Caveman Learn
Act on Caveman token-cost reports — review ranked token sinks and apply cost-lowering fixes with per-edit user consent
- What
- Act on Caveman token-cost reports — review ranked token sinks and apply cost-lowering fixes with per-edit user consent
- Cost
- Free
- Needs
- the `caveman` CLI installed; a `caveman learn report --json` output to act on; the user approves each edit individually
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — the Caveman Learn editing skill: the consent-gated half of `caveman learn` — read the JSON report (Cave Score, ranked token sinks: cache efficiency, tool-output portfolio, session outcomes, subagent spend, procedure repeats), then propose concrete diffs per sink and apply them only with the user's yes on each edit, verifying the reduction afterward (revert if tokens-per-turn didn't drop). Strict money-reporting rules: spend is what the window cost, never projected; subscription plans have zero marginal cost. By @juliusbrussee, listed here with credit to its creator. Honest caveats: requires the `caveman` CLI and a generated learn report to act on; never claims an unmeasured saving and never makes the agent dumber. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Prerequisites: the `caveman` CLI installed; a `caveman learn report --json` output to act on; the user approves each edit individually Install "Caveman Learn" for me. Act on Caveman token-cost reports — review ranked token sinks and apply cost-lowering fixes with per-edit user consent Repository: https://github.com/juliusbrussee/caveman 1. Fetch the SKILL.md file for the juliusbrussee-caveman-learn skill from the repository into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "juliusbrussee-caveman-learn". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. any accounts, API keys, or CLI tools mentioned in the prerequisites above). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. Never ask me to paste secrets in chat — credentials go through the secure vault or environment variables. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.