Claude Code plugins for LLM second opinions, security triage, documentation upkeep, and pre-commit setup.
This repository also configures its own agents. See what claude-toolz tells them →
Plugin Claude Code
Bundles 1 skill, 1 command · 118 tokens together
Get a second opinion from Codex, Antigravity, or DeepSeek — three different vendors. Standard-library Python script with no dependencies and no install step; the Codex and Antigravity agents need no API key at all. Available as the /ask-llm command and as a model-invoked skill.
Plugin Claude Code
Read-only check for pre-commit setup state. Detects missing pre-commit binary, uninstalled .git/hooks/pre-commit, and unreachable Docker daemon when the config requires it. Walks you through approval-gated installs via SessionStart and PostToolUse:EnterWorktree hooks.
Plugin Claude Code
Bundles 1 skill, 1 command · 146 tokens together
Resolve GitHub security alerts (Dependabot, code scanning, secret scanning) across pip / pip-tools / poetry / uv / npm / cargo / go-modules / Docker / GitHub Actions ecosystems. Opens PRs for manual review. Available as the /resolve-github-alerts command and as a model-invoked skill.
Plugin Claude Code
Bundles 1 skill, 2 commands · 147 tokens together
Revise and audit CLAUDE.md, README.md, and docs//.md. /revise-all-docs captures session learnings; /improve-all-docs runs a static quality audit.
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: