Human Gate plugin: what it installs and how to add it
Adds a structured human sign-off gate for agent workflows, with review pages, batched feedback and unresolved-blocker checks.
From the Marketplace: claude-code-skills marketplace
Install
> /plugin marketplace add alirezarezvani/claude-skills> /plugin install human-gate@claude-code-skillsRun both lines inside Claude Code: the first adds the marketplace, the second installs the plugin.
What is inside
- 1skill
- 1command
- 1agent
About this plugin
Human Gate creates a single-file review page for Markdown or HTML artefacts and collects feedback as structured batch.v1 data rather than chat prose. Reviewers can assign severities, suggest edits, approve explicitly, and write feedback to a Markdown sidecar when no browser is available.
Use it before shipping a plan, specification, RFC, report or other irreversible action. The gate refuses to close if nobody has reviewed, the reviewer is unnamed, a blocker remains open, feedback integrity checks fail, or the sidecar changed after collection. It is non-blocking, headless-guarded and round-capped, with escalation when rounds are exhausted. The implementation is standard-library-only Python with no build step.
What's inside
- 1 skill:
human-gate - 1 slash command:
/cs-human-gate - 1 agent:
cs-human-gate
More from claude-code-skills
- A11y AuditScans and fixes WCAG 2.2 accessibility issues in React, Vue, Angular, Svelte, Next.js and HTML projects.Marketplace: claude-code-skillsGitHub stars: 27.2k
- AEOAudits and optimises content for citation by AI answer engines including ChatGPT, Perplexity, Claude, Gemini and Mistral.Marketplace: claude-code-skillsGitHub stars: 27.2k
- Agent HarnessRuns bounded agentic loops that turn goals into verified tasks and close only when checks pass or are explicitly waived.Marketplace: claude-code-skillsGitHub stars: 27.2k
- Agent Launcher SkillsBuilds, launches, grades, and schedules Claude Managed Agents in your Anthropic account through bounded workflows and loops.Marketplace: claude-code-skillsGitHub stars: 27.2k
- Agent MemoryAdds tiered memory for Claude Code, recalling relevant project context while requiring repeated evidence and human approval before promotion.Marketplace: claude-code-skillsGitHub stars: 27.2k
- AgentHubRuns parallel Claude Code agents in isolated worktrees, evaluates their competing solutions and merges a selected winner.Marketplace: claude-code-skillsGitHub stars: 27.2k
Related plugins
- PonytailForces AI coding agents towards the shortest working solution, favouring YAGNI and the standard library over unrequested abstractions.Marketplace: ponytailGitHub stars: 151k
- CavemanCompresses coding-agent messages while preserving technical terms, code, commands, and exact errors.Marketplace: claude-communityGitHub stars: 109k
- Claude MemAdds persistent memory and context compression to Claude Code, carrying useful context across sessions.Marketplace: thedotmackGitHub stars: 95.1k
- Claude-Mem CoworkCaptures Claude Cowork tool use and restores relevant memory in new sessions and spawned agents through cmem.ai.Marketplace: thedotmackGitHub stars: 95.1k
Skills, not plugins
Prefer a single skill for productivity work? 109 skills in the same category, each installed on its own.