juliusbrussee/caveman

67

caveman Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ult…

juliusbrussee/caveman

493K

157

caveman-commit Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit o…

juliusbrussee/caveman

345.5K

158

caveman-review Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this P…

juliusbrussee/caveman

342.2K

159

caveman-compress Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable …

juliusbrussee/caveman

340.5K

163

caveman-help Quick-reference card for caveman modes, skills and commands.

juliusbrussee/caveman

333.3K

184

cavecrew When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` …

juliusbrussee/caveman

291K

187

caveman-stats Show real token usage and estimated savings for the current session, read from the session log. Trigger: /caveman-sta…

juliusbrussee/caveman

290.1K

545

compress

juliusbrussee/caveman

46.8K

587

caveman-explore Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search fail…

juliusbrussee/caveman

40.5K

592

caveman-optimize Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when…

juliusbrussee/caveman

40.1K

593

caveman-learn Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and r…

juliusbrussee/caveman

40.1K

597

investigate-first Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, o…

juliusbrussee/caveman

39.9K

595

safe-refactor Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where veri…

juliusbrussee/caveman

39.9K

598

verify-and-stop Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion ch…

juliusbrussee/caveman

39.8K

600

surgical-patch Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surround…

juliusbrussee/caveman

39.7K

604

caveman-evidence-review Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. U…

juliusbrussee/caveman

39.6K

605

caveman-discover Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. …

juliusbrussee/caveman

39.5K

607

caveman-manage Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, pr…

juliusbrussee/caveman

39.5K

606

lean-build Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repositor…

juliusbrussee/caveman

39.5K

608

migration Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependenc…

juliusbrussee/caveman

39.4K

613

caveman-setup Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use fo…

juliusbrussee/caveman

39.1K

22

caveman-es Modo cavernícola en español. Corta ~75% de tokens hablando como cavernícola técnico. Misma precisión técnica, menos p…

juliusbrussee/caveman

522

23

caveman-cn

juliusbrussee/caveman

445