6 tagged caveman, measured the same way as everything else here.
Agent
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.
Agent
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is caveman-compressed so the main thread eats 60% fewer tokens than vanilla Explore. Refuses to suggest fixes.
Agent
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
Agent
A narrowly scoped editing agent for small changes in one or two existing files, such as typo fixes, simple renames, single-function rewrites, comment removal, or formatting adjustments.
Agent
A read-only code investigator that locates definitions, uses, callers, imports, tests, and directory structures, then reports file paths and line numbers. It is designed to return very compact results.
Agent
A Japanese code-review style that reports only concrete findings, one per line, with severity labels and file locations.