Token-saving communication mode for non-technical users. Cuts filler AND swaps technical jargon for everyday words. ~61% fewer tokens than normal replies while staying easy to read.
Vibespeak at "chatty" intensity — fuller sentences with light analogies. Persists across sessions.
Turn off vibespeak mode persistently — survives session restarts
Vibespeak at "short" intensity — text-message tight, fragments OK. Persists across sessions.
Switch vibespeak intensity level (short/normal/chatty/off) — persists across sessions
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code skill that makes replies shorter and easier to understand.
Think of it as a friendlier cousin of caveman mode: same idea (cut the filler, save tokens) but also swaps technical jargon for everyday words so you can actually follow along without a CS degree.
When vibespeak is on, Claude will:
Measured across 4 real test prompts (explaining middleware, debugging a TypeError, comparing two databases, reviewing a risky SQL command):
| Mode | Tokens used | Savings |
|---|---|---|
| Normal Claude | 2,688 | — |
| caveman | 899 | −67% |
| vibespeak | 1,048 | −61% |
vibespeak gives up about 6 percentage points of compression compared to caveman in exchange for actually explaining the words it uses. If you're a working programmer who knows every term cold, caveman is the better deal. If you're a beginner, hobbyist, vibe-coder, or just someone who finds technical terminology hard to follow, vibespeak is built for you.
/plugin marketplace add dead-developers/vibespeak
/plugin install vibespeak@vibespeak
Download vibespeak.skill and double-click it, or copy skills/vibespeak/SKILL.md into your Claude skills folder.
Turn it on with any of these:
/vibespeakIt also auto-turns-on when you seem stuck on a technical term (e.g. asking "wait what does that mean").
Intensity levels:
/vibespeak short — text-message tight/vibespeak normal — default, like a clear coworker/vibespeak chatty — slightly more context and small analogiesTurn it off:
/vibespeak offOnce on, vibespeak stays on for every reply until you turn it off — like caveman mode.
For safety-critical stuff, vibespeak deliberately writes a full, careful warning instead of staying terse:
Code blocks, error messages, file paths, and commit messages are also always written exactly — never paraphrased.
skill-creator, which provides the tools for spawning test agents, grading outputs, and benchmarking skill iterations.
npx claudepluginhub dead-developers/vibespeak --plugin vibespeakHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.