o9k — token-efficiency meta-framework for AI coding agents (Claude Code, Cursor, Codex, OpenCode, Hermes): seven pillars incl. multi-agent roster + memory MCP
Plugin Claude Code
Bundles 1 skill · 66 tokens together
Output compression: telegraphic response style with lite/full/ultra levels and automatic fallback to full prose for safety-critical content. Adapted from JuliusBrussee/caveman (MIT).
Plugin Claude Code
Bundles 5 skills, 1 hook · 396 tokens together
The o9k doctrine: token-efficiency rules of engagement and the arbitration layer that keeps efficiency plugins from colliding. Zero-effort: a SessionStart hook activates the doctrine automatically, checks dependencies for updates (npm o9k package + git marketplace channels; refreshes multi-CLI skills/hooks after…
Plugin Claude Code
Bundles 1 skill · 84 tokens together
Persistent memory integration: session-start briefing, on-demand recall, save-before-compact. Prefers TIM (npm tim-cli) when present; falls back to hmem (npm hmem-mcp).
Plugin Claude Code
Bundles 3 skills · 250 tokens together
Discovery & onboarding: a GitHub Scout skill for finding new agent frameworks and slotting them into the o9k compatibility matrix, one-command companion bundle installs, and a bundle benchmark for measuring companion combos.
Plugin Claude Code
Bundles 2 skills · 166 tokens together
Multi-agent model registry: role-based model selection with fallback chains, usage-limit awareness, tmux worker dispatch, limit-triggered session handoff, mailbox runs + crash resume. Selection is deterministic code, not LLM reasoning.
Plugin Claude Code
Bundles 1 skill · 80 tokens together
Context discipline: load structure before files, search before read, one canonical repo map per session.
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: