Skill Claude CodeCodex
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn cavecrew-investigator (locate code), cavecrew-builder (1-2 file edit), or cavecrew-reviewer (diff review) instead of doing the work inline or using vanilla Explore. Subagent output is caveman-compressed so the tool-result…
Skill Claude CodeCodex
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit.…
Skill Claude CodeCodex
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or…
Skill Claude CodeCodex
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
Skill Claude CodeCodex
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
Skill Claude CodeCodex
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens"…
Settings file Claude Code
Agent settings declaring 22 allowed tools.
Cursor rule Cursor
Caveman mode — terse communication, 65% fewer output tokens (measured), full technical accuracy.
Cursor rule Cursor
Read CLAUDE.md, AGENTS.md, and .github/copilot-instructions.md before making changes.
Agent
Run card cache compliance tests — verify all cards store and retrieve cached data from IndexedDB across navigation. Wraps scripts/cache-test.sh.
Agent
Check CI pipeline status, monitor running jobs, summarize check results, and route to RCA on failures. For kubestellar/console GitHub Actions.
Agent
Design agentic workflows using GitHub Agentic Workflows (gh-aw) extension with interactive guidance on triggers, tools, and security best practices.
Agent
Debug and refine agentic workflows using gh-aw CLI tools - analyze logs, audit runs, and improve workflow performance.
Agent
Automated issue scanner — monitors 4 repos, verifies and fixes all open issues (bugs + enhancements), reviews open PRs against quality criteria, enforces contributor policies.
Agent
Kubernetes debugging and troubleshooting — pod status, logs, events, health checks, and service debugging for clusters managed by kubestellar/console.
Agent
Run dashboard navigation performance tests — cold/warm nav, rapid clicks, route transitions. Wraps scripts/nav-test.sh.
Agent
Run dashboard performance tests — TTFI metrics, demo/live modes, budget gates. Wraps scripts/perf-test.sh with guided analysis.
Agent
Root cause analysis for CI and test failures — systematic 5-phase investigation of build, lint, and test failures in kubestellar/console.
Agent
GitHub repository health — personal status dashboard, PR health analysis, issue triage, and stale item detection for kubestellar/console.
Agent
Test-driven development workflow for kubestellar/console — code, build, lint, test, commit, push, iterate on CI failures.
Agent
Run UI compliance tests for card loading behavior — 8 criteria across 150+ cards with optional baseline gate. Wraps scripts/ui-compliance-test.sh.
Instructions file GitHub Copilot
Instructions for kubestellar/console, covering copilot instructions for kubestellar console, mandatory: build and lint before every commit, commit workflow, project structure and code standards.
Instructions file CodexOpenCode
Instructions for kubestellar/console, covering agents.md — kubestellar console, source of truth, quick orientation, non-negotiable rules (excerpt — full list in claude.md) and reporting back.