10 tagged agent-observability, measured the same way as everything else here.
Plugin Claude Code
Bundles 3 skills · 215 tokens together
Route model calls and browse durable BRO conversations in native scrollback. Run Thread/Turn conversations with FIFO input, steering, Codex-style AGENTS.md startup context and nested rules, six native tools (read, glob, grep, write, edit, shell), bounded read workers, configured MCP client tools, skills discovery and…
Plugin Claude Code
Bundles 12 skills, 2 agents · 1,579 tokens together
ax - the agent experience layer. Local graph of every Claude Code + Codex session, skill invocation, edit, and commit. Surfaces what to use, what to ground on, and which experiments to package next.
monte-carlo-data/mc-agent-toolkit
Plugin Claude Code
Monte Carlo Agent Toolkit — data observability for AI coding agents. Surfaces blast radius, active alerts, and monitor coverage gaps before you edit dbt SQL. Includes skills for incident response, proactive monitoring, storage cost analysis, and push ingestion. Hooks enforce data-safety checks automatically as you…
Plugin Claude Code
Bundles 1 skill, 2 hooks, 1 MCP server · 82 tokens together
Standalone visualization MCP for Cortex — a live neural-graph galaxy of every project, file, symbol, memory, discussion and wiki page, plus a per-session execution trace. Read-only bridge over Cortex's shared PostgreSQL and the /.claude artifacts.
Plugin Claude Code
Announces in an Agent PTT voice channel what Claude Code is working on — each project speaks with its own auto-designed voice.
podlayer/message-drop-sentinel
Plugin Claude Code
Detects Claude Code's silent mid-turn message drops and provides a delivery channel the bug can't touch.
Plugin Claude Code
Flight recorder + undo for Claude Code sessions: append-only journal of every Bash/Edit/Write call, pre-action snapshots (incl. Bash file effects) for one-click undo, dangerous-command escalation, and a durable kill switch. Operator console: npx -y agent-rewind ui → http://localhost:4821.