By stebennett
Safety guardrails and convenience auto-approvals for Claude Code: blocks destructive commands, protects critical dotfiles and credentials, prevents secret leaks and force-pushes, and auto-approves read-only/test/build commands.
github.com/stebennett/nyx-claude
A personal Claude Code plugin marketplace — a small collection of plugins used with Claude Code, published so they can be installed the same way as any other marketplace.
Add the marketplace, then install the plugins you want:
/plugin marketplace add stebennett/nyx-claude
/plugin install <plugin>@nyx-claude
Once added, plugins appear in /plugin and update when the marketplace is refreshed.
| Plugin | What it does |
|---|---|
code-safely-plugin | Safety guardrails + convenience auto-approvals: blocks destructive commands, protects dotfiles/credentials, keeps secrets out of git, prevents force-pushes, and auto-approves provably read-only/test/build commands. See its README. |
kanban | Placeholder — not yet implemented / not registered. |
.claude-plugin/
marketplace.json # Marketplace manifest — lists every published plugin
plugins/
<plugin>/
.claude-plugin/plugin.json # Plugin manifest (name, version, description)
commands/ agents/ skills/ # Optional, auto-discovered components
hooks/hooks.json # Optional event hooks
A plugin is discovered only once it is both present under plugins/ and listed in .claude-plugin/marketplace.json.
plugins/<name>/.claude-plugin/plugin.json with name, version, and description.commands/, agents/, skills/, hooks/hooks.json, .mcp.json — all optional)..claude-plugin/marketplace.json under plugins with a source pointing at its directory.${CLAUDE_PLUGIN_ROOT} so they resolve regardless of install location.Matches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
npx claudepluginhub stebennett/nyx-claude --plugin code-safely-pluginDeveloper-workflow automation for Claude Code. Its first skill, 'renovator', autonomously drains a repository's open Renovate dependency PRs — merging provably-safe green patch/minor updates through a cheap haiku agent and parking major-version and red-CI updates with PR state annotations for review.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Comprehensive SEO analysis plugin for Claude Code. 25 sub-skills (21 core + 1 orchestrator + 1 framework + 2 extension mirrors) and 18 sub-agents cover technical SEO, content quality, schema, sitemaps, Core Web Vitals, local SEO, backlinks, AI/GEO, ecommerce, hreflang, SXO, clustering, drift monitoring, and Google APIs. Includes optional MCP extensions, SPA-aware rendering, portability, and hardened SSRF/DNS-rebinding safe fetchers.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use