dryvist/ai-assistant-instructions
Agent Claude Code
Fallback executor, used only when codex-quota exits 1 (Codex runs first otherwise), for scoping, bulk reads, triage, mechanical shipping and implementation chunks delegated by a lead session. Runs at xhigh effort, never below high; reports evidence to the file the prompt names. Brief it completely: it knows only its…
dryvist/ai-assistant-instructions
Agent Claude Code
Fallback strong-reasoning executor, used only when codex-quota exits 1 (Codex runs first otherwise), for architecture, cross-system design and security judgment delegated by a lead session; never for read-only scouting or routine implementation. Runs at medium effort; proves claims with source and live evidence…
Plugin Claude Code
Bundles 7 skills · 403 tokens together
Harness-agnostic session continuity: goal statements, status snapshots, cold resume, replanning, and wrap-up. No git or GitHub required.
Plugin Claude Code
Bundles 7 skills · 347 tokens together
Delegate tasks to AI models, orchestrate premium-model work, and run autonomous maintenance loops.
Plugin Claude Code
Bundles 1 skill · 30 tokens together
Estate-specific code conventions not covered by generic review skills: logging format, monitoring-vs-test philosophy, doc format.
Plugin Claude Code
Bundles 2 skills, 1 command, 3 agents · 77 tokens together
Systematic CodeQL alert analysis and resolution for GitHub Actions workflows.
Plugin Claude Code
Bundles 2 skills · 129 tokens together
Combined content validation and guard plugin: token-validator, markdown-validator, readme-validator, webfetch-guard, issue/PR backlog limiter, public-repo leakage guard, and script/wrapper-generation guards.
Plugin Claude Code
Bundles 7 skills · 299 tokens together
Git main branch synchronization, troubleshooting, and post-merge cleanup workflows.
Plugin Claude Code
Bundles 18 skills · 1,049 tokens together
PR finalization (single, repo-wide, or org-wide including bots), repo refresh, rebase-merge, merge, review thread resolution, issue shaping, issue sweeping that reconciles open issues against reality, and diagnosing silent GitHub Actions failures.
Plugin Claude Code
Bundles 9 skills · 511 tokens together
Operational runbooks for infrastructure state, maintenance, and recovery: monitoring-first checks, Proxmox VE cluster operations, DNS ingress convergence, secrets-engine identity bring-up, Terrakube operations, PXE netboot installs, LLM router operations, workstation off-box backup, Dell iDRAC BMC operations, and…
Plugin Claude Code
Bundles 3 skills · 63 tokens together
Cross-repo infrastructure orchestration for Terraform and Ansible workflows.
Plugin Claude Code
Bundles 1 skill · 34 tokens together
Infrastructure standards for Proxmox, Terraform, Ansible: VMID/IP assignment ranges and the Terraform-to-Ansible inventory contract.
Plugin Claude Code
Bundles 2 skills · 112 tokens together
OpenBao-backed secrets access model: mint ephemeral credentials from secrets engines instead of storing static ones, read with the pre-authorized tier, and route write/apply through a human-gated wrapped single-use secretid.
Plugin Claude Code
Bundles 4 skills · 148 tokens together
Claude skill authoring standards, workspace management, and skills/tools registry lookup.
Plugin Claude Code
Raise a local macOS banner for every PushNotification call and every attention-needed Notification event.
Plugin Claude Code
Bundles 1 skill · 23 tokens together
Specific to the maintainer's own setup and not intended for general use.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: