Claude Code mod
review-gate
The review gate as a tool.check function hook. Every shell call is decided in process, so the non-commit calls -- almost all of them -- cost no subprocess at all, and a blocked commit can be put to you as a question instead of refused outright. The decision itself is still bin/review-gate, run only for a command that mentions a commit, so both routes read the same receipts and cannot disagree.
Install
/plugin marketplace add rlorenzo/ai-coding-setup
/plugin install review-gate@ai-coding-setupMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: runs processes, reads files, reads env vars, draws
- Hooks
tool.check
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
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.
Details
- Repository
- rlorenzo/ai-coding-setup
- Folder
mods/review-gate- Marketplace
ai-coding-setup- Author
- Rex Lorenzo
- License
- MIT
- Last updated
- 28 September 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is review-gate?
The review gate as a tool.check function hook. Every shell call is decided in process, so the non-commit calls -- almost all of them -- cost no subprocess at all, and a blocked commit can be put to you as a question instead of refused outright. The decision itself is still bin/review-gate, run only for a command that mentions a commit, so both routes read the same receipts and cannot disagree. It is a mod for Claude Code, from rlorenzo/ai-coding-setup on GitHub.
What can the review-gate mod access?
Its widest reach is "writes or runs" (runs processes, reads files, reads env vars, draws). Like any mod, it runs with your permissions.
How do I install review-gate?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add rlorenzo/ai-coding-setup and then /plugin install review-gate@ai-coding-setup.
Is review-gate popular?
rlorenzo/ai-coding-setup has 1 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 28 September 2026.
More context & usage mods
regia
1purpleheads2026/Mod_claude
A graphic control room for Claude Code: a live radar of agents, skills and tools, with context and usage limits, in motion.
savvy-progress
1lippdev/lippstack
Agents panel (/agents-info): running, finished and planned subagents with model, context, tokens and time, plus the account plan quota (5h and weekly). Fork of johnnyvizz/claude-kit savvy-progress with new Clawd costumes.
quota-band
1kuan0808/cliproxy-kit
Account, quota, context and cache cards above the Claude Code prompt, with handoffs and a warning before a turn rewrites the prompt cache; quota and routing come from CLIProxyAPI with the quota-pilot plugin
session-cards
1alan-oliv/claude-mods
Session stats above the prompt: repo folder, branch and session name, then cards for model, effort, context, startup, limits and cost
quanta-costa
1wukonigcom/quanta-costa
Quanta Costa: your Claude subscription period, weekly limit with a pace forecast, session cost and plan value, as bars right above the Claude Code prompt.
session-hud
1anderson-spider/claude-mods
A card above the prompt: model, the repository, folder and branch, context and cache; the five-hour and seven-day limits with their pace; the running subagents with their type, model and effort, and the tokens they used; what the last turn sent and added, edits and errors; when turned on, next steps to tick and put in the prompt; and /session-panel, a pane with every agent the session ran and the last 15 minutes.
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.