caveman
Auto-activation works differently per agent: Claude Code uses SessionStart hooks, this repo's Codex dogfood setup uses .codex/hooks.json, Gemini uses context files…
Plugin bundle · by JuliusBrussee
About
caveman is a plugin bundle for AI coding tools published by JuliusBrussee. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). We first saw it on 2026-10-11 and have recorded no change since. As of our marketplace pass on 2026-10-12.
Auto-activation works differently per agent: Claude Code uses SessionStart hooks, this repo's Codex dogfood setup uses .codex/hooks.json, Gemini uses context files. Cursor/Windsurf/Cline/Copilot can be made always-on, but npx skills add installs only the skill, not the repo rule/instruction files. ¹ Codex uses $caveman syntax, not /caveman. This repo ships .codex/hooks.json, so caveman auto-starts when you run Codex inside this repo. The installed plugin itself gives you $caveman; copy the same hook into another repo if you want always-on behavior there too. caveman-commit and caveman-review are not in the Codex plugin bundle — use the SKILL.md files directly. ² Add the "Want it always on?" snippet below to those agents' system prompt or rule file if you want session-start activation. ³ Cursor and Windsurf receive the full SKILL.md with all intensity levels. Mode switching works on-demand via the skill; no slash command. ⁴ Available in Claude Code, but plugin install only nudges setup. Standalone install.sh /
What it asks for
- Installs as a plugin bundle
- Hooks: 2
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Connect
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
Where it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Claude Code: claude-plugins-community (Open the source on GitHub) | Listed | 3098342 | Forks (GitHub): 6 428 Stars (GitHub): 111 029 |
Not marked |
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.
What the bundle contains
As published on Claude Code: claude-plugins-community.
Skills: 7
cavecrewcavemancaveman-commitcaveman-compresscaveman-helpcaveman-reviewcaveman-stats
Commands: 5
cavemancaveman-commitcaveman-initcaveman-reviewcaveman-stats
Agents: 3
cavecrew-buildercavecrew-investigatorcavecrew-reviewer
Hooks: 2
SessionStartUserPromptSubmit
What changed
Nothing has moved on this plugin since we started watching it.
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
Six focused slash commands for safer, more deliberate coding sessions. Save and restore named git checkpoints, review diffs before committing, analyze blast radius before changing…
-
MCP bridge that lets Claude Code delegate coding tasks to GitHub Copilot CLI. Forwards prompts to the locally installed Copilot CLI and returns results. Includes a /copilot skill…
-
10 slash commands and 3 agent definitions distilled from 6 months of daily Claude Code use. Not a framework -- just the patterns that survived: multi-agent build pipelines…
-
Autonomous Plan → Work → Review cycle for Claude Code. Go-native engine with 25× faster hooks, runtime guardrails on .git/ / secrets / destructive commands, and SSOT memory…
-
Nine Claude skills for multi-repo workflows: audit builds, tame CI, sync docs↔code, and keep sister repos in lockstep.
-
23 reusable skills, 2 agents, and smart hooks for any project. Covers the full development cycle: architecture mapping, implementation planning, code review, safe refactoring…
-
The most comprehensive agentic coding harness for Claude Code that works for both greenfield and brownfield projects. Drops 38 slash commands, 36 sub-agents, and 16 skills into…
-
Project intelligence skills for Claude Code. Teaches Claude when to use Mako's MCP tools (context packets, code and schema search, diagnostics, RLS audits) instead of grep-walking…
-
Give Claude Code the knowledge layer your agents deserve: local code intelligence, a persistent knowledge graph, task context, and team sync.
-
Automated code review and swarm remediation for large changesets. Spawns adversarial reviewer agents, presents findings interactively, then dispatches fixer agents to remediate…
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on Claude Code: claude-plugins-community (5)
-
Six focused slash commands for safer, more deliberate coding sessions. Save and restore named git checkpoints, review diffs before committing, analyze blast radius before changing…
-
MCP bridge that lets Claude Code delegate coding tasks to GitHub Copilot CLI. Forwards prompts to the locally installed Copilot CLI and returns results. Includes a /copilot skill…
-
10 slash commands and 3 agent definitions distilled from 6 months of daily Claude Code use. Not a framework -- just the patterns that survived: multi-agent build pipelines…
-
Autonomous Plan → Work → Review cycle for Claude Code. Go-native engine with 25× faster hooks, runtime guardrails on .git/ / secrets / destructive commands, and SSOT memory…
-
Nine Claude skills for multi-repo workflows: audit builds, tame CI, sync docs↔code, and keep sister repos in lockstep.
Has a listing on Claude Code: claude-plugins-official (5)
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
-
Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
-
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin…
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
Has a listing on Claude: knowledge-work-plugins (5)
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
MCP server for terminal commands, file operations, and process management
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
-
AI-powered code review in Codex, powered by CodeRabbit.
-
Qodo setup, code intelligence, and review workflows.
Has a listing on Community GitHub marketplaces (5)
-
Endor Labs workflow agents and setup for Claude Code.
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
Local Git via MCP: status, log, diff, file history, branches, and gated stage/commit. Pure-JS.
-
Comprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized agents for schema design, architecture planning, code review, and…
-
Local graph memory that lets Codex recall project context across sessions.
Has a listing on Copilot CLI: github/awesome-copilot (5)
-
Meta prompts that help you discover and generate curated GitHub Copilot agents, instructions, prompts, and skills.
-
Generic cross-repo command center canvas for GitHub Copilot with onboarding, focus planning, repo health, work signals, and session cleanup.
-
Build applications with the GitHub Copilot SDK across multiple programming languages. Includes comprehensive instructions for C#, Go, Node.js/TypeScript, and Python to help you…
-
Tools and techniques for maximizing GitHub Copilot effectiveness through better context management. Includes guidelines for structuring code, an agent for planning multi-file…
-
Plain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into clear, jargon-free English with…
Has a listing on Copilot CLI: github/copilot-plugins (5)
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Advanced Security plugin for GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
Has a listing on Cursor: cursor/plugins (5)
-
Internal team workflows for CI, code review, shipping, local automation, and verification.
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
-
Skills for building on the Cursor Origin API. Fetch the live spec first, then follow the Origin rules for credentials, scopes, webhooks, paging, and errors. Includes a skill that…
-
Consult a stronger model before major decisions, when stuck, and before declaring done.
Has a listing on Docker MCP Catalog (5)
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
-
MCP server for terminal commands, file operations, and process management
-
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Tools for interacting with Git repositories.
Has a listing on Official MCP Registry (5)
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
-
Delegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.
-
Full-text search, browse, and resume across your coding agent sessions (Claude Code, Codex, Amp)
-
Personal RAG over your GitHub history (commits, code, reviews), served to Claude Code over MCP.
-
GitWhy — The Context Layer for Git
The shared AI context engine for git — save, search, and share the reasoning behind code changes.
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Is this your plugin?
Prove you maintain it with a file in its repository, a file on your domain or a DNS record. You get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and can put its remote endpoint on monitoring as a web service.
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.