caveman-learn
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.
Why this score
This repo hosts 10 skills, so its 113,672 stars are split between them (about 11,367 each) for scoring.
Popularity score: 90/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 20, 2026 at commit bad48a0e1df5, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This onecaveman-learn JuliusBrussee/caveman · Skill | 90 | ★ 114k | ≈77 always | 16d ago |
| caveman JuliusBrussee/cavekit · Skill Both about caveman and md | 64 | ★ 1.2k | ≈22 always | 3mo ago |
| learn tigerless-labs/autoharness · Skill Both about learn | 86 | ★ 11k | ≈16 always | 20d ago |
| caveman-browse JuliusBrussee/caveman-browse · Skill Both about caveman and act | 60 | ★ 44 | ≈83 always | 1mo ago |
| learn-graph Li-Evan/Bloom · Skill Both about learn | 60 | ★ 289 | ≈48 always | 2mo ago |
| learn-anything-skill read2017/learn-anything-with-AI · Skill Both about learn | 66 | ★ 200 | ≈50 always | 1mo ago |