claude-human-review
Irteza v0.1.0
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 en...
From the developer
License
MIT
Works with
Claude Code
Description
From the marketplace listing
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 line per symbol and skipped entirely for trivial helpers, tests, and already-documented code. The goal is a short lesson on your own codebase every time Claude edits it, not a wall of text.
What changed
No changes recorded yet. Follow this plugin to keep track of future changes.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Find recurring email and make it stop with Claude. Scan inbox exports, review brand-by-brand in chat, then unsubscribe one item at a time...
Shared terms: approval, stop, review, per
-
Beads development for humans — a structured, human-controlled development pipeline with task tracking, code review gates, and multi-agent...
Shared terms: gate, human, review, code
-
Comprendo gates AI implementation behind a visual developer approval step. When you type /comprendo <task>, Claude reads your codebase, b...
Shared terms: approval, gate, why, review
-
Structured AI development workflows for Claude Code. Enforces planning, approval, task tracking, and code review gates through MCP — so A...
Shared terms: approval, gate, review, code
-
Upload, share and transfer files instantly from Claude Code. Drag-drop file sharing with end-to-end encryption. No signup or API key requ...
Shared terms: drop, end, file, code
Keywords
Files & skills
claude-human-review · catalog manifest
Saved declaration
{}
claude-human-review · catalog manifest
Saved declaration
{
"name": "claude-human-review",
"source": {
"sha": "ef74813509aab3368c404bd3b3ae6e882754968e",
"url": "https://github.com/IrtezaAsadRizvi/claude-human-review.git",
"source": "url"
},
"homepage": "https://github.com/IrtezaAsadRizvi/claude-human-review",
"description": "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\npauses 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\nblock it created or materially changed, using the right style per language (JSDoc for TS/JS, docstrings for Python, // for Go, and so on).\nSecond, write a short plain-English review of what changed and why, flagging risks the diff alone won't show.\\n\n\nYou reply with 1 (Approve) to keep the changes or 2 (Undo) to roll them back. Undo is deterministic: filesystem snapshots are taken before\neach 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\ncompaction on long sessions.\\n\n\nThe 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\nsmall. Inline comments are capped to one line per symbol and skipped entirely for trivial helpers, tests, and already-documented code. The\ngoal is a short lesson on your own codebase every time Claude edits it, not a wall of text."
}
claude-human-review · catalog manifest
Saved declaration
{
"name": "claude-human-review",
"author": {
"url": "https://github.com/IrtezaAsadRizvi",
"name": "Irteza"
},
"license": "MIT",
"version": "0.1.0",
"homepage": "https://github.com/IrtezaAsadRizvi/claude-human-review",
"keywords": [
"review",
"approval",
"undo",
"human-in-the-loop",
"code-review",
"hooks",
"skill",
"safety"
],
"repository": {
"url": "https://github.com/IrtezaAsadRizvi/claude-human-review.git",
"type": "git"
},
"description": "Force a human review gate after every Claude turn that edits files. Summarizes what changed and why, drops one-line doc comments on touched classes and functions, then waits for the developer to Approve or Undo."
}
plugin.json observed Nov 6, 2026 · 10:42 UTC. Manifest source ↗
Catalog declarations and available plugin.json metadata are saved. Referenced skills and executable source files are not downloaded or tested. Missing components in a manifest do not prove that the plugin has none.
Installation instructions
Community
/plugin marketplace add anthropics/claude-plugins-community
/plugin install claude-human-review@claude-community
Technical details
- Sources
- Community
- First seen
- Oct 3, 2026 · 22:13 UTC
- Last seen
- Nov 9, 2026 · 18:07 UTC
- Latest observed change
- Oct 3, 2026 · 22:13 UTC
- Collection status
- Listed
- Reported installs
- Not provided
Installation counts are source-reported, not independently verified active users. Observation dates are not release dates.
Download plugin data (JSON)Plugin history: freshly prepared. Prepared . Refreshed when catalog data changes or after 6 hours. Your account and Follow status are live.