Caveman
ChatGPT pluginCompressed coding workflows
- Featured
- No
not on the featured shelf
Movement
From our daily snapshots over the last 30 days.
Rank by placement
Rank in Developer tools
In its category
How this plugin compares with others in the same category. Positions are counted within the category, not across the whole directory.
Developer tools352nd of 537 by placement
| # | Plugin | Position | 7d |
|---|---|---|---|
| 349 | #4849 | — | |
| 350 | #4856 | — | |
| 351 | #4865 | — | |
| 352 | #4873 | — | |
| 353 | #4878 | — | |
| 354 | #4879 | — | |
| 355 | #4883 | — |
Provides compact engineering workflows for reasoning about code, implementation, debugging, and delivery with minimal unnecessary context.
Example prompts
- “Use Caveman to simplify this coding task”
- “Review this implementation with the Caveman workflow”
- “Turn this requirement into a compact execution plan”
Skills
cavecrew
Use when a coding task should be delegated to a focused investigator, small-change builder, or diff reviewer so the main context stays compact.
caveman
Use when the user asks to run or coordinate a Caveman workflow for reducing LLM cost, inspecting workflow evidence, or optimizing agent usage.
caveman-commit
Use when the user asks for a concise Conventional Commit message or wants a commit message compressed to the change intent.
caveman-compress
Use when the user explicitly asks to compress a memory, instructions, or todo file into Caveman format while keeping a readable backup.
caveman-discover
Use when the user asks to discover or label LLM workflows in a repository so Caveman can attribute spend by workflow.
caveman-evidence-review
Use when the user asks what Caveman found about LLM cost, traces, latency, errors, routing, savings, or workflow evidence.
caveman-explore
Use when a repository needs broad read-only exploration for orientation or localization and the exact file or symbol is not already known.
caveman-help
Use when the user explicitly asks for Caveman help, available modes, skills, commands, or a quick-reference summary.
caveman-learn
Use when the user asks to reduce an agent workflow's token cost, review Caveman savings, trim heavy context files, or act on a Caveman learning report.
caveman-manage
Use when the user explicitly asks to start, approve, cancel, promote, or roll back a Caveman experiment.
caveman-optimize
Use when the user asks to inspect or evaluate a Caveman optimization report before explicitly approving any optimization action.
caveman-review
Use when the user asks for a focused review of a code diff or change using the Caveman workflow.
Show all 20Show fewer
caveman-setup
Use when the user explicitly asks to configure Caveman for a repository, workspace, or cloud-backed workflow.
caveman-stats
Use when the user asks for Caveman usage, cost, savings, score, or workflow statistics from available Caveman evidence.
investigate-first
Use when a bug or unexpected behavior needs evidence and a credible root cause before any code is edited.
lean-build
Use when implementing a feature or change and the work should be reduced to the smallest coherent, testable slice.
migration
Use when planning or implementing a migration that must preserve data, support rollback, and move through reversible transition steps.
safe-refactor
Use when restructuring code while preserving observable behavior and proving the refactor with tests or other evidence.
surgical-patch
Use when a narrow regression or defect should be fixed at the responsible layer while preserving surrounding behavior and proving the patch with focused tests.
verify-and-stop
Use when a change appears complete and the next step is to run only the relevant proof, report the result, and stop without unrelated cleanup.
- Categories
- Made by
- RONALD FERRARI SOARES
- Sign-in
- On Install
- Capabilities
- Compressed communication, Code review, Refactoring guidance
- Availability
- Available
- Version
- 2.7.0
- Keywords
- concise, developer-tools, review, refactoring, workflow
- Created
- September 20, 2026