published by juliusbrussee

36 listings on this page, in order of arrival. Each one has its own page with README, repository facts and source links.

1. caveman ★ 105,268
   Auto-activation works differently per agent: Claude Code uses SessionStart hooks, this repo's Codex dogfood setup uses .codex/hooks.json, Ge
2. caveman ★ 105,268
   Ultra-compressed communication mode. Shortens replies while preserving technical substance, code, commands, and exact errors.
3. caveman-browse ★ 25
   Token-efficient browser driver: compressed accessibility snapshots, uid actions, byte-exact recovery over MCP.
4. caveman ★ 105,268
   Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Suppo
5. caveman-commit ★ 105,268
   Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
6. caveman-review ★ 105,268
   Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff
7. caveman-compress ★ 105,268
   Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /cavem
8. caveman-help ★ 105,268
   Quick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".
9. cavecrew ★ 105,268
   When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead o
10. caveman-stats ★ 105,268
    Show real token usage and estimated savings for the current session, read from the session log. Trigger: /caveman-stats.
11. compress ★ 105,268
    Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical sub
12. caveman-explore ★ 105,268
    Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the ex
13. caveman-optimize ★ 105,268
    Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or ev
14. caveman-learn ★ 105,268
    Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes
15. investigate-first ★ 105,268
    Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needin
16. safe-refactor ★ 105,268
    Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket s
17. verify-and-stop ★ 105,268
    Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs
18. surgical-patch ★ 105,268
    Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-
19. caveman-discover ★ 105,268
    Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workf
20. caveman-evidence-review ★ 105,268
    Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Cave
21. lean-build ★ 105,268
    Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope,
22. caveman-manage ★ 105,268
    Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Ca
23. migration ★ 105,268
    Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring
24. caveman-setup ★ 105,268
    Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or a
25. caveman ★ 162
    juliusbrussee/skills · skills.sh
26. caveman ★ 1,143
    juliusbrussee/cavekit · skills.sh
27. build ★ 1,143
    juliusbrussee/cavekit · skills.sh
28. spec ★ 1,143
    juliusbrussee/cavekit · skills.sh
29. check ★ 1,143
    juliusbrussee/cavekit · skills.sh
30. backprop ★ 1,143
    juliusbrussee/cavekit · skills.sh
31. grill-me ★ 162
    juliusbrussee/skills · skills.sh
32. junior-to-senior ★ 162
    juliusbrussee/skills · skills.sh
33. interface-kit ★ 162
    juliusbrussee/skills · skills.sh
34. fuck-slop ★ 162
    juliusbrussee/skills · skills.sh
35. context-canary ★ 162
    juliusbrussee/skills · skills.sh
36. loop-factory ★ 162
    juliusbrussee/skills · skills.sh