agent-hub
claudeAgent hub: a pane listing this session's subagents with status, model, turns and tokens, and a box to steer a running one.
2
claude
eval-kernel
A persistent JavaScript kernel the model drives with one `eval` tool: state survives between cells, and cells call Claude Code tools, models and subagents.
/
Plugin eval-kernel from marketplace claude-mods in kzarzycki/claude-mods. Commands read from the repo's manifest — 12 days ago.
What it installs
No skills, commands, agents, hooks or MCP servers were found in the standard plugin folders.
More from kzarzycki/claude-mods
All 8 plugins →auto-effort
claudeAuto effort: the decision model rates each prompt and the turn it starts runs at that effort.
2
compact-methods
claudeoh-my-pi compaction methods: shake (move old tool output to files, no model call) and handoff (continue from a handoff document). Use `/compact shake` or `/compact handoff [focus]`.
2
decision-model
claudeA decision model for other mods ($.decision.ask): typed questions about a state, answered by any System One endpoint (Jev by default) or a small Claude model.
2
resume-on-stop
claudeUnexpected stops: when a turn ends right after saying it will act, the decision model spots it and one turn resumes the work.
2
self-compact
claudeCompaction at task boundaries: the model can ask to compact once its turn ends, and after a turn that looks like a finished task in a full context it is asked whether to. Uses decision-model to spot finished tasks when it is installed.
2
Maintain eval-kernel?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.
claude & codex plugins8 plugins