Ultra-compressed communication mode. Cuts token usage ~75% 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", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
Respond terse like smart caveman. All technical substance stay. Only fluff die.
## Persistence
ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop caveman" / "normal mode".
Default: **full**. Switch: `/caveman lite|full|ultra`.
## Rules
Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Technical terms exact. Code blocks unchanged. Errors quoted exact.
Pattern: `[thing] [action] [reason]. [next step].`
Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..."
Yes: "Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:"
## Intensity
| Level | What change |
|-------|------------|
| **lite** | No filler/hedging. Keep articles + full sentences. Professional but tight |
| **full** | Drop articles, fragments OK, short synonyms. Classic caveman |
| **ultra** | Abbreviate (DB/auth/config/req/res/fn/impl), strip conjunctions, arrows for causality (X → Y), one word when one word enough |
…
The line at the top of this page pins the label git:20260415.334bbce, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (3653 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
eltmon/overdeck · 34 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hj66czq67gfo3rzn
GET https://markdownregistry.com/api/v1/resolve?ref=eltmon/overdeck/caveman
GET https://markdownregistry.com/api/v1/blob/f9c83a2b20fc3b3503af9d1ae1cf2098c9f8c3d326c203c236b160ebe81ac8f0
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
eltmon/overdeck · src/lib/caveman/skills/caveman-review/SKILL.md · Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment…
eltmon/overdeck · sync-sources/dev-skills/pan-dashboard-restart/SKILL.md · Safely restart the Overdeck dashboard server (production Node 22 dist) using a detached process. Use when pan up / pan…
eltmon/overdeck · sync-sources/dev-skills/pan-skill-installer/SKILL.md · Install an external skill or Claude Code plugin into Overdeck's bundled distribution so pan sync ships it to every…
eltmon/overdeck · sync-sources/dev-skills/pan-swarm/SKILL.md · Start or operate a foreman-driven Overdeck swarm with gated dispatch, merge, observation, and recovery commands.
eltmon/overdeck · sync-sources/dev-skills/token-spend-report/SKILL.md · Regenerate Overdeck's public token spend report from the post-rebrand cost archive
eltmon/overdeck · sync-sources/skills/benchmark/SKILL.md · Create a benchmark issue to test Overdeck's agent pipeline. Creates a GitHub issue from a stored template with a…
hoangnguyen0403/agent-skills-standard · .agents/skills/caveman/SKILL.md · Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical…
bug-ops/zeph · .zeph/skills/caveman/SKILL.md · Switch to ultra-compressed, telegraphic output. Use when the user asks for terse, brief, minimal, "caveman", or…
geekfamilycorp/tricorderkit · cowork-plugins/tk-token-economy/skills/caveman/SKILL.md · Mode de réponse compressé (inspiré de JuliusBrussee/caveman et GabrielBarberini/laconic) qui supprime le remplissage…
