Claude Code Mods

ruvnet/ruflo

Local WASM and managed cloud runtimes with bounded dynamic workflows, live capability discovery and session-local mod policy.

ruvnet/ruflo

AI safety scanning, PII detection, prompt injection defense, and adaptive threat learning

ruvnet/ruflo

Domain-Driven Design scaffolding — bounded contexts, aggregate roots, domain events, value objects, repositories, and anti-corruption layers; navigable domain graph stored in AgentDB

ruvnet/ruflo

DeepSeek model harness for ruflo — agents, commands, scripts, and skills for running and evaluating DeepSeek-backed workflows within the ruflo swarm.

ruvnet/ruflo

Cross-installation agent federation with zero-trust security, peer discovery, consensus-based task routing, and per-call budget circuit breaker (ADR-097)

ruvnet/ruflo

Long-horizon goal planning, deep research orchestration, and adaptive replanning using GOAP algorithms

ruvnet/ruflo

IoT device lifecycle, telemetry anomaly detection, fleet management, and witness chain verification for Cognitum Seed hardware

ruvnet/ruflo

RuVector 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 shows

ruvnet/ruflo

Run 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/ruflo

Security review, dependency scanning, policy gates, and CVE monitoring

ruvnet/ruflo

SPARC methodology — Specification, Pseudocode, Architecture, Refinement, Completion phases with gate checks

ruvnet/ruflo

Test gap detection, coverage analysis, and automated test generation — drives the testgaps background worker via hooks_worker-dispatch; SPARC Refinement-phase canonical owner

ruvnet/ruflo

Persisted workflows, native orchestration and discovery of the optional managed cloud runtime.

oliverow/catch-me-up

A side pane with a live catch-up summary of your Claude Code session: why it started, what was done, where things stand, and what needs you

jonpojonpo/cc-crayon

Colorful replies: themed Markdown plus inline <t color bold italic> tags the model can write, drawn with real Ink Text styling

MikeGT4/agent-tree

Terminal side pane that shows a session's agents as a live tree: stop a sub-agent, send it new instructions mid-task, switch its model and effort, change the look.

xuanji86/claude-agentpane

A side pane for Claude Code that lists the subagents a session runs, what each is doing and what it costs in tokens, with each one's conversation a click away.

GGGODLIN/cc-mod-park

/park a session you will come back to; a new session in the same folder offers it back with one click.

Mucida/critical-decisions

Shows you, above the prompt, the critical decisions the agent made without being asked: red to rethink, yellow to know, each with a rethink button. Works out of the box for any kind of project; /critical-areas auto lets the agent learn what is critical in yours.

Akramovic1/jev-pilot

TypeSafe's Jev decides how Claude Code works on each prompt: the main conversation's reasoning effort (low to xhigh, raised to max mid-turn when tool calls keep failing), each subagent's model, whether to split the work across subagents, and the one skill the prompt needs. Brings in custom OpenRouter models (a junior coder reviewed by Opus, or cheap bulk work) and Codex or OpenCode as reviewers, in modes you choose, each health-checked. Reads the prompt with recent context, records every decision, and suggests its own tuning. Backends: OpenRouter, TypeSafe's API, the Vercel AI Gateway, or Claude Code's built-in classifier. Built on claude-code-templates' jev-model-router and jev-skill-suggestion.

alonbaron/claude-skills

Live session and Workflow tracker: main-thread turns, skills fired, spawned subagents, git commits and workflow stages with models, effort, tokens and timeline waterfall, drawn only in a side pane.

hamzafer/claude-code-mods

Shows 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.

bekir1184/agent-crew

Shows your subagents above the prompt as pixel-art Claude crew members: what each one is doing, how far along it is and how many tokens it used.

KilimcininKorOglu/claude-code-mods

Keeps the 1-hour prompt cache warm for a window you set, or with no end in every session under always, with one cache-shared fork per idle stretch and one keep-warm message after a resume, arms a window for you after a paid cold write, and shows the cache state, the cold price and this session's cold writes.

davekiss/mods

Know when main is broken before you build on it: a red row above the prompt says how long your repo's default branch has been failing CI and how many pushes landed on top, and the agent is told too.

drkokorev/context-diet

Trims huge tool outputs (logs, JSON, diffs, grep, file lists) before they reach Claude's context, and saves the full text to a file Claude can read

KilimcininKorOglu/claude-code-mods

Moves compaction from Claude to Gemini: in summary mode Gemini summarizes the conversation and the newest messages stay verbatim, in prune mode every message stays and Gemini keeps, cuts or drops older tool calls. Off until /gemini-compact on; gemini-core holds the key, tier, model and thinking level.

mishgoldenberg/claude-mods

Clickable safety rules with presets: block rm -rf, force-push, destructive git, secret files, sudo, installs, network; lock Claude to the project folder or read-only; add your own block patterns.

davekiss/mods

Find where your Claude Code week went and fix it: /leaks ranks the avoidable spend in your transcripts with one-press fixes, and a strip above the prompt flags a leak while it happens.

mishgoldenberg/claude-mods

Notices when Claude is going in circles (the same command failing again and again, the same code rewritten over and over) and tells Claude to step back and rethink, and tells you too.

oztrkemree/mochi

Mochi Buddy: a clay mascot above the prompt that reacts to everything Claude Code does, in 16 languages

VedantAndhale/claude-pro-kit

/nudge <goal> applies behavioral design to a product or flow: diagnose why users don't act, design interventions that remove barriers, ranked hypotheses to test, and an ethics check on every answer. Its guide reaches Claude only when you run /nudge.

VedantAndhale/claude-pro-kit

An Improve button above the prompt (and /polish) rewrites your draft with Opus at low effort (/polish model picks another) using the prompt-master rules (MIT, nidhinjs/prompt-master); Undo puts the original back. Each press is one model call; its exact tokens are shown.

thkt/dotclaude

Read ツールの結果に含まれる認証情報の形をした文字列を、モデルが読む前に伏せる。

avansaber/tailtest

tailtest auto-generates and runs tests for every file your AI agent edits in Claude Code. R1-R15 rule layer + adversarial test mode (V13).

bruw/workflow-conductor

Terminal UI for planning, running and understanding complex agent workflows inside Claude Code.

YeonwooSung/my-claude-code-mods

Persistent pinned memos and clickable todo checkboxes above the Claude Code prompt

alexandernicholson/agent-router

Choose a model and effort for five agent roles and for agent team teammates with /agent-models, and inspect routing and usage. Requires Claude Code Mod function hooks enabled.

Aitherium/awdk

Compacts a long tool result through the AitherOS decision door before the model reads it: per LINE SHAPE, learned from outcomes, never dropping a traceback or a summary line.

Aitherium/awdk

awsh for Claude Code: an `aw` subagent type whose model steps are answered by a session on the local awsh harness daemon, so any harness and any backend the daemon can drive runs as a native Claude Code subagent, streamed live. Also carries the Aither World skills, the `aither` output style, MCP servers for installed bricks and portable brick hooks.

Arunjay4213/claude-mods

Stops a session before it runs past a budget. Three figures are guarded, each with a limit you set: the session cost in dollars, the 5-hour plan window and the 7-day plan window. It says nothing until a figure nears its limit, then pins a status line and warns once; past the limit it refuses tool calls and asks before sending another prompt. /guard shows the state and changes the limits.

rbinar/cli-dispatch

Delegate tasks to the right worker CLI — multi-backend delegation hub. Backends: DeepSeek-powered Claude Code (claude-ds), Antigravity / Gemini (agy, ag-agent), OpenAI Codex CLI (codex, cx-agent), OpenCode via OpenRouter (opencode, oc-agent), GitHub Copilot CLI (copilot, cp-agent), and a local Ollama model (ol-agent). Setup-time backend selection, deterministic runner (cli-dispatch-run — worker + verify with zero LLM babysitter tokens), single-command ds/ag/cx/oc/cp/ol-agent, session tracking (live monitoring + resume), read-only mode (Codex only — real OS-level sandbox; OpenCode/Copilot have no sandbox equivalent, isolation is via git worktree only), global MCP isolation, runtime/idle timeout safety net, fully-agentic tasks in isolated worktrees, optional auto-install of missing worker CLIs (`--install-missing`/`-InstallMissing`, opt-in).

KuiyiGao/deepcrew

The /deepcrew skill to lead a crew, the crew's requests answered above your prompt, and /crew to see the whole crew

JrCx7scC/claude-code-fanyi

Write to Claude Code in your own language while Claude works in English: prompts are translated to English, and each reply gets a streamed translation underneath.

mpolatcan/flowpane

A live workflow pane: replaces the default Workflow progress list with a phase-by-phase graph or a timeline beside the transcript, showing each agent's state, timing, live token spend, tool calls, what it is saying, and prompt.

alexandernicholson/agent-router

A prompt cache bar for every conversation, subagent and teammate, a dashboard with /keepalive, per-conversation cache TTLs, and upkeep that keeps an idle cache warm or compacts it before it expires. Requires Claude Code Mod function hooks enabled.

ice-lfernandes/claude-code-mods

Plan limits, cache clock and context above the prompt: model and effort, 5-hour and weekly windows with reset times, a countdown of the prompt cache with an opt-in keep-warm that spends plan, context split by group (system, MCP, messages), tokens per turn, and a toast on a costly model switch near the limit

Arunjay4213/claude-mods

Shows the subscription plan limits - the 5-hour window, the 7-day window and a gateway spend limit - as a pinned status line under the prompt, with a reset countdown and a projection of when you would hit 100% at the pace of the last few samples. /quota opens a pane with a bar, the reset clock time and the burn rate for each window.