiprovider_mcp★ 2

Switchyard: a small local daemon that keeps one live session per coding agent (agy, Claude Code, OpenCode, Codex). Spawn, watch, steer, interrupt and stop them from one CLI, MCP bridge or dashboard, with tier routing and a policy guard.

orthonym-skills★ 2

Claude Code skills for measurement-driven chemistry development — spy-site, check-target, gauntlet-loop, eval/gate/refusal-census loops, and more.

claude-code-agentic-setup★ 2

Personal Claude Code setup — orchestrator/subagent delegation policy, custom agents, and a colored PowerShell statusline (git branch, model+effort, tokens, cost, rate limits).

seatbelt★ 2

Keeps your CLAUDE.md/AGENTS.md rules alive across compaction, resume, and long Claude Code sessions — and nudges before a command breaks one you've flagged. Reminds and nudges, never blocks.

agent-harness-skills★ 2

IDE skills for scaffolding AI agent harnesses: ReAct, plan-and-execute, self-evolving, reflexion, multi-agent, code agent, RAG memory

opencode-smart-reasoning★ 2

OpenCode plugin that routes per-request reasoning effort for agents via Jev (TypeSafe SystemOne) — cheap prompts stay cheap, hard ones get full reasoning

wiggum★ 2

Self-driving agent loop for Claude Code. It turns an issue into a planned, verified, committed change, and lets you run, supervise, and chain workplans from the shell.

ultimate-copywriting-agent-skill★ 2

🧠 The ultimate AI agent copywriting skill — 3 legendary books (Sugarman, Whitman, Hopkins), 20 chapters, 50+ frameworks, fill-in-the-blank templates. Plug into Claude Code, Codex, Hermes, Amp, Antigravity, Cursor. Write copy that converts.

claudex★ 2

Claude Code <-> Codex adversarial-collaboration reconciliation workflow

codex-claude-companion★ 2

Durable Codex-to-Claude delegation with tmux ownership, recovery, collaboration, independent verification, and isolated review lanes.

Forge-Core★ 2

Forge-Core: a multi-agent build, test and review setup for Claude Code.

forge-master★ 2

Claude Code plugin for agentic loop-engineering: PRD design/import, tagged phase planning, and an autonomous TDD execution loop with deterministic escalation and disk-backed state.

agent-quick-menu★ 2

Quick menu for Claude Code: every plugin's commands and settings, and Claude Code's own, in one pane and a band above the prompt.

ghost-cofounder★ 2

👻 A brutally honest AI co-founder that challenges your assumptions and provides contrarian feedback in Claude Code

jjtask★ 2

🗂️ Manage tasks effectively with jjtask, leveraging JJ (Jujutsu) for structured planning and execution using DAGs and TODO markers.

never-code★ 2

The gold standard for agentic fullstack engineering. TypeScript monorepo template with Claude Code harness, blueprint loops, and immutable quality gates.

iphone-duo-adapter-skill★ 2

AI-assisted adaptation guide for iPhone Duo foldable devices. Comprehensive Claude Code skill + docs based on Apple WWDC 2026 Tech Talks.

deeplocal-chat-adapter★ 2

VS Code extension for chatting with and delegating coding tasks to local DeepLocal OpenAI-compatible models.

claude-business-skills★ 2

601 Claude Code Agent Skills for business work — finance, engineering, ops, HR, legal, retail, Excel, presentations, and 43 more domains. Install one domain in 30 seconds.

AI-harness-Character-creator★ 2

AgentDeck: one local GUI to configure every AI coding agent. Tune behavior, permissions, token usage and cost, skills, subagents, MCP servers and hooks for Claude Code, Codex CLI, Gemini CLI, Cursor, OpenCode and 16 more. Zero dependencies.

kanban-flow★ 2

Artifact-gated kanban workflow for AI coding agents. Gates read files on disk, not the agent's summary: every entry into testing mints a fresh execution id, so yesterday's green report stops counting.

Agents-and-Skills★ 2

52 Claude Code subagents, 44 skills, and the .claude/ project-brain pattern I use in every repo.

codex★ 2

Production-ready plugin ecosystem for OpenAI Codex CLI 26 plugins, 37 expert subagents (TOML), 196 skills, lifecycle hooks wired to a Bun harness, full AGENTS.md rules corpus, plugin marketplace and one-command installer. Faithful port of the Fusengine Claude Code plugin ecosystem.

ai-handover★ 2

AI 工作交接套装 | 一键生成交接文档,让下一个 AI 无缝接手

claude-skills-and-systems★ 2

360 production-ready agent skills for Claude Code: frontend, backend, AI agents, RAG, video/UGC, marketing, DevOps, security, testing + the skill-router system that runs them. One-command install.

claude-jev-funnel★ 2

Claude Code plugin + zero-dependency CLI for TypeSafe's Jev: judge items in bulk with calibrated yes/no, pick-one and rubric answers; handle the confident ends in code, review only the uncertain band.

Claude-Code-Skills-Custom-DevTools-Pack★ 2

A curated pack of custom Claude Code skills for developers — installable as a Claude Code plugin marketplace.

susanoo★ 2

Workflow guardrails for Claude Code. Susanoo routes each coding task to FAST, STANDARD or DEEP, blocks edits until you approve the plan and won't let Claude finish without verified test evidence.

pstack-for-cc★ 2

the top benchmarked pstack port for Claude Code: contains playbooks, skills and principles, enforced by a hook at every action

crewkit-cli★ 2

Institutional memory and governance for AI-assisted engineering. Give Claude Code your team's context, enforce your standards, and know which agent version did what. CLI-first.

open-sdlc-skills★ 2

A software team as Claude Code agent skills — PM, Architect, Project Manager, Sprint Master, Engineer, QA, Reviewer, DevOps, Release Manager. Covers the full SDLC and software quality management flow, coordinated through GitHub issues and committed markdown.

war-room★ 2

War-game your hard calls. A council of non-colluding officers plus a mandated dissenter returns the strategy that wins — and what would make it lose. Claude Code plugin.

agent-creator-skill★ 2

Build production-grade LLM agents from patterns distilled from real agent codebases.

yallaflow★ 2

YallaFlow — Persistent project memory and verified development workflows for AI coding agents like Claude Code and Codex.

tokenlens★ 2

See exactly what's eating your Claude Code context window, and stop it.

basicly★ 2

basicly writes the instruction files for Claude Code, Codex and Copilot from one catalog of rules, and adds git hooks that check every commit. It includes a tracker and a loop that builds each task in its own git worktree.

claude-usage-audit★ 2

Reflect on past Claude Code sessions to find the highest-leverage skills/automations to build next — evidence, not implementation.

codex-plugins★ 2

Production-ready plugin ecosystem for OpenAI Codex CLI 26 plugins, 37 expert subagents (TOML), 196 skills, lifecycle hooks wired to a Bun harness, full AGENTS.md rules corpus, plugin marketplace and one-command installer. Faithful port of the Fusengine Claude Code plugin ecosystem.

fp-pluginplaza★ 2

Flarepoint Plugin Plaza: small, single-purpose Claude Code plugins that fix one thing the model does that gets in your way, acting only at the edges of a task.

ripple-hud★ 2

Benchmarked Claude Code plugin that makes cheaper Claude models (Haiku, Sonnet, Opus) match Fable 5's output at a fraction of the token cost — auto-routed reasoning levels, verification discipline, closed-loop habit correction, statusline HUD with usage meters, and a portable AGENTS.md export for any AI coding agent.

crowsnest★ 2

See which Claude Code session is waiting on you — a macOS menu bar app showing your Claude Code sessions (local + remote over SSH), grouped by repo, surfacing the one stuck at a permission prompt.

jev-harness★ 2

Jev (TypeSafe) as the decision layer for Claude Code: permission gate, skill routing, conditional instructions, effort-tiered subagents, context packs. Tested PoC with evals.

visual-docs★ 2

Claude Code plugin that turns plans, designs, reports and guides into a clean one-page visual document (HTML Artifact)

off-the-wall★ 2

Stop telling Claude Code and Codex the same thing twice. Saves your corrections and quotes them back word for word before the agent answers. Local, no API key, zero dependencies.

forkcast★ 2

A Claude Code skill that gives your todo list a world model. Forks every decision, simulates 10 steps ahead, scores branches, emits a human-editable decision tree. The constructive answer to LeCun's world-model critique.

atlas★ 2

92% fewer AI-agent orientation tokens — Multi Agent , LOOP . The agentic harness standard: 4 Markdown files (map·tasks·scars·behavior) every Claude/Codex/Cursor/Gemini/Copilot session reads first. Install: npm·brew·apt·AUR·PPA. Zero infra.

agentic-wallpaper★ 2

Agentic Wallpaper: a live pixel-art wallpaper for Wallpaper Engine where your Claude Code and Codex sessions are little robots, driven by agent hooks.

loopgen-rs★ 2

Agentic loop runner for Claude Code — turns a goal into an iterative claude -p loop with a LOOP_STATUS termination contract (max-iter cap, optional verify gate, BLOCKED escape).

cc-tempo★ 1

A Claude Code statusline that measures real work time, SubAgent speedup, and code-churn pace — not just tokens and cost.

Copilot★ 1

docker region:us

copilot2Serice★ 1

docker region:us

HF-Copilot-auto★ 1

gradio region:us

copilot★ 1

docker region:us

GitHub_Copilot_Basics★ 1

static region:us

Claude-Code-Slash-Commands-Linux-Desktop★ 1

static region:us

claude-code-master-2026★ 1

static region:us

claude-plugins★ 1

Official, MySpec-managed directory of high quality Claude Code Plugins that using MySpec MCP to perform SDLC follow Spec Driven Development

sato-hub-skill★ 1

⬡ Sato Hub skill + plugin — query the scored index of onchain-agent tooling (frameworks, MCPs, wallets, x402, ERC-8004) and its agent-economy numbers from Claude Code, Codex, Cursor, Hermes

cc-audit

Lint any CLAUDE.md / AGENTS.md against the 12-rule baseline. One Python file, no deps, ~200 lines.

CodeGPT

AI coding assistant. Use your API key, your models, your way.

Wp Phpstan

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

Laravel Best Practices

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

Laravel Patterns

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

Laravel Specialist

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

Eloquent Best Practices Iserter

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

Laravel Security

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

Php Pro

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

Laravel Tdd Affaan M

Laravel/PHP AI agent skill — compatible with Claude Code, Cursor, Windsurf

More in Coding agents & developer tools