Claude Code guard & safety mods

Stop, hold or rewrite risky tool calls, protect secrets and ask before deploys. Most popular first.

576 mods · showing 1–48

Pane & dashboard modsContext & usage modsGit & GitHub modsMemory & instructions modsNotification & sound modsSpinner, theme & fun modsWorkflow modsStatus linesHooksSlash commandsPlugins & marketplacesWorkflow kitsOutput stylesThemes & HUDsNotifications & soundsDesktop, web & mobile appsUsage & cost trackersSessions & historyModel routers & proxiesMulti-agent & worktreesEditor integrationsConfig & memory
  1. 1secrets-veilyonatangross/orchestkitMasks secret values in tool results before the model reads them: named vendor variables, value-shape patterns, and high-entropy tokens. No reveal path.300
  2. 2flightdeckscasella/claude-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 events216
  3. 3vibeclaudetranskatgirl/vibeclaudeFeel every Claude Code lifecycle event through Intiface Central / buttplug.io. Streaming output, edits, tool results, permission prompts and turn completion are mapped to vibration pulses.161
  4. 4secret-boxray-amjad/claude-code-modsClaude can use a secret without seeing it: a masked box saves keys to .env and gives Claude a placeholder, every key a tool prints comes back as a placeholder, and committing .env is refused101
  5. 5transcript-redactorray-amjad/claude-code-modsKeeps secrets and email addresses out of the session transcript: swaps each one for a stable placeholder on the way in, and puts the real value back on the way into a tool call101
  6. 6tool-linesTickloop/claude-modsDraws each tool call as one compact 'tool_call: Tool(input) - meta' line and hides its result block83
  7. 7so-hudKanevry/session-orchestratorSee Session Orchestrator status, warnings and session beacons in Claude Code ($.so contract v1), with protection gates for secret-printing commands, rule traps, outward actions and scope collisions.52
  8. 8ruflo-browserruvnet/rufloSession-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 a status file the console shows.80k
  9. 9ruflo-x-gatewayruvnet/rufloCoordinate 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.80k
  10. 10fuse-statuslinefusengine/agentsResponsive statusline mod for Claude Code (function hooks, no command hooks); figures computed by the core-guards statusline engine34
  11. 11jev-permission-gatemadisonrickert/jev-permission-gateUses TypeSafe's Jev to allow or deny routine tool calls in auto mode, and hands uncertain ones to the built-in classifier32
  12. 12ruflo-rvfruvnet/rufloRVF 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 shows80k
  13. 13extra-modsJhonatan-de-Souza/ClaudeModsAn extra-mods menu in the bottom corner: Zen mode with a progress band, Claude Code themes from terminalcolors.com, model, effort and permission mode controls and a status line.26
  14. 14ruflo-knowledge-graphruvnet/rufloKnowledge 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 shows80k
  15. 15prodguarducsandman/Agnostic-AIPRODUCTION 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 runs. /prodguard24
  16. 16ruflo-observabilityruvnet/rufloStructured 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 shows80k
  17. 17helmersinkoc/claude-modsKOZMOS Helm: one-press settings profiles in a sidebar. Seven built-in ways of working (Token saver, Fast flow, Max quality, Plan first, Guarded, Autopilot, Quiet focus) plus your own saved setups; each shows exactly what it changes, lets you leave any step out, applies /config rows the way the menu does, saves effort for the model in use at once, and every activation can be undone. /helm toggles it; <profile>, apply <profile>, save <name>, rm <name>, undo, list.21
  18. 18ruflo-protectorruvnet/rufloProject 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.80k
  19. 19zsh-safeHolyGrail/claude-modsLets Bash commands written for bash run under zsh: unmatched globs, leading =, and a missing timeout19
  20. 20ruflo-migrationsruvnet/rufloSchema 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 shows80k
  21. 21clock-guardnekyialabs/claude-code-toolkitCompanion to the clock mod: drops a clock wake that arrives twice for the same firing, which can happen when Claude Code replaces a lost hooks worker and replays a timer's prompt submit. Guard by Ray and Starling.14
  22. 22ruflo-aidefenceruvnet/rufloAI safety scanning, PII detection, prompt injection defense, and adaptive threat learning80k
  23. 23guardrailsmishgoldenberg/claude-modsClickable 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.12
  24. 24redactthkt/dotclaudeRead 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
  25. 25debriefsxhmilyoyo/sundayhao-pluginsA debrief block closes substantial turns; the band above the prompt draws the latest one as a card, with Copy and Pin, and a "me, on your word" step is a draft prompt.9
  26. 26coadavebream/claude-of-alexandriaRigorous analytical skills for biblical study, exegetical analysis, and faithful application. Built with TDD methodology to prevent AI exegetical malpractice.8
  27. 27public-repo-guardSzotasz/claude-modsPush guard: before a git push to a public GitHub repo (or making one public) it scans what would go out for Supabase project IDs, keys, tokens, emails, local paths, private repo names and .env files, and asks in a one-key popup. /pushor toggles. Hungarian or English.8
  28. 28honmoon-redactpleaseai/honmoonClient-side secret/PII redaction hooks: keep API keys and sensitive identifiers out of Claude Code's model context by redacting Read/Bash/Grep tool output, blocking prompts that carry secrets, and denying reads of known credential files. Session-transcript scrubbing verified on Claude Code 2.1.263 (updatedToolOutput is what gets persisted); re-verify on other versions.7
  29. 29jev-guardmuratcakmak/jev-guardProbability-scored guardrails for Claude Code: deny rule-breaking edits and unasked-for deploys, route your own docs into each prompt, and check the final answer against the turn's own evidence.7
  30. 30latexzaahiral/claude-latexRender TeX math, TikZ diagrams and LaTeX blocks in Claude Code's desktop app, in any of 10 LaTeX fonts, with every LaTeX compile sandboxed7
  31. 31mdviewxuanji86/claude-mdviewClick a .md path in the Claude Code conversation to read it rendered as markdown beside the session, pictures included, and point at any block to have Claude edit it.7
  32. 32mermaid-modngothanhluc/claude-mermaid-modDraws ```mermaid blocks in Claude's replies as Unicode diagrams, in place7
  33. 33ultramodmertkayacs/ultramodThe best all-in-one mod pack for Claude Code: a usage limits and context HUD, a guard with undo for rm -rf and git reset --hard, .env and secret protection, and a receipt for every turn.7
  34. 34read-only-modewhyashthakker/awesome-claude-code-modsToggle a reminder guard that refuses built-in mutating tools and Bash.109
  35. 35doomreporails/arcadeDoom in a Claude Code pane: Freedoom on the doomgeneric engine, a real picture in kitty and Ghostty and block characters elsewhere, played with the keys and the mouse while Claude works. Prebuilt engines for Linux, macOS and Windows.6
  36. 36pdpa-thaiBoom-Vitt/boombignose-modsHelps reduce personal data sent to Claude: redacts detected Thai and international personal data before sending and masks it on screen. Detection runs locally and the mod makes no network calls of its own; the redacted conversation is still sent to your configured model provider (Anthropic by default). Best effort, not legal advice.6
  37. 37lang-guardescapeboy/claude-code-kitFlags Russian words and plain-language slips (em-dash asides, 40+ word sentences, aphorisms) in Bulgarian answers; reminds Claude.97
  38. 38chartshashd1ve/agent-chartsInline terminal charts for Claude Code: ```chart blocks in Claude's replies render as line, bar, column, heatmap, calendar, candle, pie, gauge, box, waterfall and sparkline charts5
  39. 39dotnet-pilotzdanovichnick/dotnet-pilot.NET development plugin for Claude Code — Roslyn semantic analysis, DI/architecture/EF Core guards, convention-aware scaffolding, TDD agents, security and performance review, and project lifecycle commands.5
  40. 40flightdeckahmadhammoud56/MOAAFlightdeck: 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 events5
  41. 41mermaid-drawgalElmalah/claude-modsMermaid diagrams in Claude Code: every ```mermaid block Claude writes is drawn as box art, in colour, right where the fence was in the transcript. Needs function hooks (early access) and an interactive terminal.5
  42. 42cannibal-guardNicoSKOOL/seo-modsStops Claude from creating a new page whose target keyword an existing page already covers or ranks for (local pages + DataWise).4
  43. 43copy-blocksimakarov/claude-copy-blocksOne-click copy for Claude's drafts in the terminal: emails, LinkedIn posts, Telegram and Slack replies, commands. Exact text, no extra spaces or broken lines to fix after pasting4
  44. 44flysuperfly/sprites-claude-pluginManage Fly.io apps, Machines, volumes, secrets, Managed Postgres, and Sprites through the hosted Fly MCP server.4
  45. 45lexisavinofiore/lexiTest-first workflow for coding agents, without the spec ceremony. A PreToolUse hook keeps source edits behind a mirror test and protects existing assertions; the flow drives one vertical slice at a time, red to green, through the project's own gate. Ships its own tdd and grill skills; includes the Jev layer (model and effort routing, compaction, review), required like ponytail and the interface (usage row, gate, subagents); requires ponytail for the implementation step and caveman for terse output.4
  46. 46signet-eval-functionswandercom/signet-evalOptional Claude Code 2.1.274 and 2.1.280 function hooks for Signet-eval policy and output redaction4
  47. 47slop-filterNicoSKOOL/seo-modsBlocks AI slop in website copy: scores every page Claude writes for AI tells and SEO cliches (English and Spanish) and makes Claude rewrite it.4
  48. 48slopsquat-guardSingh-AP/awesome-claude-modsStops Claude from installing hallucinated or typosquatted packages: every npm, pip, uv, poetry, cargo and gem install is checked against its registry first. Packages that don't exist are blocked; brand-new, barely used or lookalike packages ask you first.4

How Claude Code mods work

  • A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
  • It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
  • Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
  • Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Claude Code docs →