Commands
28 mods. New slash commands.
- ruflo-arena 0.2.3 Competitive ruliology for Ruflo swarms â arenas, tournaments, and adaptive co-evolution of program strategies (ADR-147/148). Strategies-as-programs compete under payoff games; tournaments produce Wolfram-style competitive arrays; hill-climb and mutual co-evolution discover winners empirically. 73.9k
- ruflo-agntcy 0.2.3 mod + skill AGNTCY/Outshift Internet-of-Cognition runtime integration for Ruflo â SLIM secure transport for cross-host agent coordination, CASA intent-scoped tool authorization enforcement, optional IOC Layer 9 coordination events, and AGNTCY identity/observability spans (ADR-380). Optional, removable augmen... 73.9k
- ruflo-plugin-creator 0.4.1 mod + skill Scaffold, validate, and publish new Claude Code plugins with the canonical plugin contract â now including governed Claude Code mods (function hooks), ADR + smoke + Compatibility + namespace coordination + MCP-tool drift warnings. As a mod (ADR-445): /creator-mod (status, reserved names, a plugin... 73.9k
- fable-pin 0.1.0 Pins every subagent to the fable model: rewrites the model on agent.spawn unless the spawn is a fork, with /fable-pin on, off and status. Touches nothing but its own store. Needs function hooks (early access). 35
- taskcut 0.9.1 Compacts when the work moves on from one sub-task to the next instead of when the context window fills, including in the middle of a long turn. Once the context is past a floor, a model judges each step, reading what you asked for and where Claude has got to but never any tool output, for whether... 7
- orphan-server 0.3.1 Lists the servers a Bash call of the model started in this repository and left listening on a port, with their age and session, and stops one with SIGTERM, then SIGKILL. 6
- diagram-render 0.1.3 Renders the mermaid blocks of the model's replies with an installed mmdc after each turn and draws each picture under its reply. 6
- output-flood 0.4.2 Measures how much context each Bash command spent and tells the model, past a size limit, which narrower command would have answered the same question. 6
- mod-doctor 0.5.1 Names each installed plugin, of every marketplace, whose local clone already offers a newer version, with the claude plugin update command that closes the gap. 6
- mcp-doctor 0.2.2 Tells you when an MCP server failed to connect or dropped, with the engine's reason and a reconnect button, and when it is back; claude.ai connectors are left out. 6
- pin-note 0.1.2 Keeps the notes you pin with /pin-note for the whole session and sends them to the model again, word for word, after each compaction and /clear. Off until /pin-note on. 6
- ai-skills 1.73.0 mod + skill Benjamin's collection of Claude Code skills â daily workflow, code quality, dev tools, and specialist agents. 4
- p1 0.0.1 aside probe 1: fork shape, budget, continuation, store, messages 2
- p6 0.0.1 aside probe 6: mid-turn fallbacks (session.messages + model.complete) vs fork 2
- auto-checkpoint 0.1.0 Snapshots the working tree into hidden git refs at the start of every turn, with /checkpoints to list them and /undo-turn to roll back. 1
- worktree 0.1.0 /wt creates a worktree for the work under discussion and moves the session into it, without a turn of the main model. 0
- session-relaunch 0.1.0 Update Claude Code and resume this session on the new version 0
- hyperspace 0.2.0 Spinner mod: an X-wing or a TIE fighter flies through a parallax starfield while Claude works, with laser volleys and a hyperspace jump every 24 s. /ship switches the ship. 0
- tldr 1.0.0 A one-line TL;DR under every long answer, written by a small fast model, so you can skim a wall of text in two seconds. 0
- updates 0.2.0 A weekly check of your Claude and Codex plugins, global npm packages and adapted skills for newer versions, with a one-line summary of each 0
- 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. 0
- mod-doctor 1.0.0 /mod-doctor checks every installed mod in one report: hook scripts, plugin mods loaded, Node, Claude Code version, errors and ESLint timings in the mods log. 0
- machine-tag Prefixes session titles with this machine's emoji tag (ðŧ MBP, ðŠķ Air, ðŪ Rig, ðĨ 5090), so pinned and listed sessions show which computer they run on 0
- understand-mode 0.1.0 Makes Claude explain its work in the fastest format to understand: STE-style text, diagrams, throwaway HTML pages or explainer videos, alone or combined, chosen by project and context. 0
- latex 0.1.0 Reads your LaTeX header's macros so math renders in the desktop app, and draws math as Unicode in the terminal 0
- agent-skills 0.1.1 Loads skills from the cross-harness .agents/skills directories (project and ~) into Claude Code: listed for the model and runnable as /<skill>. 0
- pi-prompt 0.1.0 Replaces Claude Code's core system prompt with pi's coding agent prompt; /pi-prompt toggles it, remembered across sessions. 0
- agent-models 0.1.0 Pins the model each subagent type runs on, set in /config or with /agent-models 0