Mods leaderboard
Ranked by GitHub stars, plus forks and curated-list mentions.
- 1gstackgarrytan/gstackGarry Tan's opinionated Claude Code setup of role-based commands and skills.Workflow kits139k
- 2Superpowersobra/superpowersPlugin bundling a skills-based methodology for brainstorming, planning, TDD and debugging.Plugins & marketplaces312k
- 3CC Switchfarion1231/cc-switchCross-platform desktop app for switching Claude Code providers, configs and MCP servers.Model routers & proxies152k
- 4Everything Claude Codeaffaan-m/ECCLarge harness-optimisation kit of skills, hooks, commands, memory and security rules.Workflow kits296k
- 5Rufloruvnet/rufloAgent orchestration harness for swarms and autonomous workflows on Claude Code.Workflow kits81k
- 6claude-memthedotmack/claude-memPlugin that captures session activity with hooks and restores compressed context in later sessions.Plugins & marketplaces112k
- 7Karpathy CLAUDE.mdmultica-ai/andrej-karpathy-skillsSingle CLAUDE.md that steers Claude away from common LLM coding pitfalls.Workflow kits229k
- 8Spec Kitgithub/spec-kitGitHub's toolkit that installs spec-driven development commands for Claude Code and other agents.Workflow kits147k
- 9SuperClaude FrameworkSuperClaude-Org/SuperClaude_FrameworkConfiguration framework adding specialised commands, personas and methodologies to Claude Code.Workflow kits24k
- 10Claude Code Templatesdavila7/claude-code-templatesCLI for installing agents, commands, hooks and settings into Claude Code.Workflow kits33k
- 1agents-mdanthropics/claude-codeAGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.Memory & instructions mods154k
- 2sec-defaultanthropics/claude-codeSecurity default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and adds no policy of its own; one managed option, allowManagedModsOnly, limits mods to the organization's.Workflow mods154k
- 3code-modernizationanthropics/claude-plugins-officialGuided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).Memory & instructions mods46k
- 4ruview-liveruvnet/RuViewRuView live sensing in Claude Code: /ruview opens a pane beside the transcript with three views: an overview of your CSI nodes (ESP32, Realtek) and 60 GHz radar (rates, loss, RSSI, presence, device-reported vitals, alerts), a live CSI amplitude waterfall, and a radar range fan with vitals charts, all drawn in terminal cells. Reads only; runs the @ruvnet/ruview CLI it ships beside.Pane & dashboard mods102k
- 5ruflo-bbs-federationruvnet/rufloAgentBBS cross-host agent federation for ruflo (ADR-164). Phase 1 exposes room coordination — federation_bbs_register / federation_bbs_publish / federation_bbs_watch / federation_bbs_human_join. Phase 2 (v3.40.0) adds signed cross-host federation — federation_bbs_identity (persistent Ed25519 node identity), federation_bbs_peer_add (pin a peer by nodeId + public key), federation_bbs_peers (audit/unpin), federation_bbs_serve (read-only pull endpoint), and federation_bbs_sync (pull pinned peers and union-merge what verifies). Every merged envelope is Ed25519-verified against a pinned key; unsigned/misattributed/oversize/over-hop envelopes are dropped and counted. Transport is HTTP pull and works on any network (Tailscale, LAN, VPN, loopback) — no tailnet required. Coordinates work ownership via claim messages (ClaimIssued/Released/Handoff/Ack). agentbbs lives in optionalDependencies; every handler gracefully degrades to {degraded:true} when the package is missing (ADR-150 pattern). As a mod (ADR-445 pattern): a tighten-only tool guard, a local slash command, and a status file the console shows.Workflow mods80k
- 6ruflo-consoleruvnet/rufloruflo's cockpit inside Claude Code and the one /ruflo command for every ruflo mod (function hooks, early access). Views: overview with health alerts, swarm topology graph, claims flow with TTL rings, federation map, plugin health matrix, learning curve and pipeline, MetaHarness radar and audit trend, memory, cost gauge, agent timeline, approvals queue, event stream, a main menu, an x.ruv.io federation board, an AI terminal (codex, claude or both in remembered sessions, streamed), Skills (npx skills), a Hive-Mind view, a MetaHarness lab, agent drill-down; a command palette for confirm-gated actions through the ruflo CLI; a band above the prompt. Reads ruflo's files and the CLI's local JSON; anything not measured reads n/a. The one network call it makes by itself is a daily read of the published plugin.json at github.com/ruvnet/ruflo to offer an update (Settings → Updates: ask, auto, or off); it installs only through Claude Code's own claude plugin update, and never a new major version without asking.Notification & sound mods80k
- 7fmkunchenguid/firstmateFirstmate Calm for Claude Code: the sailboat working animation and conversation-only transcript presentation, sharing the per-home config/calm preference with the Pi Calm extension. Its hooks module may load through CLAUDE_CODE_ENABLE_FUNCTION_HOOKS or Claude Code's tengu_plugin_hooks_modules rollout flag, but the mod activates only when CLAUDE_CODE_ENABLE_FUNCTION_HOOKS is exactly 1 and is otherwise a complete no-op.Workflow mods8.5k
- 8fast-jev-compactiontamaratran/fast-jev-compactionVerbatim Jev-guided compaction for Claude Code sessions.Workflow mods7.8k
- 9terminal-browserzenbu-labs/terminal-browserA browser running directly inside claude code. Preview websites, view HTML documents, and let your agent control the built in browser.Pane & dashboard mods4.4k
- 10token-optimizeralexgreensh/token-optimizerThe Token Optimizer status bar on its own, for its tests. It ships inside the token-optimizer plugin.Context & usage mods2.8k
- 1Claude HUDjarrodwatts/claude-hudA plugin that turns the status line into a HUD showing context usage, active tools, running subagents and todo progress.29k
- 2ccstatuslinesirmalloc/ccstatuslineA highly configurable status line for Claude Code with powerline styling, themes and an interactive setup tool.14k
- 3CCometixLineHaleclipse/CCometixLineA fast status line for Claude Code written in Rust, with git info, model and usage segments and a TUI configurator.3.5k
- 4claude-powerlineOwloops/claude-powerlineA vim-style powerline status line with usage tracking, git integration and custom themes.1.2k
- 5claude-statuslinenilbuild/claude-statuslineA minimal personal status line setup for Claude Code.1.4k
- 6cc-statuslinechongdashu/cc-statuslineGenerates an informative status line script for Claude Code through an interactive setup.645
- 7claude-dashboarduppinote20/claude-dashboardA status line plugin showing context usage, API rate limits and session cost.586
- 8best-claude-hudGaoSSR/best-claude-hudA minimal Rust-powered status line HUD for Claude Code.995
- 9claude-statusbarleeguooooo/claude-code-usage-barA one-line status line showing 5-hour and 7-day rate-limit usage, reset countdowns, model and context, with several styles and themes.388
- 10model-effort-bandYeonwooSung/my-claude-code-modsA mod that shows the selected model and observed effort level in a coloured band above the prompt.1.1k
- 1Claude Code Hooks Masterydisler/claude-code-hooks-masteryReference project demonstrating every Claude Code hook event with working Python scripts for logging, blocking and TTS.4k
- 2Multi-Agent Observabilitydisler/claude-code-hooks-multi-agent-observabilityStreams hook events from many Claude Code agents to a live web dashboard for real-time monitoring.1.6k
- 3Claude Code Ultimate GuideFlorianBruniaux/claude-code-ultimate-guideThe most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.6.3k
- 4destructive_command_guardDicklesworthstone/destructive_command_guardFast Rust PreToolUse hook that stops destructive shell, git and filesystem commands before they run.6.2k
- 5Continuous Claude V3parcadei/Continuous-Claude-v3Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.3.9k
- 6TDD Guardnizos/tdd-guardHook-based enforcer that blocks code changes which skip the red-green-refactor TDD cycle.2.4k
- 7Everything Claude CodeWorldFlowAI/everything-claude-codeClaude Code toolkit - agents, commands, skills, rules, and hooks for productive AI-assisted development5.8k
- 8Skillsharerunkids/skillshareSync skills, agents, MCP, plugins to all AI CLI tools with one command and simplify team sharing.2.9k
- 9Claude Memory Compilercoleam00/claude-memory-compilerHooks that capture sessions and compile them into evolving project memory for Claude Code.1.3k
- 10Claude Code Prompt Improverseverity1/claude-code-prompt-improverIntelligent prompt improver hook for Claude Code. Type vibes, ship precision.2k
- 1Happyslopus/happyOpen-source mobile and web app for controlling Claude Code and Codex sessions on your computer from your phone.24k
- 2Claude Code Best Practiceshanraisshan/claude-code-best-practicefrom vibe coding to agentic engineering - practice makes claude perfect69k
- 3AionUiiOfficeAI/AionUiOpen-source desktop cowork app that gives Claude Code and 20+ other CLI agents a shared graphical workspace.34k
- 4CloudCLIsiteboon/claudecodeuiSelf-hosted web and mobile interface for driving Claude Code sessions remotely from any browser.14k
- 5opcodewinfunc/opcodeDesktop GUI for Claude Code that manages sessions, custom agents, background runs and usage in one app.22k
- 6KilocodeKilo-Org/kilocodeKilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.28k
- 7Cmuxmanaflow-ai/cmuxOpen source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.29k
- 8cc-connectchenhg5/cc-connectBridges local Claude Code and other coding agents to chat platforms like Slack, Feishu and DingTalk.16k
- 9Clawd on Deskrullerzhou-afk/clawd-on-deskPixel-art desktop pet that reacts to and watches over your Claude Code sessions.6.7k
- 10CC HahaNanmiCoder/cc-haha本地优先的跨平台 Claude Code / AI Agent 桌面工作台:多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物;支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git worktrees, diffs, skills marketplace, multi-model, Computer Use, task-aware desktop pets; remote via WeChat, Feishu, DingTalk, Telegram, WhatsApp & H5.15k
- 1CodexBarsteipete/CodexBarmacOS menu bar app showing Claude Code and Codex usage limits without logging in.23k
- 2Claude Code Usage MonitorMaciek-roboblog/Claude-Code-Usage-MonitorReal-time terminal monitor for Claude Code token usage with burn-rate predictions and limit warnings.8.8k
- 3ccusageccusage/ccusageCLI that analyses Claude Code's local JSONL logs to report token usage and cost by day, month and session.19k
- 4CodeBurngetagentseal/codeburnLocal tool that tracks token usage and cost across Claude Code and dozens of other coding agents.12k
- 5cost-xraytigerless-labs/cost-xrayShows what Claude Code sends to the API and what each part of the request costs.5.8k
- 6Loop Engineeringcobusgreyling/loop-engineeringPractical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.12k
- 7FailproofaiFailproofAI/failproofaiObservability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.7.8k
- 8abtopgraykode/abtophtop-style terminal monitor for Claude Code and Codex sessions, tokens, context window and rate limits.3.8k
- 9Token MonitorJavis603/token-monitorDesktop widget tracking token usage, cost and limits across Claude Code and other AI coding tools.3.5k
- 10Tokscalejunhoyeo/tokscaleTrack token usage across AI coding agents from your terminal. Global leaderboard with trillions of tokens tracked.5.8k
- 1Cmuxmanaflow-ai/cmuxOpen source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.Desktop, web & mobile apps29k
- 2OpenagentsOpenAgentsInc/openagentsThe Agent NetworkMulti-agent & worktrees462
- 3gstackgarrytan/gstackGarry Tan's opinionated Claude Code setup of role-based commands and skills.Workflow kits139k
- 4claude-code-toolspchalasani/claude-code-toolsProductivity tools and plugins for Claude Code including session search and safety hooks.Plugins & marketplaces2k
- 5Gh Awgithub/gh-awGitHub Agentic WorkflowsMulti-agent & worktrees5.6k
- 6Plannotatorbacknotprop/plannotatorThe workspace to stay in the loop and on top of agents - shape, decide, plan, annotate, review code, share with team, and send all feedback to agents with one click.Multi-agent & worktrees9.8k
- 7TuiosGaurav-Gosain/tuiosA terminal window manager that knows what your agents are doing. Tiling panes, workspaces, sessions that survive restarts, and one Inbox for every coding agent. Official only at tuios.dev and this repo. tuios has no X/Twitter account.Desktop, web & mobile apps6.3k
- 8InstarJKHeadley/instarPersistent Claude Code agents with scheduling, sessions, memory, and Telegram.Sessions & history86
- 9Openrigmvschwarz/openrigBuild your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.Multi-agent & worktrees8.6k
- 10KilocodeKilo-Org/kilocodeKilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.Desktop, web & mobile apps28k
Mods, by what they do
Mods are Claude Code's newest extension point (v2.1.287+): plugins with code that runs inside Claude Code, so they can draw panes and bands, restyle the interface and step into tool calls.
Panes beside the transcript and bands above the prompt: dashboards, trackers, viewers.
Live context fill, token use, rate limits, cache and cost, drawn inside Claude Code.
Stop, hold or rewrite risky tool calls, protect secrets and ask before deploys.
Branches, diffs, commits, pull requests and CI status without leaving the session.
Notes, rules, CLAUDE.md and AGENTS.md handling, handoffs and context carried between sessions.
Toasts, sounds, voice and phone pings when Claude finishes or needs you.
Restyled spinners and tool rows, pets, games and music while Claude works.
Commands, prompts and helpers that change how you work with Claude Code.
More ways to customise Claude Code
Status lines, settings hooks, commands and plugins, plus the apps and tools people run Claude Code with.
Custom bars under the prompt: model, git branch, context use, cost and more.
Settings hooks that run on Claude Code events: guardrails, auto-formatting, tests, logging.
Reusable prompts you trigger with /name inside Claude Code.
Bundles of commands, hooks, agents and servers you install with /plugin.
Frameworks that install a whole way of working: specs, phases, personas, rules.
Change Claude Code's tone, format and role with /output-style.
Change the look of Claude Code: themes, HUDs, panels, keybindings, spinners.
Get pinged on your desktop, phone or speakers when Claude needs you.
Run Claude Code from a GUI, the browser or your phone.
See tokens, costs and plan limits from your Claude Code sessions.
Browse, search, resume, share and export past Claude Code sessions.
Point Claude Code at other models and providers, or route between them.
Run many Claude Code sessions in parallel, each in its own worktree or container.
Use Claude Code inside Neovim, Emacs, VS Code, JetBrains, Zed and more.
Manage CLAUDE.md, settings, permissions, memory and dotfiles for Claude Code.
All mods
8,346 listed, most popular firstidle-compact
ShadowDog007/claude-mods
Runs /compact while the session sits idle waiting on background work, right before the prompt cache expires.
idle-compact
wryskware/claude-mods
Compacts the session once it is 20% full and has been idle 50 minutes, while the prompt cache is still warm.
idle-compact
xyjk0511/idle-compact
Compact once after 50 idle minutes, while the 1h prompt cache is still warm. Works in the desktop app and SDK sessions too.
idle-opacity
UnlimitedxIQ/brysons-claude-setup
WezTerm window goes more solid when Claude stops, so the answer is easier to read, and back to see-through while it works
ifc-viewer
Rinze-Smits/ifc-viewer-claude-mod
View IFC models in a pane beside the chat (IfcLite geometry, SVG view) and highlight the elements you're working on
image-mod
zyx1121/image-mod
See the images you paste into Claude Code: thumbnails above the prompt while the draft holds them, and the picture under each sent message. Needs a terminal with kitty graphics (Ghostty, kitty).
image-peek
thomasreichmann/image-peek
Draws the images the agent reads (Read on png/jpg/gif/webp, image blocks in tool results) as pictures under their tool row in the terminal transcript.
image-preview
ezoushen/claude-mods
Render image paths inline: a thumbnail in the user's prompt row (aspect-fill, max 10 rows) and in agent reply rows when the model mentions a path. Recognises a file path ending in a supported image extension (quoted or with escaped spaces too), or an [Image #N] token for a pasted picture.
image-preview
f64991144/claude-image-preview
See the images you paste into Claude Code: thumbnails above the prompt instead of bare [Image #N] tags, and click a thumbnail to enlarge it.
image-preview
hedingerm/image-preview
Inline image previews in the terminal (Ghostty, kitty): under every image Claude reads, above the prompt for pasted images, and on demand with /img
image-preview
sandipchitale/claude-code-image-preview
Browse the images you paste into the prompt: chips above the prompt and a master/detail browser window that previews them and opens them in your OS viewer
image-preview
seanmars/my-agent-plugins
Pasted images become chips you can click to open in the system viewer, in the transcript and above the prompt
image-shrinker
varunmoka7/image-shrinker
Shrinks big screenshots before Claude reads them, so long sessions last longer, and tells Claude the scale so clicks still land in the right place.
image-thumbs
ohade/claude-mods
Shows pasted images as framed thumbnails under the prompt; click to expand, open in a pane, or /image
img-view
liliang-cn/aigui
Shows images in a pane beside the conversation: real pixels where the terminal draws them, colour block art everywhere else
imgview
hieuvo/claude-imgview
Preview images inside Claude Code: hover the chip under a reply that names an image file to pop its picture up, click it to open the picture in a pane, or use /img <path>. Pixels on kitty and Ghostty, colored block characters on every other terminal.
implement-plan-tracker
hoangbits/claude-implement-plan-tracker
Live pane with every step of the current plan, the current step marked, and a done/total count
inbox
eshin087/claude-code-mods
Which of your chats, across every project on this computer, are waiting on you and why: in the footer, /inbox for the list, a notification when one starts waiting.
inbox
tylergraydev/cc-mods
The repo's inbox/ work queue as a pane: todo items at the root, then processing/, review/, done/ and blocked/. Shows what is ready (dependencies, owner-path overlap, locks), starts Codex or Claude workers on items, drains the queue, reviews and accepts, with a watchdog for idle workers and cross-session locks
inline-images
nnemirovsky/cc-inline-images
Images inline in the Claude Code transcript through the terminal's kitty graphics: files Claude sends or reads, pasted images, image paths, locally and over ssh
inline-images
samuelpatro/claude-code-inline-images
Shows images inline in the Claude Code terminal: pasted images under your prompt and above the prompt box, and the images Claude reads, writes or screenshots under their tool call.
inline-replies
betoescobar46/pituto
Answer Claude's questions and quote its paragraphs with a click: numbered questions with clickable options, a on every paragraph, and the full context sent along with your message.
inline-tribunal
ccdwyer/inline-tribunal
A second_opinion tool and /tribunal command: your diff is reviewed by Codex and Grok side by side, read-only, inside the session
insights
ClarvAI/job-search-hq
How your search is going: a /job-insights pane with where applications stall, where replies come from, whether fit scores predict replies, and why you passed on leads.
integral
serg-yalosovetsky/integral
One HUD above the prompt: context bar with compact/checkpoint, plan limits, MCP health, plan progress. Replaces context-bar-compact and mcp-doctor.
integrity
NMenzel/claude-integrity-mod
Tells implemented apart from verified: a requirement contract from your own words, a Mirage Detector for fake completeness, evidence from real test/build/lint runs, and an audit of completion claims.
isobar
r3al1tym/isobar
isobar, a Claude Code mod: a weather map for the session's change, drawn over a fixed map of the codebase, to read a complex change at a glance. A red storm sits on what Claude edited, each changed region is captioned with what the change did there, green rain falls on the code that uses what changed, the latest turn shows brightest, and an optional scope check flags edits nobody asked for.
issue-first
bahaospanov/skills
Feature work starts from an issue, and each commit names its own: a feat commit naming none is refused until Claude finds the issue, drafts one the user agrees to, or the user says it needs none; a commit whose subject does not end with the issue the user or the branch named gets a suggestion.
issue-map
romtaugranot/issue-map
Draws a Project's open Issues as a Map joined by the Links its Tracker records, inside Claude Code.
jargon
Danh295/dannys-claude-mods
Highlights jargon in Claude's replies; hover or click a term for a plain-English definition
jaugeai-band
BenjaminSanchezPaper34/jaugeai-claude-code
JaugeAI usage band above the Claude Code prompt: plan, tightest limit and reset time for Claude, Codex and Gemini (requires JaugeAI for Mac, Pro)
jc-gearbox
KevinYu1580/jcGearbox
Picks the model once per session and the effort every turn, using TypeSafe's Jev to judge how hard the task is.
jc-hud-mod
karimdjaafar/jc-hud-mod
JC HUD — mod Claude Code : barre d'instruments Jasmine Conseil (contexte, forfait, modèle, horloges)
jeanCLAUDE
gblachstein/claude-mods
A dancing GIF at the bottom left that moves while Claude is working and freezes when it stops
jev
gecm0/jev-mod
Adds $.jev: typed Choice, Score and Noul judgments from TypeSafe's Jev, with a timeout and validated answers, for other mods to call.
jev
yinjs/claude-jev
Jev answers clear permission prompts, flags prompt injection in fetched content, checks done claims, nudges large or vague requests, and routes effort and models without trading away the prompt cache.
jev-compact
HAR5HA-7663/jev-compact
Context compaction that prunes instead of summarising: rules drop exploration output and hook noise locally, Jev ranks the rest against a budget, a note says what was removed, and removed outputs are archived for the brain. Falls back to the built-in summary when it cannot do better.
jev-compact-trigger
HAR5HA-7663/jev-compact
Companion to jev-compact: watches context use after every turn and starts a compaction at the configured percentage. Separate plugin on purpose — the engine skips a plugin's own session.compact hook when that plugin raises the compaction, so the trigger must come from outside jev-compact for the pruning to run.
jev-guard
klefix/claude-code-mods
Asks Jev whether a prompt leaves a choice open and whether each edit stays within what the user approved
jev-judge
kuhku/kuhaku-plugins
Annotates Claude Code's AskUserQuestion dialog with TypeSafe Jev's probabilities and a recommended option (labels in Japanese).
jev-model-router
m-esm/jev-model-router
TypeSafe Jev scores each prompt and switches the session's model and effort to match, per turn.
jev-model-router
Tolsee/dotfiles
Sets the model of every subagent spawn (agent.spawn). The agent type sets the baseline: agents whose definition pins a model keep it, general-purpose, claude and Plan get sonnet, and TypeSafe's Jev may move those down to haiku, or up to opus when the task is risky (production, money, irreversible data). Sonnet is the ceiling otherwise; a description starting with [opus] goes to opus. No key or no verdict in time leaves the baseline, never the parent's Opus.
jev-prompt-grader
Syptern/jev-prompt-grader
Grades each prompt you send with TypeSafe's Jev model and shows what is missing above the prompt box.
jev-router
Xvectorio/xvector-claude-mods
Per-turn model routing: TypeSafe Jev picks Haiku, Sonnet or Opus for each prompt (port of gargpratyush/jev-router).
jev-semaphore
staticdreams/jev-semaphore
Jev Semaphore for Claude Code: Jev / Kev model routing for subagents, with a live allocation pane, agent graph and context-exchange band
jev-skill-suggestion
AnatoliyShk/bulgolingo
Keeps the skill listing out of the context window and lets TypeSafe's Jev, a System One decision model, pick at most one skill per prompt from the skills' descriptions, the way TypeSafe's skill-suggestion cookbook does: one request ranks every skill and asks whether the prompt needs a skill at all, a second re-reads the top three with their SKILL.md and can reject them all. The winner's SKILL.md is attached to the prompt, so the skills can be hidden from the model altogether (/jev-skill-suggestion:setup makes them user-invocable-only and /context counts them at 0). Falls back to the engine's built-in classifier when no key is set.
jev-vault-gate
sohryuu101/jev-vault-gate
Uses Jev to spot durable knowledge in a turn and auto-capture it into ~/vault/raw/ for /compile.
jev-watch
deadczarvc-labs/jev-watch
Logs what fast-jev-compaction does (outcomes, TypeSafe requests, compactions, hook failures) to JSONL files.
About Claude Code mods
What is a Claude Code mod?
Since version 2.1.287, a mod is a Claude Code plugin with JavaScript or TypeScript handlers that run inside Claude Code. Unlike a settings hook or a status line script, a mod can draw panes beside the transcript and bands above the prompt, add buttons and toasts, restyle the spinner and tool rows, and hold, rewrite or answer a tool call. Mods work in the CLI, the Code tab of the desktop app and the VS Code extension.
How do I install a Claude Code mod?
A mod installs like any plugin. Inside Claude Code, add its marketplace with /plugin marketplace add owner/repo, then run /plugin install name@marketplace. To try one without installing it, clone the repo and start Claude Code with --plugin-dir pointing at the mod folder. Every mod page here has the exact commands.
What else is in this directory?
Every other way people customise Claude Code: status line scripts, settings hooks, custom slash commands, output styles, themes, plugin marketplaces and workflow kits, plus the apps people run it with, such as GUIs and mobile clients, usage and cost trackers, session browsers, model routers, multi-agent and worktree runners and editor integrations. Skills and MCP servers have their own directories.
What does a mod's reach mean?
Reach is the widest thing a mod's code asks Claude Code to do, from a static scan of its source: L0 only draws and remembers, L1 reads files or settings, L2 writes files, runs processes or drives Claude, and L3 reaches the network. It is a footprint, not a verdict: a pull request tracker has to run git. A mod runs with your permissions, so read its code before you install it.
How is popularity measured?
By the GitHub stars of each repo, with forks, curated awesome lists and listing in Anthropic's plugin directory as smaller signals. When one repo holds many mods they share its stars, so only its first few rank high. The data refreshes every day.
Are Claude Code mods safe?
Mods, hooks, status lines and most tools run on your machine with your permissions, so treat them like any code from the internet: check a mod's reach, read the code before installing, prefer well-starred and recently updated repos, and check the license. Run claude plugin validate on a clone to list what a mod hooks and calls without running it, and start Claude Code with --safe-mode to turn every customization off for a session.
Sources: our own research, awesome-claude-code-mods, awesome-claude-code, jqueryscript/awesome-claude-code, subinium/awesome-claude-code, awesome-claude-code-toolkit, awesome-claude-code-hooks and GitHub search. Last updated 3 November 2026. Looking for more? See the skills and MCP server directories.