Skip to main content

Talking to Copilot like a caveman

 

I think that everyone who uses AI recognizes the following pattern; you ask an LLM a simple question and it answers like it's writing a blog post: introduction, context, three examples, a closing summary. Fine for a first read, expensive when you're chaining calls or running an agent loop all day.

The trick to avoid this is called "caveman prompting". You tell the model to drop articles, pleasantries and filler, and answer in short, blunt fragments. It sounds silly. But it works up to a point.

A first attempt: just say "be concise"

Most people's first instinct is a one-line system prompt:

Be concise. No fluff.

This already gets you a good chunk of the savings. In benchmarks I've seen floating around, a plain "be concise, return structured output" instruction accounts can already give you a nice reduction. It's the cheapest fix and most people stop here, which is reasonable.

The caveman approach

The caveman skill takes this idea further and transform it into a token-saving solution. Just drop it as a skill/plugin into Claude Code, Copilot, Cursor, Codex, Gemini or one of a few dozen other agents. One install command:

npx skills add JuliusBrussee/caveman

The skill file tells the agent to drop articles, filler and pleasantries, answer in fragments, and use short synonyms ("big" instead of "extensive", "fix" instead of "implement a solution for"). Code, commands, error strings and symbols are explicitly left untouched, byte-for-byte.

It isn't all-or-nothing. There are several modes you switch between with a slash command:

  • /caveman lite  drop filler and hedging, keep full sentences. Professional but tight.
  • /caveman (default, "full")  drop articles too, fragments are fine, short synonyms.
  • /caveman ultra  bare fragments, standard abbreviations (DB, auth, fn), arrows for causality.

Remark: The caveman skill only shrinks what an agent says. If you want that it shrinks everything, have a look at the caveman-code skill.

What I saw when I actually tried it

I installed it on a few real sessions rather than trusting the README numbers. The reduction was real, but nowhere near the headline 65%. Depending on the task, I landed somewhere between 15% and 30% fewer tokens.

The variance made sense once I looked at what I was doing in each session. Short, back-and-forth debugging sessions barely moved the needle, the ~1-1.5k token overhead of the skill instruction itself was eating a good chunk of whatever it saved. Longer sessions with more explanatory answers, code reviews, architecture discussions, got closer to the 30% end.

Remark: I'd treat the 65% figure as a ceiling reached under fairly specific conditions, not a number to plan a budget around. If you're chaining a lot of short calls, measure it yourself before assuming the savings are there.

The author has built a small family of tools around the same idea: a full terminal coding agent that's caveman by default, a memory layer that stores session context compressed in the same grammar so it stays smaller across sessions, and even a fine-tuned model where the compression is baked into the weights instead of a system prompt. Worth a look if you're building agent-heavy workflows and the per-turn overhead of a text instruction actually matters to you.

More information

Labels:

Popular posts from this blog

Podman– Command execution failed with exit code 125

After updating WSL on one of the developer machines, Podman failed to work. When we took a look through Podman Desktop, we noticed that Podman had stopped running and returned the following error message: Error: Command execution failed with exit code 125 Here are the steps we tried to fix the issue: We started by running podman info to get some extra details on what could be wrong: >podman info OS: windows/amd64 provider: wsl version: 5.3.1 Cannot connect to Podman. Please verify your connection to the Linux system using `podman system connection list`, or try `podman machine init` and `podman machine start` to manage a new Linux VM Error: unable to connect to Podman socket: failed to connect: dial tcp 127.0.0.1:2655: connectex: No connection could be made because the target machine actively refused it. That makes sense as the podman VM was not running. Let’s check the VM: >podman machine list NAME         ...
Read more

Cache stampede: when our cache turned against us

While investigating some performance issues, we ran into an ASP.NET Core API that cached a fairly expensive aggregation query for 60 seconds. Under normal load, that was fine: one request rebuilds the cache, everyone else reads from it. Under peak load, dozens of requests would arrive in that same expiry window, all see a cache miss, and all fire the same expensive query in parallel. The database didn't like that. That was the moment when our caching layer stopped helping and started hurting. A burst of requests comes in at the same time, all miss the cache, and all go hammer the database or the downstream API at once. That's a cache stampede . The cache was supposed to protect our backend, and for a few hundred milliseconds it did the opposite. Why this happens IMemoryCache.GetOrCreate (and its async sibling) looks like it protects you, but it doesn't add any locking on its own. Look at the naive version: public async Task<Report> GetReportAsync(string key) ...
Read more

A complex system designed from scratch never works

A few years ago, I worked as an architect on a big mainframe rewrite. I still count it as one of my failures. Not because the technology was wrong, but because I couldn't convince the management team to simplify the approach. Years later, the organization is still struggling to get the new system up and running. I left the project at the time, because I couldn't put my name behind an approach that would take very long and cost a lot of money without a working system to show for it along the way. Gall’s Law That memory keeps coming back to me, because it's a textbook case of Gall's Law playing out in real life. Gall's Law , from John Gall's Systemantics , states it plainly: A complex system that works is invariably found to have evolved from a simple system that worked. A complex system designed from scratch never works, and it cannot be patched to make it work. You have to start over with a simple system that works. What does that mean in practice,...
Read more