A multi-stage code review process in which one reviewer looks for failures, another independently checks the findings and the changed code, and a final reviewer decides which findings stand. It requires evidence such as code locations or test results and states that the reviewers may still share the same model's blind spots.
Route token-heavy context, noisy shell logs and output through the smallest measured CLI or projection before loading heavy tools; recall past agent sessions before re-deriving; fan out to free lanes; benchmark cheap subagent workflows without broad prompt bloat.
Local version management for installed skills. Provides version archiving, history viewing, and rollback capabilities. Use when you need to manage local skill versions, revert changes, or save snapshots of modified skills.
Use when agent skill entrypoints for Codex and Claude Code may be broken, duplicated, unmanaged, or drifting away from /.skm, and you want a structured diagnosis before fixing anything.
★not rated 2 7mo agoA48 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: