ModsCode / Claude Code Mods / Ranking

• blast-radiusSee what a risky command would change before it runs.deepseek-ai★ 247,289
  1 more in this repository

  • replay-theaterStep through the last turn's edits, one diff at a time.deepseek-ai★ 247,289
• ruview-liveRuView 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 ampl…ruvnet★ 97,236
• ruflo-protectorProject Anatole: an optional, learning watchdog for unattended agents. Deterministic OWASP-mapped rules, a per-project behavioural baseline, four modes (off, learn, notify, enforce), alerts you can read later.ruvnet★ 74,323
  40 more in this repository

  • ruflo-swarmAgent teams, swarm coordination, Monitor streams, and worktree isolation — wraps 4 swarm_* + 8 agent_* MCP tools (12 total) plus 6 topologies (hierarchical / mesh / hierarchical-mesh / ring / star / adaptive). With Claude Code function hoo…ruvnet★ 74,323
  • ruflo-agentAgent runtimes for ruflo — local WASM-sandboxed agents (rvagent: 10 wasm_agent_*/wasm_gallery_* MCP tools, built on @ruvector/rvagent-wasm + @ruvector/ruvllm-wasm per ADR-070) plus Anthropic Claude Managed Agents as a cloud backend (manage…ruvnet★ 74,323
  • ruflo-agentdbSubstrate plugin for Ruflo memory: AgentDB controller bridge (15 agentdb_* MCP tools), RuVector ONNX embeddings (10 embeddings_* tools incl. RaBitQ 32x quantization), and WASM HNSW pattern router (3 ruvllm_hnsw_* tools). As a mod (ADR-445)…ruvnet★ 74,323
  • ruflo-agntcyAGNTCY/Outshift Internet-of-Cognition runtime integration for Ruflo — SLIM secure transport for cross-host agent coordination, CASA intent-scoped tool authorization enforcement, optional IOC Layer 9 coordination events, and AGNTCY identity…ruvnet★ 74,323
  • ruflo-ai-teamGive Claude a tenant-isolated AI team that divides work, coordinates progress, recalls approved context, and returns evidence-backed results.ruvnet★ 74,323
  • ruflo-aidefenceAI safety scanning, PII detection, prompt injection defense, and adaptive threat learningruvnet★ 74,323
  • ruflo-arenaCompetitive ruliology for Ruflo swarms — arenas, tournaments, and adaptive co-evolution of program strategies (ADR-147/148). Strategies-as-programs compete under payoff games; tournaments produce Wolfram-style competitive arrays; hill-clim…ruvnet★ 74,323
  • ruflo-autopilotAutonomous /loop-driven task completion with learning, prediction, and progress tracking — wraps 10 autopilot_* MCP tools (status/enable/disable/config/reset/log/progress/learn/history/predict)ruvnet★ 74,323
  • ruflo-bbs-federationAgentBBS 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 fed…ruvnet★ 74,323
  • ruflo-browserSession-as-skill browser automation: Playwright + RVF cognitive containers + ruvector trajectories + AgentDB selector memory + AIDefence PII/injection gates As a mod (ADR-445 pattern): a tighten-only tool guard, a local slash command, and …ruvnet★ 74,323
  • ruflo-business-podsADR-164 Phase 2 — business-domain pod templates for the federated business autopilot. Ships the sales pod template (templates/sales.json) and a single-tick runner (scripts/pod-tick.mjs) that pre-flights templates via business_pod_validate,…ruvnet★ 74,323
  • ruflo-daaDynamic Agentic Architecture — 8 daa_* MCP tools for adaptive agents (create/adapt), cognitive patterns, workflows (create/execute), knowledge sharing, and learning/performance metrics. Feeds the JUDGE phase of the 4-step intelligence pipe…ruvnet★ 74,323
  • ruflo-deepseek-harnessDeepSeek model harness for ruflo — agents, commands, scripts, and skills for running and evaluating DeepSeek-backed workflows within the ruflo swarm.ruvnet★ 74,323
  • ruflo-docsDocumentation generation, API docs (JSDoc/TSDoc/OpenAPI), and drift detection — drives the `document` background worker via hooks_worker-dispatch; uses Haiku model for cost-efficient docs workruvnet★ 74,323
  • ruflo-federationCross-installation agent federation with zero-trust security, peer discovery, consensus-based task routing, and per-call budget circuit breaker (ADR-097)ruvnet★ 74,323
  • ruflo-goalsLong-horizon goal planning, deep research orchestration, and adaptive replanning using GOAP algorithmsruvnet★ 74,323
  • ruflo-graph-intelligenceRuFlo Graph Intelligence Engine — real-time relationship intelligence with complexity-aware execution. Single-entry personalized PageRank, streaming delta updates, witness-signed reasoning artifacts, federation-distributable PR vectors. Bu…ruvnet★ 74,323
  • ruflo-intelligenceUser-facing surface for Ruflo's self-learning system: 6 neural_* + 10 hooks_intelligence_* + 6 routing/meta hooks + 3 hooks_model-* + 4 SONA/MicroLoRA tools (29 total). Implements the 4-step pipeline (RETRIEVE → JUDGE → DISTILL → CONSOLIDA…ruvnet★ 74,323
  • ruflo-iot-cognitumIoT device lifecycle, telemetry anomaly detection, fleet management, and witness chain verification for Cognitum Seed hardwareruvnet★ 74,323
  • ruflo-jujutsuAdvanced git workflows with diff analysis, risk scoring, change classification (feature/bugfix/refactor/...), and reviewer recommendations — wraps 6 analyze_* MCP tools (diff, diff-risk, diff-classify, diff-reviewers, file-risk, diff-stats…ruvnet★ 74,323
  • ruflo-knowledge-graphKnowledge graph construction — entity extraction, relation mapping, and pathfinder graph traversal. As a mod (ADR-445): keeps secrets out of the graph, confirms graph deletes, /kg-mod, and a status file the console showsruvnet★ 74,323
  • ruflo-loop-workersCache-aware /loop workers and CronCreate background automation — wraps 5 hooks_worker-* MCP tools (list/dispatch/status/detect/cancel) and exposes 12 background worker triggers (ultralearn, optimize, consolidate, predict, audit, map, prelo…ruvnet★ 74,323
  • ruflo-market-dataMarket data ingestion — feed normalization, OHLCV vectorization, and HNSW-indexed pattern matching. As a mod (ADR-445): keeps credentials and credentialed feed URLs out of market memory, /market-mod, and a status file the console showsruvnet★ 74,323
  • ruflo-metaharnessMetaHarness integration for ruflo — surfaces score/genome/mint/mcp-scan/threat-model via skills; pairs with @metaharness/router (ADR-148/149) for cost-optimal model routing; honors ADR-150's architectural constraint that MetaHarness remain…ruvnet★ 74,323
  • ruflo-migrationsSchema migration management — generate, validate, dry-run, and rollback database migrations. As a mod (ADR-445): a tighten-only guard on its tools, /migrations-mod, and a status file the console showsruvnet★ 74,323
  • ruflo-musicAI music generation via Cognitum Music (cogmusic MCP) — compose lyrics/prompts, generate tracks, separate stems, extract MIDI, and master through your own music.cognitum.one account. As a mod (ADR-445): a tighten-only guard on its tools, /…ruvnet★ 74,323
  • ruflo-neural-traderNeural trading via npx neural-trader — self-learning strategies, Rust/NAPI backtesting, 112+ MCP tools, swarm coordination, and portfolio optimization. As a mod (ADR-445): a tighten-only guard on its tools, /trader-mod, and a status file t…ruvnet★ 74,323
  • ruflo-observabilityStructured logging, distributed tracing, and metrics — correlate agent swarm activity with application telemetry. As a mod (ADR-445): a tighten-only guard on its tools, /observe-mod, and a status file the console showsruvnet★ 74,323
  • ruflo-plugin-creatorScaffold, validate, and publish new Claude Code plugins with the canonical plugin contract — now including governed Claude Code mods (function hooks), ADR + smoke + Compatibility + namespace coordination + MCP-tool drift warnings. As a mod…ruvnet★ 74,323
  • ruflo-rag-memoryRuVector memory with HNSW search, AgentDB, and semantic retrieval. As a mod (ADR-445): a write guard that keeps secrets out of memory, /rag-mod, and a status file the console showsruvnet★ 74,323
  • ruflo-ruosRun ruflo swarm agents on your own ruOS cloud desktops via the tenant-authenticated fleet MCP or per-tenant SSH; optional and removable (ADR-405)ruvnet★ 74,323
  • ruflo-ruvectorSelf-learning vector database via npx ruvector@0.2.25 — HNSW, adaptive LoRA embeddings, code-graph clustering, hooks routing, brain/SONA, 103 MCP tools. As a mod (ADR-445): a write guard that keeps secrets out of the vector store and share…ruvnet★ 74,323
  • ruflo-ruvllmRuVLLM local inference with chat formatting (Claude/GPT/Gemini/Ollama/Cohere), model configuration, MicroLoRA fine-tuning, and SONA real-time adaptation. As a mod (ADR-445): a guard that keeps secrets out of adapters and the pattern router…ruvnet★ 74,323
  • ruflo-rvfRVF format for portable agent memory, session persistence, and cross-platform transfer. As a mod (ADR-445): a write guard that keeps secrets out of memory, sessions and transfers, /rvf-mod, and a status file the console showsruvnet★ 74,323
  • ruflo-security-auditSecurity review, dependency scanning, policy gates, and CVE monitoringruvnet★ 74,323
  • ruflo-testgenTest gap detection, coverage analysis, and automated test generation — drives the testgaps background worker via hooks_worker-dispatch; SPARC Refinement-phase canonical ownerruvnet★ 74,323
  • ruflo-workflowsWorkflow automation across two surfaces: the 10 workflow_* MCP tools (create/run/execute/status/list/pause/resume/cancel/delete/template) with full state-machine lifecycle (created → running ↔ paused → completed/cancelled), and native Clau…ruvnet★ 74,323
  • ruflo-x-gatewayCoordinate AI-agent swarms through signed federation messages, channels, and work claims. The remote Claude connector exposes a directory-safe Streamable HTTP MCP surface with OAuth-protected publishing and five ruv:// reference resources.ruvnet★ 74,323
  • ruflo-chatgpt-federationDedicated ChatGPT Federation MCP publisher with isolated Nostr signing-key custody, OAuth-scoped publishing, and signed public-channel coordination over the Ruflo relay. As a mod (ADR-445 pattern): a tighten-only tool guard, a local slash …ruvnet★ 74,323
  • my-modA Claude Code mod scaffolded by ruflo-plugin-creator: counts the session's tool calls in a status line, adds /my-mod-status, and keeps a classic hook as the fallback where function hooks are off.ruvnet★ 73,986
• code-modernizationGuided 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…Anthropic★ 37,653
• seo-cockpitMods companion for claude-seo: a spend guard on paid SEO APIs, a live audit band with a receipt, an economy mode, a visual cockpit (Search Console, rankings, Core Web Vitals, audit, Maps, spend) and zero-token commandsAgrici Daniel★ 18,364
• mobile-mcpMobile automation for Claude Code: the mobile-mcp server, and /mobile-mirror, a live, clickable device screen in a pane.Mobile Next★ 8,957
• fmFirstmate 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_FUNC…Firstmate★ 7,801
• fast-jev-compactionVerbatim Jev-guided compaction for Claude Code sessions.tamaratran★ 7,439
• obsidian-mindDelivers obsidian-mind's session context as an instruction file, so it survives compaction whole and reaches subagents, and shows the vault's Stop report as one line under the answer, handing the agent the full report with your next messag…Brenno Ferrari★ 5,157
• jev-memoryRemembers the preferences you state in prompts: Jev (via treg) judges each prompt's sentences after the turn and saves lasting ones to .claude/jev-memory.md.Shawn Esquivel★ 4,976
• next-stepsAfter each turn, suggests up to three next prompts above the input. Press 1, 2 or 3 to put one in the prompt box as a draft you can edit, 0 to dismiss.Thariq Shihipar★ 4,505
• lean-ctxThe LeanCTX cockpit (Select · Control · Prove sidebar, pulse line, turn and milestone overlays), wake on background job completion, remove redundant lean-ctx hook context, shape native Bash output, keep core tools in front, and show per-se…Thinkery / Yves Gugger★ 3,872
• terminal-browserA browser running directly inside claude code. Preview websites, view HTML documents, and let your agent control the built in browser.zenbu-labs★ 3,800
• token-optimizerThe Token Optimizer status bar on its own, for its tests. It ships inside the token-optimizer plugin.Alex Greenshpun★ 2,534
• cuelumeTwo cuelume sounds for Claude Code: ready when a long turn ends, attention when a permission prompt waits.Daniel Belyi★ 1,951
• reflect-modclaude-reflect as a Claude Code mod: a model check on each short prompt finds reusable corrections (any language); a band above the prompt saves them to CLAUDE.md on one pressBayram Annakov★ 1,703
• caliber-jev-compactionVerbatim Jev-guided compaction for Claude Code sessions.caliber-ai-org★ 1,298
• moai-boardRead-only side panel for the MoAI kanban queue, factory lanes and SPEC documents. Actions: refresh, open, pick (confirmed).MoAI-ADK★ 1,230
  1 more in this repository

  • moai-statusUsage/context warning strip, lane notification toast and health/status warning line. Strictly additive observer: draws only, never acts.MoAI-ADK★ 1,230
• crit-tuiEarly: crit inside Claude Code. Comment on the conversation, your diff or a file in a pane, send the review to Claude, and read Claude's replies in threads.Tomasz Tomczyk★ 1,196
• lcu-approveNative per-app approval for LCU computer use in the Claude app and Claude Code (Allow this conversation, Always allow, Deny), and the /computer-use-apps panel of approved apps.LCU★ 894
• ai-maestro-secretsLets an agent ask for a credential. You type it into a field in Claude Code; it goes to your local vault (aim-secret), never to the model or the chat.23blocks-OS★ 817
  1 more in this repository

  • amp-inbox-bandShows unread AMP messages above the prompt, in the status line and as a toast, and can wake an idle Claude Code session to read them. Needs Claude Code 2.1.287 or later.23blocks-OS★ 817
• storybloqProject memory for Claude Code and Codex. Storybloq stores tickets, issues, handovers, and lessons in a .story/ folder inside your repo.Amir Shayegh★ 765
• remctlApple Reminders in Claude Code: RemCTL's tools, plus today's tasks above the prompt in your lists' colors.Federico Viticci★ 595
• artifact-dashboardA one-line summary of the project's shared Kanban artifact above the prompt, read through Claude's own ArtifactData toolDanny McAteer★ 536
  6 more in this repository

  • assumption-ledgerGives Claude a register_assumption tool and shows the turn's assumptions, decisions and considered-but-not-done items above the promptDanny McAteer★ 536
  • mode-registryA shared /mode switch that any plugin can offer a mode to. Shows the active mode in the prompt footer. Makes no model calls.Danny McAteer★ 536
  • next-steps-supervisorAfter a turn that changed things, a forked check asks whether the goal was met, where it cut corners and what to do next, and draws the verdict above the promptDanny McAteer★ 536
  • quiz-afterAfter a turn that finished a task, a forked check writes 2-3 questions about what was built and draws them above the promptDanny McAteer★ 536
  • effort-modesOffers three modes through mode-registry: ui (low effort), api (medium) and review (max, for code review and security). Sets the main thread's effort per mode; makes no model calls of its own.Danny McAteer★ 536
  • my-modA starting point: registers /my-command at session start and answers it. Makes no model calls. Replace this line with what your mod does and what it costs per turn.Danny McAteer★ 536
• hello-modThe smallest Claude Mod: logs one line when the session starts and refuses one Bash command. Three files, no dependencies, exists so you can see the validator print a footprint.Karan Bansal★ 483
• jev-auto-compactJev-powered verbatim compaction: once context reaches 60%, prunes stale tool calls with zero generation. Skips (never falls back to the LLM summarizer) when nothing is prunable; records evidence for learning.db.vexjoy-agent★ 441
• context-levelGives Claude a tool that reads how much of the context window remains.Tobias Hagemann★ 408
• sutando-observerObserves the Claude main loop for HealthStatus and draws a compact status band above the promptSutando★ 396
• usage-beginnerPlain-language technical terms for beginnersaqua5230★ 338
  1 more in this repository

  • usage-dashQuota, Claude sessions and background jobs paneaqua5230★ 338
• promote-lightsShows CI status lights above the prompt while a promote PR (base main) is open. One REST page per minute, PR-open only. Cancelled is not-pass.OrchestKit★ 292
  5 more in this repository

  • secrets-veilMasks secret values in tool results before the model reads them: named vendor variables, value-shape patterns, and high-entropy tokens. No reveal path.OrchestKit★ 292
  • lesson-cardsDisplays lesson hint cards when tool calls match known patterns. Additive surface during pilot; the classic --strict guard keeps its 12 block-severity denies.Yonatan Gross★ 292
  • memory-lensRecalls the few memories related to each prompt: one line for the human, one context entry for the model. Local files only, no network on the hot path.Yonatan Gross★ 292
  • fn-hooks-canaryFixture-only plugin. Not shipped, not installed. Pins the Function Hooks module contract so CI notices when upstream moves it (orchestkit#3917).OrchestKit★ 292
  • tool-list-modProbe plugin for the R3 function-hook question: answers tool.list with one named tool removed and writes one marker file per call. Used by tests/probes/function-hooks-probe.sh.yonatangross★ 292
• codev-spikeEXPERIMENT #1782 spike: Codev guard, attribution scrub, context band and issue peek. Never installed; loaded only by an explicit --plugin-dir.Codev★ 288
• cortexdb-liveCortexDB inside Claude Code: haiku-planned auto-recall shown above the prompt, the brain on the status line, and durable facts captured while the session is idle. A mod: Claude Code only, needs the cortexdb plugin.Liang Li★ 275
• pii-guardDe-identifies personal data before it reaches the model and restores it on the way back out, by asking the resident pii-guard hookd service on loopback. Tool results are redacted, writes and shell commands are restored, a prompt's @ refere…pii-guard-tw★ 247
• compact-adviserSuggests (or, opt-in, runs) /compact at a completed checkpoint, judged by TypeSafe Jev. Its hooks module activates only when CLAUDE_CODE_ENABLE_FUNCTION_HOOKS is exactly 1 and is otherwise a complete no-op.Kun Chen★ 211
• shuntA Claude Mod for the shunt gateway: a band above the prompt shows how much of each window is used and the time to reset — the shared account pool's, read from shunt's GET /usage, or the session's own Claude rate limits off shunt — and /shu…Minsu Lee★ 209
• task-orchestrator-modOpt-in Claude Code mod for MCP Task Orchestrator: live work graph, gate band, and in-process orchestration hooks (early-access function-hooks API)Jeff Picklyk★ 208
• agentctlAgent Control Plane for one Claude Code session: task scope, evidence, hand-over. A control and a display, not an isolation boundary.sd0xdev★ 192
• better-statuslineThe status line above the prompt: the session's status and the music playing, one designEwen Gao★ 187
• agent-radarOne live line above the prompt per running subagent: time, tool count and what it's doing. /radar shows every agent and its messages.Hamza Zafar★ 184
  22 more in this repository

  • blast-radiusHolds risky Bash commands and shows what they would change before they run.Hamza Zafar★ 184
  • browser-lanesShows if this session has a Playwright browser and who holds it. /browser clean closes leftover browsers. A subagent that wants the browser waits until the one using it is done.Hamza Zafar★ 184
  • context-barYour context window as a stacked bar above the prompt, a color per category, with token counts and the compaction point. /context-bar shows or hides it.Hamza Zafar★ 184
  • glanceOne line above the prompt with what needs you: next meeting, PRs, Linear issues and Slack DMs. /glance lists them all.Hamza Zafar★ 184
  • md-previewShows the Markdown files Claude edits, rendered like GitHub, in a pane next to the chat. Before and after side by side. /md opens it.Hamza Zafar★ 184
  • merge-gateHolds `gh pr merge` until CI passes and one Codex review (OpenAI's luna model) has run. A PR line above the prompt, and /gate shows the PR's status.Hamza Zafar★ 184
  • mission-control/mission opens a live map of the main agent, its subagents and every tool call, plus a code map of the files they touch.Hamza Zafar★ 184
  • next-stepsAfter each turn, 2 or 3 likely next prompts above the prompt. Press 1, 2 or 3 in an empty prompt to draft one, 0 to dismiss.Hamza Zafar★ 184
  • now-playingWhat Spotify is playing, one line above the prompt: track, progress and the lyric being sung, with ⏮ ⏸ ⏭ buttons. /music controls it too. macOS.Hamza Zafar★ 184
  • openai-balanceYour OpenAI API credit above the prompt: an estimated balance with a gauge, today's spend, where the money mostly went, and the last call. /openai-balance shows the breakdown.Hamza Zafar★ 184
  • prayer-timesThe current prayer and how long is left, the next prayer, and zawal, above the prompt. Computed on your computer from your location; nothing is sent anywhere.Hamza Zafar★ 184
  • reelsYouTube Shorts in a terminal pane: plays while Claude works, pauses when Claude is done.Hamza Zafar★ 184
  • replay-theaterStep through the last turn's file edits, one diff at a time.Hamza Zafar★ 184
  • review-watchA live line above the prompt for each running code review: Codex or a review subagent, its model, what it reviews, time, and Codex's latest output. A toast with the findings when it ends.Hamza Zafar★ 184
  • rulebook-guardWriting and git rules: replaces em dashes in prose, and asks before git commit --amend, an unformatted push, or personal info in notes and commits.Hamza Zafar★ 184
  • session-saverNames untitled sessions through unpause. /park saves where you left off, and a resumed session shows it.Hamza Zafar★ 184
  • snakeSnake in a pane while Claude works, paused when it's done. Opt-in, so nothing opens until /snake.Hamza Zafar★ 184
  • switchboardPicks the model for each subagent that names none, with OpenAI's Decisions API or Jev, from its short label only. One line per spawn above the prompt; /route shows each pick and what each subagent cost.Hamza Zafar★ 184
  • token-weatherA live forecast of the context window, with a prompt-cache countdown, drawn above the prompt.Hamza Zafar★ 184
  • usage-meterYour plan's 5-hour and 7-day usage as small bars above the prompt, with the reset countdown and the session's cost.Hamza Zafar★ 184
  • where-am-iA live recap above the prompt: goal, doing now, waiting on you, next. /where for a longer one.Hamza Zafar★ 184
  • cache-clockA prompt-cache line under your status line: minutes left while warm, and how many tokens the next message re-caches once cold. /cache-clock setup adds it.Hamza Zafar★ 184
• clodfarmThe farm's messaging inside Claude Code: wakes an idle conversation for its mail, gates and logs SendMessage, and gives the model a msg toolclodfarm★ 176
• recallRecall Memory-as-a-Service — persistent memory, semantic search, and context management across Claude Code sessions. Connects to recallmcp.com or self-hosted instances.Jose Airosa★ 174
• voxAnimates a waveform in Claude Code while vox speaks or listensrtk-ai★ 164
• fast-jev-outputTrim long Bash output with Jev before the model sees it (Claude Code plugin)tamaratran★ 159
  2 more in this repository

  • jev-eval-observerPass-through evaluation instrumentation; never changes tool results.tamaratran★ 159
  • jev-long-session-observerCapture synthetic live-test evidence without changing Jev requests.Jev integration tests★ 159
• image-viewSee the images you paste into Claude Code: thumbnails above the prompt instead of bare [Image #1] tagsJarrod Watts★ 147
• hal-grammar-checkGrammar-check your prompt as you type, shown above the prompt boxVinta Chen★ 138
• edgeePick the model that serves this Claude Code session through the Edgee gateway: /edgee.Edgee★ 136
• filetreeAn IDE-style file tree for Claude Code that shows what Claude is doing and where in filesKurt Buhler★ 131
• blast-radiusHolds risky shell commands (rm -rf, git reset --hard, git clean, force push, migrations) and shows what they would change, with Proceed and Cancel buttons.Claude Code DevRel★ 127
  2 more in this repository

  • replay-theaterReplay Theater: step through the file edits Claude made in the last turn, one diff at a time.Claude Code DevRel★ 127
  • token-weatherA live forecast of the context window, drawn above the prompt: a weather icon, the fill percentage, and a chart of the last turns.Claude Code DevRel★ 127
• lane-stackSolo PM conveyor for Claude Code: orchestrator agents, lane playbooks, onboard and resume commands.VKirill★ 122
• agent-state-observerObserve-only: writes the agent's state (working / idle / awaiting_approval / ended), its transitions and its rate-limit readings to a JSON file. Never blocks, rewrites or delays anything.Marveen★ 117
• pulse-ccStock and crypto quotes above the Claude Code prompt, with a /pulse panel to manage your watchlist.fatwang2★ 113
• great-ctoYou already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 72 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and th…Alexander Velikiy★ 103
• winnowA calibrated context sieve for Claude Code. Every large tool result is judged by a System One model before it enters context; irrelevant blocks are replaced with a summary and a recall key.Ghaleb Dweikat★ 102
• intermissionPlay Doom deathmatch while Claude works, and get handed back when it's doneJarrod Watts★ 99
• cache-warmerKeeps an idle session's prompt cache warm with silent pings, then compacts large sessions once while the cache is still warm.samyakjain0606★ 97
• llm-router-receiptllm-router receipt band: after a turn served off Claude, keep it (k) or redo it on Claude (r); /router shows the last routing decisions.ypollak2★ 97
• genesis-web-overrideAnswers Claude Code's built-in WebSearch with Genesis's web_search chain, falling back to the built-in on any failure. Needs CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1.WingedGuardian★ 96
• mindful-claudeGuided breathing exercises above the prompt while Claude works: coherent, box, 4-7-8 and the physiological sigh, four animation styles, and the spinner reads the breath. Appears when Claude starts, disappears when Claude answers. Needs fun…Anthony★ 94
• wendy-modsWendy mods for Claude Code: verifies Wendy deploys and shows the connected device above the prompt.Wendy Labs★ 92
• glamour-darkDraws the model's text replies with charmbracelet/glamour's default dark stylePulkit Arya★ 77
  1 more in this repository

  • tool-linesDraws each tool call as one compact 'tool_call: Tool(input) - meta' line and hides its result blockPulkit Arya★ 77
• intenticCheaper, sharper Claude Code sessions: Bash output trimmed before Claude reads it, a project map and this project's field notes at session start, iq code search and fileq document reading taught, and /intentic:stats to show what each one s…intentic★ 77
  1 more in this repository

  • intentic-guardKeeps the sandbox's own decisions on tool calls final: a mod someone installs can neither answer nor overturn them.Intentic★ 77
• ctx-handoffHands off to a fresh conversation when context fills up, keeps the cache warm while you're away, and turns what you teach Claude into project notesCabLate★ 75
• transcripted-liveThe meeting Transcripted is recording, inside Claude Code: Claude gets the call as context, a live dashboard (now, asked of you, action items), prompt suggestions for questions aimed at you, and an after-call wrap-up that gains speaker nam…Transcripted★ 75
• hyday-petA virtual pet that lives above your Claude Code prompt and grows from the work Claude does: it evolves by what Claude does most, gets sick from tool errors, plays mini games, and spends coins in a shop. Requires CLAUDE_CODE_ENABLE_FUNCTION…Muki Wu★ 72
• console-statusClaude Console：跨專案 STATUS、Claude/Codex 派工、工作階段與用量總覽（含手機 Remote Control）SaM-runtime★ 69
• archcoreSpec-driven development and context engineering for AI coding agents, backed by project context in Git.Archcore★ 68
• abraA pixel Abra that lives at the right edge of the band above the promptdeniz gökçin★ 64
• reply-viewPreview pasted images and media from the last Claude reply, open links and localhost, and copy the whole reply.yrzhe★ 63
  1 more in this repository

  • translate-viewTranslate outgoing prompts and stream reply translations into a side pane with configurable LLM and Jev detection.yrzhe★ 63
• cortex-barShows Cortex Hub tool calls above the prompt as a stacked bar, one color per category, with /cs session progress, tokens in and saved, and hit@k for code lookups. Toggle with /cortex-bar, per-tool table and calls with /cortex-calls.Cortex Hub★ 60
• tw-stock-modWatchlist band above the Claude Code prompt: Taiwan hours show the Taiwan list (紅漲綠跌), US hours show the US list (綠漲紅跌), in a broker-style table with a Solari split-flap footer, plus a 損益 mode (P&L view) for your holdings. 20 symbols a mar…Darrell Wang★ 60
• localvoxtral-modShows whether localvoxtral is connected to this Claude Code session, puts dictated text in the prompt box, shows the dictation above the prompt, and ends a turn on your spoken stop phrase. A Claude Code mod: needs a Claude Code build that …localvoxtral★ 59
  1 more in this repository

  • localvoxtral-remotePublishes Claude Code session context from a REMOTE host to localvoxtral on your Mac, over an SSH RemoteForward tunnel. Command hooks running a bundled POSIX-sh shim that POSTs via curl — needs only sh and curl on the remote host, and fail…localvoxtral★ 59
• auto-handoffHands a Claude Code session off to a fresh one before the context fills: a Haiku-written brief, /clear, and a seed that points the new session at the brief.Alex Hillman★ 58
• savvy-progressProgress bar above the prompt for /savvy-flow, plus an agents panel (/agents-info): running, finished and planned subagents with model, task progress, context, cost and time.johnnyvizz★ 53
• phoneWatch and drive a phone, emulator or simulator in a pane, through the phone CLIluisnquin★ 51
• reviewer2In sessions opened at the Rev2Agent root, Reviewer 2 adds a one-line aside in a speech bubble above the prompt after each answer, beside an avatar whose expression fits it.Haebom Lee★ 51
• auto-handoffWrites a handoff document when a session has sat idle long enough that its prompt cache is about to go cold.Obie Fernandez★ 48
• compaction-triggerRequests a session compaction when the live context passes a token threshold, so verbatim compaction plugins run near the working ceiling instead of at the model window.Darkroom Engineering★ 47
  2 more in this repository

  • context-reportPrints which instruction files the engine loaded (tier, path, @ imports, size) once per context load, and hints when a project CLAUDE.md keeps its AGENTS.md from being read.Darkroom Engineering★ 47
  • drift-fuseScores each unattended turn against the task the person asked for with TypeSafe's Jev model, and after consecutive off-task turns redirects or pauses the next machine-submitted prompt.Darkroom Engineering★ 47
• cscs's in-session mod: the rotate band above the prompt, forced rotation past CS_ROTATE_FORCE_CTX, and the wrap keycs★ 47
  1 more in this repository

  • cs-updateRelease notes for a pending cs update, once per launch, with 1 to install it in place; /cs-update reopens the pane.cs★ 47
• session-inboxCollects what is waiting on you in a session: questions, Claude's notes and PR reviewspetekp★ 47
  1 more in this repository

  • think-firstAsks what you expect while a long task runs, then shows how your predictions hold uppetekp★ 47
• usage-statusMod that shows the remaining 5-hour session, 7-day weekly and context window usage as percentages in a row under the prompt, turning yellow when one runs low.Robert Terhaar★ 42
• jev-compact-gateJev decides when the session compacts, inside a 280k–400k token band; Claude's own summary does the compacting.Tom di Mino★ 41
• auto-handoffWrites a cold-start handoff to handoff/ before the context fills up or compacts, and offers to resume from it in the next session.Prompt Advisers★ 40
  12 more in this repository

  • changes-receiptA plain-English receipt after every turn: files created, changed and deleted, by tool or via shell, with failed attempts listed apart.Prompt Advisers★ 40
  • codex-computer-useRoute Claude's desktop computer use through Codex's computer-use engine, one Codex session per Claude session so threads can drive apps in parallel. Toggle with /codex-cu on|off.Prompt Advisers★ 40
  • context-meterContext window and session cost meter, drawn above the prompt.Prompt Advisers★ 40
  • flight-recorderSee inside a turn: a live Gantt timeline of model requests, tool calls and subagents, with tokens and cost per lane.Prompt Advisers★ 40
  • model-routerRoute supported subagent work to Sonnet or Haiku while keeping the main conversation on its model. /router for controls.Prompt Advisers★ 40
  • output-trayA side panel of the files this session created, with Open, Reveal in Finder and Copy path.Prompt Advisers★ 40
  • repo-heatmapWatch where Claude looks: a live treemap of the repo that lights up as files are read, searched and edited.Prompt Advisers★ 40
  • session-bookmarksExplicit bookmarks for Claude Code sessions you want to come back to. /bm saves one, /bm open lists them with a copyable resume command.Prompt Advisers★ 40
  • terminal-petA pixel-art crab above the prompt that reacts live to what Claude is doing. /pet for commands.Prompt Advisers★ 40
  • threadsA lead chat creates real Claude Code sessions on chosen models, watches them live and steers them.Prompt Advisers★ 40
  • coral-skinCoral, ink and cream reskin of Claude Code with risk-coded tool rows. Toggle with /skin.Prompt Advisers★ 40
  • read-counter-exampleTeaching example: count successful Read events.Prompt Advisers★ 40
• cc-arcadeGames above the Claude Code prompt (snake, Tetris, 2048, Minesweeper, Flappy, Pong, typing test, Space Invaders, Doom) plus a pet that grows as Claude tests, commits and edits. Clones of the genre, not affiliated with or endorsed by Tetris…Seza Akgün★ 40
• superpowers-vCompound V for Superpowers: triple parallel pre-flight (code archaeology + domain-expert advisor + library/doc validator — Context7 MCP when the session has it attached, WebSearch/WebFetch otherwise), disjoint file partitioning, manifest-d…Oleg★ 40
• corgi-bandA band above the prompt: corgi sessions waiting on you elsewhere (with Focus), and what this turn posted, moved or pushed - each with a tick or the errorAndrii Klymiuk★ 37
  1 more in this repository

  • corgi-guardStops the Bash shapes that fail in corgi runs (zsh set -- $pair, rm -rf on corgi worktrees) and adds the corgi fix to errors it knowsAndrii Klymiuk★ 37
• paste-previewSee and mark up the images you paste into Claude Code: thumbnails above the prompt and in the transcript, and an editor that opens on pastealan890104★ 36
• ailang-brandAILANG look for Claude Code: the AILANG version beside the prompt hint, compiler-flavoured spinner words (Unifying…, Inferring effects…), and /ailang for a pane with the logo.AILANG★ 35
  6 more in this repository

  • ailang-inbox-bandUnread AILANG fleet messages above the prompt: a band with the count and newest title, an /ail-inbox pane with Ack, a toast when one arrives. For the person only; message text never reaches the model. Requires the `ailang` binary on PATH.AILANG★ 35
  • ailang-lensLive view of AILANG as it is written: after each edit of a .ail file, a pane shows the module's functions, their types and effect rows (pure or !{IO,FS,...}) and any type errors, keeping the last good signatures beside a broken edit. A Cla…AILANG★ 35
  • ailang-check-on-editAfter Claude edits or writes a .ail file, runs `ailang check` from the project root and adds any errors to what the model reads after the tool result, so it sees its own type errors without spending a turn. Works in interactive and headles…AILANG★ 35
  • prepush-gateRuns the repo's CI gates (gofmt on tracked Go roots, make lint, make check-file-sizes when defined) before `git push` / `gh pr create|merge`, and denies the push with the failing output. Skipped where there is no Go; AILANG_SKIP_PREPUSH=1 …AILANG★ 35
  • sprint-statusStatus line for AILANG sprint work: the most recently touched in-progress sprint under .ailang/state/sprints, its milestones passed and the next one.AILANG★ 35
  • unowned-dirtyWarns when a git add/stash/checkout/restore/reset may sweep dirty files this session did not write (shared checkouts have several agents). A toast for the person, a note in the model's context; never blocks. Port of the pi extension of the…AILANG★ 35
• hopeThinking discipline for AI work. Clarify intent, shape approach, consult experts, guard unsupervised work, hand work back so you own it. The slop hook needs CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1.Saad Shahd★ 35
  1 more in this repository

  • hunchA grab bag of hunches — experimental skills and plugin features tried here before they earn a place in hope or sound. Everything graduates or dies. The tend mod needs CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1.Saad Shahd★ 35
• image-peekPreview pasted images at their prompt markers on macOS. Ghostty, plus experimental iTerm2 and Herdr support with a startup override. Claude Code 2.1.287+.Karan Bansal★ 35
  2 more in this repository

  • fable-pinPins every subagent to the fable model: rewrites the model on agent.spawn unless the spawn is a fork, with /fable-pin on, off and status. Touches nothing but its own store. Needs function hooks (early access).Karan Bansal★ 35
  • probe-mod[probe] Loaded headlessly by mod-builder so the engine writes the running build's types. Not a mod to install.mod-builder★ 35
• kindex-modernRepo-local Kindex memory and durable tasks for Claude function hooks (Claude Code mod, 2.1.287+)Wander★ 35
• aimuxEvery aimux subscription's 5-hour and weekly usage above the prompt, a warning before this one runs out, and one Enter to move onDigital Threads★ 30
• project-sentinel-demoDevelopment only: plays a scripted turn of real tool calls, without a model, for Control Room screenshots.Arjun0014★ 30
• harness-modsHarness Mod layer: heartbeat/canary, native usage, rewrite explanations, measured subagent accounting, supervisor routing, secret redaction. Modes per guard in ~/.claude/mods/mods-config.json (classic | shadow_mod | mod).Wes Sander★ 28
  20 more in this repository

  • claude-runtimeShared Claude runtime adapter: normalises function-hook events into ClaudeRuntimeEvent, exposes $.runtime (emit bus, supports, judge, snapshot) to other plugins, and writes a JSONL event logWes Sander★ 28
  • costclaw-liveCOSTCLAW LIVE: per-request cost, cache decay and repeated-read detection while the session runs, and it serves the Nth identical Read of an unchanged file from its own cache instead of paying for itWes Sander★ 28
  • probe-uiInteractive UI probe: ui.render components, toast, status, log, pane, command registerucsandman★ 28
  • prodguardPRODUCTION GUARD: ambient project/environment context + a transport-independent policy core (DashClaw evidence classifier + offlocal policy engine) enforced natively on tool.call and tool.check. Blocks, asks, or contains before the command…claude-mods-rnd★ 28
  • spike-handoffSpike: safe-boundary handoff (bundle written at turn.complete from the runtime bus) and $.turn.abort semanticsWes Sander★ 28
  • supervisorSUBAGENT SUPERVISOR: routing-and-budget Mod. Rewrites a spawn's model onto the capability graph instead of denying it, keeps a measured per-agent-type token ledger in $.store, caps tool calls per subagent, and shows live subagents + the la…Wes Sander★ 28
  • benchBenchmark: classic settings hooks vs function hooks per tool callucsandman★ 28
  • probeFunction-hooks probe: proves modules load and events fire headlesslyucsandman★ 28
  • probe2Interception probe: deny, rewrite, replace result, delay, throw, register tool, classifyucsandman★ 28
  • probe3Permission override, subagent visibility, agent.spawn model rewrite, turn.step routing, prompt context injectionucsandman★ 28
  • spike-compactSpike: does $.session.compact() work from a plugin, and what does the session.compact event carry?Wes Sander★ 28
  • spike-describeSpike: does a tool.describe rewrite reach the model, does agent.offer hide a type, does prompt.suggest fire?Wes Sander★ 28
  • guardianGUARDIAN: executable policy that protects lab/demos/protected/** from Write/Edit/Bash, whatever CLAUDE.md saysucsandman★ 28
  • matrixMATRIX: freezes a harmless tool call before it runs, shows what Claude intended, asks you, then continues or denies. /matrix on|offucsandman★ 28
  • benderREALITY BENDER: intercepts a harmless tool result and alters what Claude receives; prints REAL vs RECEIVEDucsandman★ 28
  • blackboxBLACK BOX RECORDER: structured per-session timeline of prompts, model steps, tool calls, subagents and denials; /blackbox prints itucsandman★ 28
  • tunnel-costMIDDLEWARE TUNNEL stage 2: Cost analyzer: estimates the call's token cost from the args sizeucsandman★ 28
  • tunnel-observerMIDDLEWARE TUNNEL stage 1: Observer: sees the call first, stamps t0, prints what entersucsandman★ 28
  • tunnel-policyMIDDLEWARE TUNNEL stage 3: Policy: allows everything harmless; denies a matching ruleucsandman★ 28
  • tunnel-telemetryMIDDLEWARE TUNNEL stage 4: Telemetry: records the call and its result for the ledgerucsandman★ 28
• delegation-driftCounts main-thread work since the last subagent dispatch, nudges the model to delegate at every tenth call, and refuses foreground poll loops.BioInfo★ 27
  3 more in this repository

  • read-firstClears the engine's 'File has not been read yet' error: Edit reads the file and retries; Write hands the model the file's head with the error.BioInfo★ 27
  • rollback-noticeWhen a gate denies a Bash call, tells the model the whole call was rolled back and must be re-run in full; refuses git commit -F from shared /tmp.BioInfo★ 27
  • secrets-guardDenies writes to secret files and writes whose content carries a credential, with the reason shown.BioInfo★ 27
• jev-permission-gateUses TypeSafe's Jev to allow or deny routine tool calls in auto mode, and hands uncertain ones to the built-in classifierMadison Rickert★ 27
• homie-persona-cognitionHost-bound cognitive lifecycle events for The Homie.TheSmokeDev★ 26
• show-your-workClaude shows its finished work right in the chat: screenshots, videos of it clicking through your app, and synced before/after QAUmer Ansari★ 24
• pi-agent-for-claudepi agent for claude: a `pi` subagent type whose model steps run the pi CLI, so pi subagents and agent-team teammates live in Claude Code's own agent UI, streamed live.Fazal Ali★ 23
• roof-modReplace Claude Code's built-in reminders with your own words: silence four nags, rename 'the user' in template sentences, drop the CLAUDE.md preamble.Awen★ 23
  1 more in this repository

  • roof-probeRead-only probe: lists system prompt sections and reminder types into /tmp/roof-probe-log.jsonAwen★ 23
• jevCheap, fast, typed AI judgments inside Claude Code via the jevctl CLI (verify, screen, find, classify, extract, rerank, match, route, ask, batch), plus verbatim Jev-guided context compaction that replaces the built-in summary.Nasr Shaer★ 22
• claude-jevHands the small judgments in a session to TypeSafe's Jev, a System One model that returns typed answers instead of generating text: what kind of request each prompt is, which model tier a subagent needs, whether an edit breaks a rule alrea…0x7067★ 21
• prompt-railA rail of your session's prompts beside the transcript or above the prompt; hover to read one, click to jump to it.oikon48★ 21
• cc-image-viewSee the images you paste into Claude Code: thumbnails above the prompt instead of bare [Image #1] tagsgggodlin★ 20
• explain-as/explain: get answers as ASD-STE100 prose, a diagram, an HTML page, or a 3b1b-style videoSumit Paul★ 20
• status-bandStatus band above the prompt: directory, git, model, effort, cost, rate limits and context.whatyouhide★ 20
• stoaNext plugin generation (experimental), replaces dstoicdstoic★ 20
  1 more in this repository

  • modtestSandbox for Claude Code mods experiments (not published)dstoic★ 20
• force-push-guardRefuses git push --force before it runsKen Kousen★ 19
• paste-viewSee what you paste into Claude Code: image thumbnails and long-text previews above the prompt instead of bare [Image #1] and [Pasted text #2] tagsClément Décou★ 19
• statuslineContext tokens, session cost, and estimated cache expiry above the prompt in the Desktop appDavid Crespo★ 19
  1 more in this repository

  • session-costA tool the model calls to report the session's cost, for remote control where /cost isn't availableDavid Crespo★ 19
• wp-credential-guardMasks WordPress usernames and Application Passwords in prompts with session-scoped placeholders, and restores them into Bash commands at execution time.Nathan Onn★ 19
• thimbleA browser workspace beside a Claude Code session for making sense of a corpus of files: chat, files, a canvas of cards and a report. Start it with the `thimble` command, which runs Claude Code with this plugin: the session is the main thre…Matthew Joerke★ 18
  2 more in this repository

  • thimble-cc-modA single-agent thimble inside Claude Code: answers drawn as cards between the reply's text, citations you can open and check, and verification scripts on request. An exploration.thimble exploration★ 17
  • thimble-termthimble's terminal-mode renderer: it draws thimble's cards, citations, labels, agents, side threads, documents and files in Claude Code. It only draws; the `thimble` command loads it in terminal mode.thimble★ 18
• uploadsHost screenshots, GIFs, recordings, and files on uploads.sh and embed them in GitHub PRs and issues.Build Internet★ 18
• usage-quotaKnow your Claude limits before they hit you (Live band above the Claude Code prompt): 5 Hour and Weekly usage (whole account) with a live usage forecast against limit resets, context window usage, one-click Compact and per-session Auto com…Anant Raghunath★ 18
• cache-meterGauges how long the conversation's prompt cache stays warm, its hit ratio and misses, and what the next message re-caches once it has gone coldHolyGrail★ 17
  4 more in this repository

  • notice-boardShares notices with every session in the same repository, or on the machineHolyGrail★ 17
  • pr-relayWatches the session's pull request and wakes the session when it is merged or Codex reviews itHolyGrail★ 17
  • usage-meterShows context, 5-hour, weekly and per-model weekly limit usage above the promptHolyGrail★ 17
  • zsh-safeLets Bash commands written for bash run under zsh: unmatched globs, leading =, and a missing timeoutHolyGrail★ 17
• idle-compactCompact once after 50 idle minutes, while the 1h prompt cache is still warm.takahirom★ 17
• image-viewSee the images you paste into Claude Code as big previews above the prompt instead of bare [Image #1] tagsjoshhu★ 17
• temperClaude cannot write code before you approve the intent. Gated plan, TDD, review and check for AI written code, with a phase bar in Claude Code.galando★ 17
• xcode-modsXcode in Claude Code: build, run and tests pane, scheme/destination band, notifications and SwiftUI previews over headless Xcode MCPArtem Novichkov★ 17
• agent-flowThe agent flow pane: /flow opens a live tree of the session's subagents and teammates beside the transcript, fed by engine events, with a text fallback where no pane can be drawn.Charles Tao★ 16
• flightdeckFlightdeck: a live agent dashboard for Claude Code. Main model vitals, an on-call architect, every permission check, subagent cards and swimlanes, a turn receipt and a session log, all from real session eventsStephen Casella★ 16