537 security Claude Code mods, most popular first. The most popular is ruflo-agent. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| ruflo-agent Agent runtimes for ruflo — local WASM-sandboxed agents (rvagent: 10 wasm_agent_*/wasm_gallery_* MCP tools, bui | 76.1k ★ | Low risk |
| ruflo-agentdb Substrate plugin for Ruflo memory: AgentDB controller bridge (15 agentdb_* MCP tools), RuVector ONNX embedding | 76.1k ★ | High risk |
| ruflo-aidefence AI safety scanning, PII detection, prompt injection defense, and adaptive threat learning | 76.1k ★ | Low risk |
| ruflo-bbs-federation AgentBBS cross-host agent federation for ruflo (ADR-164). Phase 1 exposes room coordination — federation_bbs_r | 76.1k ★ | Low risk |
| ruflo-browser Session-as-skill browser automation: Playwright + RVF cognitive containers + ruvector trajectories + AgentDB s | 76.1k ★ | Low risk |
| ruflo-business-pods ADR-164 Phase 2 — business-domain pod templates for the federated business autopilot. Ships the sales pod temp | 76.1k ★ | Low risk |
| ruflo-chatgpt-federation Dedicated ChatGPT Federation MCP publisher with isolated Nostr signing-key custody, OAuth-scoped publishing, a | 76.1k ★ | Low risk |
| ruflo-console ruflo's cockpit inside Claude Code and the one /ruflo command for every ruflo mod (function hooks, early acces | 76.1k ★ | High risk |
| ruflo-federation Cross-installation agent federation with zero-trust security, peer discovery, consensus-based task routing, an | 76.1k ★ | Low risk |
| ruflo-jujutsu Advanced git workflows with diff analysis, risk scoring, change classification (feature/bugfix/refactor/...), | 76.1k ★ | Low risk |
| ruflo-knowledge-graph Knowledge graph construction — entity extraction, relation mapping, and pathfinder graph traversal. As a mod ( | 76.1k ★ | Low risk |
| ruflo-loop-workers Cache-aware /loop workers and CronCreate background automation — wraps 5 hooks_worker-* MCP tools (list/dispat | 76.1k ★ | Low risk |
| ruflo-market-data Market data ingestion — feed normalization, OHLCV vectorization, and HNSW-indexed pattern matching. As a mod ( | 76.1k ★ | Low risk |
| ruflo-metaharness MetaHarness integration for ruflo — surfaces score/genome/mint/mcp-scan/threat-model via skills; pairs with @m | 76.1k ★ | Low risk |
| ruflo-migrations Schema migration management — generate, validate, dry-run, and rollback database migrations. As a mod (ADR-445 | 76.1k ★ | Low risk |
| ruflo-mods ruflo as a Claude Code mod (function hooks, ADR-404): in-process prompt routing, edit learning signals, tighte | 76.1k ★ | Review before installing |
| ruflo-music AI music generation via Cognitum Music (cogmusic MCP) — compose lyrics/prompts, generate tracks, separate stem | 76.1k ★ | Low risk |
| ruflo-neural-trader Neural trading via npx neural-trader — self-learning strategies, Rust/NAPI backtesting, 112+ MCP tools, swarm | 76.1k ★ | Low risk |
| ruflo-observability Structured logging, distributed tracing, and metrics — correlate agent swarm activity with application telemet | 76.1k ★ | Low risk |
| ruflo-rag-memory RuVector memory with HNSW search, AgentDB, and semantic retrieval. As a mod (ADR-445): a write guard that keep | 76.1k ★ | Low risk |
| ruflo-ruvector Self-learning vector database via npx ruvector@0.3.3 — HNSW, adaptive LoRA embeddings, code-graph clustering, | 76.1k ★ | Low risk |
| ruflo-ruvllm RuVLLM local inference with chat formatting (Claude/GPT/Gemini/Ollama/Cohere), model configuration, MicroLoRA | 76.1k ★ | Low risk |
| ruflo-rvf RVF format for portable agent memory, session persistence, and cross-platform transfer. As a mod (ADR-445): a | 76.1k ★ | Low risk |
| ruflo-security-audit Security review, dependency scanning, policy gates, and CVE monitoring | 76.1k ★ | Low risk |
| code-modernization Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, th | 41.9k ★ | Review before installing |
| lesson-cards Displays lesson hint cards when tool calls match known patterns. Additive surface during pilot; the classic -- | 296 ★ | Low risk |
| secrets-veil Masks secret values in tool results before the model reads them: named vendor variables, value-shape patterns, | 296 ★ | Low risk |
| rulebook-guard Writing and git rules: replaces em dashes in prose, and asks before git commit --amend, an unformatted push, o | 268 ★ | Review before installing |
| code-modernization Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, th | 155 ★ | Review before installing |
| jevmem-pane A side pane for Claude Code beside your chat: what jevmem recalled for this prompt, what its guard decided, an | 128 ★ | Review before installing |
| cache-guard Keeps the prompt cache warm while idle and holds the first prompt after the cache went cold, with its cost. | 93 ★ | Low risk |
| lang-guard Flags Russian words and plain-language slips (em-dash asides, 40+ word sentences, aphorisms) in Bulgarian answ | 93 ★ | Low risk |
| secret-redactor Hides tokens, keys and passwords in tool output as ‹secret:N›, restores them in later tool calls, blocks readi | 93 ★ | Low risk |
| ssh-guard Refuses ssh/scp/rsync to hosts listed in memory decommissioned_hosts.md; "# decommissioned-ok" overrides. | 93 ★ | Review before installing |
| subagent-models Pins subagent models to a model-routing policy (Opus for judgement, Haiku for mechanical work, Sonnet otherwis | 93 ★ | Low risk |
| read-only-mode Toggle a reminder guard that refuses built-in mutating tools and Bash. | 76 ★ | Low risk |
| secret-box Claude can use a secret without seeing it: a masked box saves keys to .env and gives Claude a placeholder, eve | 72 ★ | High risk |
| transcript-redactor Keeps secrets and email addresses out of the session transcript: swaps each one for a stable placeholder on th | 72 ★ | Low risk |
| oh-my-fable Anthropic's prompting-guide rules for Claude Code, always on (Opus 5.5, Fable 5.1; Sonnet 5.5, Haiku 5.5, Opus | 58 ★ | Low risk |
| project-sentinel Project Sentinel keeps long Claude Code runs on track: a status bar, the Control Room panel, Context Autopilot | 53 ★ | Review before installing |
| hope Thinking discipline for AI work. Clarify intent, shape approach, consult experts, guard unsupervised work, han | 38 ★ | Review before installing |
| collision-guard Asks before Claude edits a file another open chat changed in the last 30 minutes: Proceed, Move to a worktree, | 37 ★ | High risk |
| recording-mode /rec before you record: masks keys, personal details, and business figures on screen and keeps private files c | 37 ★ | Review before installing |
| jev-permission-gate Uses TypeSafe's Jev to allow or deny routine tool calls in auto mode, and hands uncertain ones to the built-in | 32 ★ | Review before installing |
| context-budget Measures a Claude Code session's fixed startup context payload per item at a pinned binary version, including | 26 ★ | Low risk |
| context-guard Per-session context-window observability. A mod writes each session's context-window figures to a snapshot fil | 26 ★ | Review before installing |
| display-redaction A mod that masks email addresses and secret-shaped text in what Claude Code draws, for recordings and screen s | 26 ★ | Low risk |
| harness-ops Claude Code operations: audit-skill-visibility (skills the listing budget hides), inventory (every invocable s | 26 ★ | Review before installing |
| rate-limit-guard Shared rate-limit guard for loop lanes and Claude: a hooks module writes the subscription rate-limit windows t | 26 ★ | Review before installing |
| lemo-guard 限时：Claude 单轮工作超时自动中止 · 等你确认的时间不计 · 默认关闭，在「安全」页开启 / Time limit: stops Claude when a turn runs over time · time | 24 ★ | Low risk |
| harness-mods Harness Mod layer: heartbeat/canary, native usage, rewrite explanations, measured subagent accounting, supervi | 22 ★ | Review before installing |
| guardian GUARDIAN: executable policy that protects lab/demos/protected/** from Write/Edit/Bash, whatever CLAUDE.md says | 22 ★ | Low risk |
| tunnel-policy MIDDLEWARE TUNNEL stage 3: Policy: allows everything harmless; denies a matching rule | 22 ★ | Low risk |
| probe2 Interception probe: deny, rewrite, replace result, delay, throw, register tool, classify | 22 ★ | Low risk |
| prodguard PRODUCTION GUARD: ambient project/environment context + a transport-independent policy core (DashClaw evidence | 22 ★ | Low risk |
| supervisor SUBAGENT SUPERVISOR: routing-and-budget Mod. Rewrites a spawn's model onto the capability graph instead of den | 22 ★ | Low risk |
| code-pet A pixel pet that lives in a pane and reacts to what Claude does: eats on tool calls, gets sick on failures, pa | 15 ★ | Low risk |
| launch-codes Dangerous Bash commands need launch codes: red alert pane, siren, a code to arm and a LAUNCH to fire | 15 ★ | Low risk |
| faultline KOZMOS Faultline: the error lens in a sidebar. Every failed or denied tool call, refused or errored turn and A | 13 ★ | Low risk |
| helm KOZMOS Helm: one-press settings profiles in a sidebar. Seven built-in ways of working (Token saver, Fast flow, | 13 ★ | Review before installing |
| warden KOZMOS Warden: a guard for destructive shell commands. Before Claude or a subagent runs rm -rf on a broad path | 13 ★ | Low risk |
| redact 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。 | 12 ★ | Low risk |
| gemini-review Has Gemini review every git commit the model runs, from the staged diff and the conversation, and stops a comm | 11 ★ | Review before installing |
| git-commit Ships a commit skill and holds every Bash git commit to it: a commit the skill did not open, a blanket git add | 11 ★ | Review before installing |
| storage-guard After an edit that keeps browser data in localStorage or sessionStorage, names each line, so the model stores | 11 ★ | Review before installing |
| commonplace LLM-maintained knowledge base for Obsidian vaults. Auto-triggers on paper sharing, vault health queries, conce | 11 ★ | High risk |
| aicq AICQ for Claude Code: your agents and friends' agents, their collaborations and what needs you. Notices messag | 10 ★ | Review before installing |
| budget-guard Holds a prompt back once your 5-hour or weekly usage is at or over a limit you set (90% by default); sending i | 10 ★ | Low risk |
| collision-guard Asks before Claude edits a file another chat on this machine changed in the last 30 minutes. Each chat keeps i | 10 ★ | Review before installing |
| loop-guard Holds back a shell command once when the exact same command already failed twice in a row, and tells Claude to | 10 ★ | Low risk |
| reread-guard Stops Claude re-reading a file it already read in this conversation, with Read or a plain cat, sed -n, head, t | 10 ★ | Low risk |
| write-guard Steers Claude to Edit instead of rewriting an existing file in full with Write: the first rewrite in a convers | 10 ★ | Low risk |
| budget-guard Stops a session before it runs past a budget. Three figures are guarded, each with a limit you set: the sessio | 9 ★ | Review before installing |
| taxi-speedcam 위험한 Bash 명령 앞의 과속 단속 카메라: force push·rm -rf·DB 삭제·변경 폐기·운영 배포를 찰칵 잡아 [가주세요]/[세워주세요]로 묻습니다 | 9 ★ | Low risk |
| guardrails Clickable safety rules with presets: block rm -rf, force-push, destructive git, secret files, sudo, installs, | 9 ★ | Low risk |
| code-mode Code mode for MCP: the model writes one JavaScript program that calls MCP tools in a sandbox, instead of one t | 7 ★ | High risk |
| jev-guard Probability-scored guardrails for Claude Code: deny rule-breaking edits and unasked-for deploys, route your ow | 7 ★ | Review before installing |
| cc-token-optimizer Claude Code token optimizer — read de-dup, output trimming, cold-start guard, model-tier nudges, plus a live t | 7 ★ | Low risk |
| guardrails Blocks shell commands you pick in /config: Cloudflare cf writes, attribution lines in commits and PRs, claude/ | 6 ★ | Low risk |
| loop-guard Tells the model, out of the user's sight, to stop when the same call fails twice with the same error | 6 ★ | Low risk |
| secret-guard Keeps secrets out of the conversation: hides API keys and private keys before the model or the transcript sees | 6 ★ | Low risk |
| mod-maker Find what you ask Claude again and again, then build a mod that does it for you: /mod-audit, /mod-build, /mod- | 6 ★ | High risk |
| secrets-guard Stops Claude reading .env and key files, masks API keys in command output, and lets you hand Claude a key thro | 6 ★ | Low risk |
| squad-chat The all-in-one Claude Code plugin. Talk with your squad, share code, and keep live rooms (usage, git, weather, | 6 ★ | Review before installing |
| screen-guard Masks sensitive names, orgs and secrets in the transcript for screen sharing; /mask toggles, click a mask to r | 6 ★ | Review before installing |
| autodev-core Autonomous development workflow: brainstorm, auto, audit, review, ship, plus the prd.json sprint system. | 6 ★ | Low risk |
| cockpit Agent cockpit for Claude Code: live context, limits, cost, tools, files, tests and a guard for risky commands | 6 ★ | Review before installing |
| orc Full-SDLC Claude Code plugin — plan → implement → QA → ship → CI → release, with root-cause debugging, inciden | 6 ★ | Review before installing |
| goblin-chrome Goblin-mode's face inside Claude Code: a goblin in the band that reacts to the session and holds a prop for th | 6 ★ | Review before installing |
| honmoon-redact Client-side secret/PII redaction hooks: keep API keys and sensitive identifiers out of Claude Code's model con | 6 ★ | Review before installing |
| decision-popup Decision popup: Claude asks every decision (approve/refuse, A or B, irreversible steps) as a one-key question, | 6 ★ | Low risk |
| public-repo-guard Push guard: before a git push to a public GitHub repo (or making one public) it scans what would go out for Su | 6 ★ | Review before installing |
| supabase-guard Supabase guard: stops Supabase calls aimed at a project other than the current folder's, and asks in a one-key | 6 ★ | Low risk |
| loop-guard Stall detector per agent loop: 5 identical tool calls in a row warn that loop and leave the session-state.json | 6 ★ | Review before installing |
| latex Render TeX math, TikZ diagrams and LaTeX blocks in Claude Code's desktop app, in any of 10 LaTeX fonts, with e | 6 ★ | High risk |
| glanceflow GlanceFlow: see what Claude is doing, at a glance. Hides tool rows and shows one plain-English checklist above | 5 ★ | Review before installing |
| pdpa-thai Helps reduce personal data sent to Claude: redacts detected Thai and international personal data before sendin | 5 ★ | Low risk |
| ultramod The best all-in-one mod pack for Claude Code: a usage limits and context HUD, a guard with undo for rm -rf and | 5 ★ | Review before installing |
| dash-guard Refuses prose that Claude writes with an em dash, an en dash or a double hyphen, and tells Claude which lines | 5 ★ | Low risk |
| shared-file-guard Refuses a shell write to a shared file (STATUS.md, CLAUDE.md, MEMORY.md, or the files you name) that this sess | 5 ★ | Low risk |