Plugin Claude Code
Infrastructure and operations specialists: reverse proxies and web servers (HAProxy, nginx, Caddy, Traefik), container runtimes (Docker, Podman), and the systemd service manager.
Agent
Expert in Caddy (current stable v2.11), the Go web server with automatic HTTPS. Use when writing/reviewing/debugging Caddyfiles or JSON config, automatic TLS (ACME, on-demand, internal CA), reverse proxying, directive ordering and matchers, the admin API, or building custom modules with xcaddy. Pairs with…
Agent
Expert in Docker (Engine , Compose v2), the container platform. Use when writing/reviewing/debugging Dockerfiles, Compose files, image builds (BuildKit/buildx), container networking and volumes, or runtime/security config. Pairs with specialist:podman (the rootless drop-in alternative) and specialist:systemd (running…
Agent
Expert in HAProxy (current stable release line 3.4 LTS, released June 2026; 3.3 is the newest odd/stable line, 3.4/3.2/3.0 are the maintained LTS lines), the reliable, high-performance TCP/HTTP load balancer and reverse proxy. Use when configuring, reviewing, or debugging HAProxy: the…
Agent
Expert in nginx (open source, current stable 1.30.4 / mainline 1.31.3), the web server, reverse proxy, and load balancer. Use when writing/reviewing/debugging nginx configuration: server/location blocks and matching, reverse proxying and upstreams, TLS/HTTP2/HTTP3, caching, rate limiting, rewrites, and the stream…
Agent
Expert in Podman (current stable 6.0.x), the daemonless, rootless-first container and pod engine. Use when running/reviewing/debugging rootless containers, pods, Quadlet systemd units, Compose compatibility, Netavark networking, or the containers.conf/storage.conf/registries.conf config. Pairs with specialist:docker…
Agent
Expert in systemd (current release v261), the Linux service manager and init system. Use when writing/reviewing/debugging unit files (service/socket/timer/mount/path/target/slice), service hardening and sandboxing, cgroup v2 resource control, socket/timer activation, journald logging, user services, or drop-in…
Agent
Expert in Traefik Proxy (open source, current stable v3.7), the dynamic, provider-driven reverse proxy and ingress controller. Use when configuring/reviewing/debugging entrypoints, routers, services, and middlewares; the Docker/Kubernetes/file providers; label-based Docker config; automatic HTTPS via ACME resolvers…
Plugin Claude Code
IOTA L1 protocol specialist: the Move-based, object-centric blockchain, its Rust monorepo, framework, RPC servers, indexer, CLI, and SDKs.
Agent
Expert in the IOTA L1 protocol (github.com/iotaledger/iota), the Move-based, object-centric blockchain. Use when building, reviewing, or debugging code in the iota monorepo (validator/fullnode, Move framework, JSON-RPC/GraphQL/gRPC servers, indexer, CLI, Rust SDK) or its siblings iota-rust-sdk and ts-packages. Covers…
Plugin Claude Code
Spec, plan, execute, snapshot, resume. Four slash-commands for multi-session work, with artifacts kept in a knowledge base outside the working repo. No hooks, no auto-invocation.
Skill Claude CodeCodex
Use when starting a new project or a substantial change that needs a written spec and plan before any code. Runs Q&A with the user, dispatches code-explorer and code-architect, writes spec and plan to the knowledge base, and gets an adversarial review before implementation. Not for small or mechanical changes - those…
Skill Claude CodeCodex
Use when picking up a plan that was interrupted, in a fresh session. Finds the newest checkpoint for the project in the knowledge base, verifies its claims against the actual tree before trusting them, reports any drift, and continues execution from the stated next action.
Skill Claude CodeCodex
Use when executing a written implementation plan from the knowledge base in a fresh session. Reads the spec and plan, works the tasks in order, checks them off in place, and keeps the expensive gates off the hot path. Pair with /plan:snapshot to stop cleanly and /plan:resume to pick up an interrupted run.
Skill Claude CodeCodex
Use when interrupting a plan that is mid-execution - the user stops the run, context is getting long, the machine needs a reboot, or the session is ending unfinished. Writes a verified snapshot to the knowledge base so a fresh session can resume without rediscovery. Read by /plan:resume.
Plugin Claude Code
Language-agnostic security auditor: attack-surface mapping and attacker-exploitable findings grounded in CWE, OWASP, and CVE/RustSec advisories.
Agent
Language-agnostic security auditor. Maps a codebase's attack surface (interfaces, trust boundaries, entry points) and finds attacker-exploitable issues, grounded in CWE, OWASP Top 10 / ASVS, and CVE/RustSec advisories. Use when threat-modeling a change, auditing a service or library for vulnerabilities, reviewing an…
Plugin Claude Code
SQL specialist: query optimization, schema and index design, execution-plan analysis, and platform-specific features across PostgreSQL, MySQL, SQL Server, SQLite, and Oracle.
Agent
Expert SQL developer specializing in complex query optimization, database design, and performance tuning across PostgreSQL, MySQL, SQL Server, SQLite, and Oracle. Use when writing, reviewing, or optimizing complex queries, designing schemas/indexes, analyzing execution plans, planning migrations, or working through…
Plugin Claude Code
Operator skills for Stackpit, the self-hosted, single-binary drop-in replacement for Sentry event ingestion: guided setup (with or without Docker, SQLite or Postgres), goal-driven reconfiguration (OIDC/OAuth SSO, org/role mapping, email/Slack/webhook alerts, filter modes, Postgres migration), and a best-practice…