Git (Reference) vs claude-human-review
Git (Reference) is an MCP server published by modelcontextprotocol. Marketplaces we read that list it: 1 (Docker MCP Catalog). claude-human-review is a plugin bundle for AI coding tools published by IrtezaAsadRizvi. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). As of our marketplace pass on 2026-10-15. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |   Git (Reference) |  claude-human-review |
|---|---|---|
| Docker MCP Catalog | Listed Version: sha256:ad6af958e794 Forks (GitHub): 11 790 Pulls (Docker Hub): 168 237 Stars (Docker Hub): 30 Stars (GitHub): 91 268 Not marked · First seen |
Not listed |
| Claude Code: claude-plugins-community | Not listed | Listed Version: 0.1.0 Forks (GitHub): 0 Stars (GitHub): 15 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | Git (Reference) | claude-human-review |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 91 268 (better) | 15 (worse) |
| Pulls (Docker Hub) (differs) | 168 237 | No figure on Docker Hub |
| Forks (GitHub) (differs) | 11 790 (better) | 0 (worse) |
| Last release | Not published | Not published |
| Where it runs (differs) | On your machine (mcp/git) | Installs as a plugin bundle |
| Transport (differs) | stdio | Not stated |
| Tools it declares (differs) | 12 | Not published |
| Environment variables it asks for | Not published | Not published |
| Hooks it runs (differs) | Not published | 3 |
| Parts of the bundle (differs) | Not a bundle | 4 |
| Licence (differs) | NOASSERTION | MIT |
| Repository (differs) | github.com/modelcontextprotocol/servers | github.com/irtezaasadrizvi/claude-human-review |
| Changes in the last 7 days | 0 | 0 |
| First seen | 2026-10-11 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
Git (Reference)
Git repository interaction and automation.
claude-human-review
claude-human-review adds a human approval gate at the end of every Claude Code turn that edits files. When Claude tries to stop, the plugin pauses it and has Claude do two things before the turn ends. First, drop a one-line doc comment on any class, function, or non-obvious config block it created or materially changed, using the right style per language (JSDoc for TS/JS, docstrings for Python, // for Go, and so on). Second, write a short plain-English review of what changed and why, flagging risks the diff alone won't show.\n You reply with 1 (Approve) to keep the changes or 2 (Undo) to roll them back. Undo is deterministic: filesystem snapshots are taken before each edit, so it works in git repos, non-repos, and folders full of untracked files. State lives on disk, so it survives Claude's context compaction on long sessions.\n The review is tuned to stay around 60 to 120 words per turn and skips sections when they would be filler, so the extra output-token cost is small. Inline comments are capped to one li
How to run each
Git (Reference) As a local MCP server: Docker image
claude mcp add --transport stdio git -- docker run -i --rm mcp/gitclaude-human-review As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install claude-human-review@claude-communityCommands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
The marketplaces of claude-human-review publish no list of tools, so we do not compare tools.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: Git (Reference) · What it can do: claude-human-review · Compare two other plugins
Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.