eval-kernel 0.1.0
A persistent JavaScript kernel the model drives with one `eval` tool: state survives between cells, and cells call Claude Code tools, models and subagents.
kzarzyckiInstall
/plugin marketplace add kzarzycki/claude-mods /plugin install eval-kernel@claude-mods
Run both lines inside Claude Code.
Hooks into
- Prompt
- Tool calls
- Slash commands
- Model tools
Also in kzarzycki/claude-mods
-
resume-on-stop
0.1.0
Unexpected stops: when a turn ends right after saying it will act, the decision model spots it and one turn resumes the work.
kzarzycki in Prompt, updated
1
-
compact-methods
0.1.0
oh-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]`.
kzarzycki in Notifications, updated
1
-
decision-model
0.1.0
A 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.
kzarzycki in Commands, updated
1
-
auto-effort
0.1.0
Auto effort: the decision model rates each prompt and the turn it starts runs at that effort.
kzarzycki in Prompt, updated
1
-
ttsr-rules
0.1.0
oh-my-pi TTSR rules: a regex rule denies the tool call that would break it, with the rule as the reason; a question rule is judged after each turn.
kzarzycki in Guardrails, updated
1
-
agent-hub
0.1.0
Agent hub: a pane listing this session's subagents with status, model, turns and tokens, and a box to steer a running one.
kzarzycki in Usage & cost, updated
1
-
self-compact
0.1.0
Compaction 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.
kzarzycki in Prompt, updated
1
More prompt mods
-
ruflo-ruos
0.1.1
mod + skill
Run ruflo swarm agents on your own ruOS cloud desktops via the tenant-authenticated fleet MCP or per-tenant SSH; optional and removable (ADR-405)
ruvnet in Prompt, updated
74.2k
-
pet
0.2.0
A virtual pet above the Claude Code prompt that grows as Claude works: passing tests, commits and edits grant XP and mood, failing tests cost mood, idling drains it; egg → baby → kid → adult → legend. Zero tokens. Split out of cc-arcade (MIT, Seza Akgün). Needs an interactive terminal.
Seza Akgün in Prompt, updated
32.5k
-
daily.dev
0.7.0
mod + skill
Access personalized developer content feeds from daily.dev - the professional network for developers. Surface relevant articles, tutorials, and discussions based on user interests.
daily.dev in Prompt, updated
20.1k
-
plannotator
0.28.9
Interactive Plan Review: Mark up and refine your plans using a UI, easily share for team collaboration, automatically integrates with plan mode hooks.
backnotprop in Prompt, updated
9.3k
-
next-steps
1.0.0
After each turn, suggests up to three next prompts above the input. Press 1, 2 or 3 to put one in the prompt box as a draft you can edit, 0 to dismiss.
Thariq Shihipar in Prompt, updated
4.6k