claude

caveman

Token-efficient communication mode: terse, direct output with no filler, applied to prose, commit messages, and code-review comments.

0 on GitHubby Luca La Rosav1.0.0UNLICENSEDupdated 7 days agodevelopment
/

Plugin caveman from marketplace claude-registry in luketherose/claude-registry. Commands read from the repo's manifest — 6 days ago.

What it installs

Skills (3)

  • caveman-commit

    This skill should be used when the user asks for a commit message. Triggers include \"write a commit\", \"commit message for this\", \"conventional commit\", \"cc:\". Produces a terse, intent-focused Conventional Commits subject line (max 72 chars) with a body only when reasoning is non-obvious. No

  • caveman-review

    This skill should be used when the user asks for code-review comments or PR review. Triggers include \"review this PR\", \"review the diff\", \"comments for this change\", \"PR feedback\". Each comment follows the format `L<line>: <severity> <problem>. <fix>.`. No hedging, no code repetition, no mot

  • caveman

    This skill should be used when the user asks for terser, more direct output. Explicit triggers include \"caveman mode\", \"caveman lite|full|ultra\", \"be terse\", \"cut the fluff\", \"token-efficient\". Activates token-efficient communication mode (~75% token reduction). Switches responses to compr

View source on GitHub

More from luketherose/claude-registry

All 7 plugins →

Production code standards, developer agents and test authoring for Java/Spring, Python, Go, Rust, Kotlin, C#, PHP, Ruby, Streamlit and frontend frameworks (Angular, React, Vue, Qwik, Vanilla), plus REST API design, bug diagnosis, and visual design and motion for own-brand interfaces.

34 skills · 3 agents · 1 MCP server

0

Technical documentation authoring and branded deliverable generation: READMEs, wikis, runbooks, LaTeX docs, Accenture-branded PDF/DOCX documents and PowerPoint presentations, UniCredit-template Word documents, and interactive HTML explainers.

9 skills · 1 MCP server

0

System architecture design, ADR authoring, functional requirement extraction, technical debt assessment, capability-registry auditing, and multi-domain task orchestration.

4 skills · 5 agents

0

Gemini CLI expertise and Claude Code parity mapping: extension authoring, capability translation in both directions, and the mirroring procedure that keeps the two registries in step.

4 skills · 1 agent

0

AS-IS to TO-BE application replatforming pipeline: codebase indexing, functional and technical analysis, baseline testing, TO-BE scaffolding, and equivalence verification.

4 skills · 1 agent

0

Multi-agent deliberative decision engine: structured debate with independent personas, challenge rounds, rebuttals, and auditable final-decision artefacts for high-stakes or irreversible decisions.

0

Similar plugins

superpowers

claudecodex

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

15 skills · hooks

obra/superpowers 316,836

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

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 plugins7 plugins