claude

caveman

Aggregated (not authored here). Ultra-compressed communication mode that cuts ~65% of output tokens (author's measurement), now grown into a 20-skill suite (commit discipline, review, refactor verbs, plus 4 skills — caveman-discover, caveman-manage, caveman-evidence-review, caveman-setup — for the author's hosted Caveman Cloud commercial service). Ships SessionStart and UserPromptSubmit hooks (needs node on PATH; runs on every prompt). General agent behavior. By JuliusBrussee; skills are MIT, the repo also ships a Business Source License 1.1 engine.

18 on GitHubby JuliusBrusseev3.2.0MITupdated 1 month agoworkflow
/

Plugin caveman from marketplace apple-dev-skills in wei18/apple-dev-skills. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (22)

  • cavecrew

    When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.

  • caveman-compress

    Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.

  • caveman-stats

    Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.

  • caveman

    Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

  • megacave

    Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave or /caveman wenyan. Stays on until "stop caveman" or "normal mode".

  • ultracave

    Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra. Stays on until "stop caveman" or "normal mode".

  • caveman-commit

    Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.

  • caveman-discover

    Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

  • caveman-evidence-review

    Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.

  • caveman-explore

    Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.

  • caveman-help

    Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".

  • caveman-learn

    Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.

  • caveman-manage

    Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.

  • caveman-optimize

    Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.

  • caveman-review

    Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".

  • caveman-setup

    Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.

  • investigate-first

    Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.

  • lean-build

    Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.

  • migration

    Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.

  • safe-refactor

    Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.

  • surgical-patch

    Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.

  • verify-and-stop

    Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.

Slash commands (1)

  • /caveman:caveman-init

    Drop the always-on caveman activation rule into the current repo for every IDE agent

Subagents (3)

  • cavecrew-builder

    Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors

  • cavecrew-investigator

    Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is caveman-compressed, one row per hit, to keep main-thread context small. Refuses to suggest fixes.

  • cavecrew-reviewer

    Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format `path:line: <emoji> <severity>: <problem>. <fix>.` Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.

Hooks (4)

  • SessionStart

    command -v node >/dev/null 2>&1 || exit 0; HOOK_ROOT=$(printf %s "${CLAUDE_PLUGIN_ROOT}" | sed 's|^/\([a-zA-Z]\)/|\1:/|'); node "$HOOK_ROOT/src/hooks/caveman-activate.js"

  • SubagentStart

    command -v node >/dev/null 2>&1 || exit 0; HOOK_ROOT=$(printf %s "${CLAUDE_PLUGIN_ROOT}" | sed 's|^/\([a-zA-Z]\)/|\1:/|'); node "$HOOK_ROOT/src/hooks/caveman-activate.js" --subagent

  • UserPromptSubmit

    command -v node >/dev/null 2>&1 || exit 0; HOOK_ROOT=$(printf %s "${CLAUDE_PLUGIN_ROOT}" | sed 's|^/\([a-zA-Z]\)/|\1:/|'); node "$HOOK_ROOT/src/hooks/caveman-mode-tracker.js"

  • SessionEnd

    command -v node >/dev/null 2>&1 || exit 0; HOOK_ROOT=$(printf %s "${CLAUDE_PLUGIN_ROOT}" | sed 's|^/\([a-zA-Z]\)/|\1:/|'); node "$HOOK_ROOT/src/hooks/caveman-stats.js" --record

View source on GitHub

More from wei18/apple-dev-skills

All 9 plugins →

Aggregated (not authored here). Broad Apple-framework skills — SwiftUI, UIKit, Swift Testing, Concurrency, SwiftData, App Intents, WidgetKit, StoreKit, HealthKit, MapKit, TipKit, apple-aso, hig, simulator-utils, xcuitest, and more (a handful more ship disabled by default in disabled-skills/). By Prisma Labs (vabole), MIT.

34 skills

18

26 first-party Apple/Swift skills. Invoke explicitly with /apple-dev-skills:<skill>.

26 skills

18

12 first-party AI-agent collaboration & process skills. Invoke explicitly with /collaboration-skills:<skill>.

12 skills

18

ponytail

claudecodex

Aggregated (not authored here). 'Lazy senior dev' mode — forces the simplest, shortest solution. General agent-behavior skill. By DietrichGebert, MIT.

6 skills

18

i-have-adhd

claudecodex

Aggregated (not authored here). ADHD-friendly output mode — leads with the next action, numbers steps, restates state each turn, makes wins visible. General agent-behavior skill. By Ayoub G. (ayghri), MIT.

1 skill · hooks

18

swiftui-expert

claudecodex

Aggregated (not authored here). SwiftUI patterns — state, performance, Swift Charts, macOS multi-window, Liquid Glass, plus an Instruments-trace toolchain. By Antoine van der Lee (AvdLee), MIT.

2 skills

18

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

gsd-core

claude

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

72 skills · 72 commands · 64 agents · hooks

open-gsd/gsd-core 11,494

Maintain caveman?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins9 plugins