Syrtis
Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗Claude Code mods, plugins, skills, hooks, status lines and MCP servers. Browse community builds with original sources and L0–L3 permission levels.
13 projectsTrack what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗activity: what Claude is doing right now, and the moment it's waiting on you. A Claude Code function-hook plugin that shows live tool calls with real commands and timers, approvals you owe, running subagents, and the current todo plan.
X post showcasing a Claude Code prompt cache control mod that adds a cache bar, sends notifications to keep the cache warm, and provides a /cache panel. Install via npx claude-code-templates@latest --mod observability/prompt-cache-control.
▶ ♫See what your skills and MCP servers put in front of Claude, which tools it called, what it read back, and what it did next. Observe-only; writes local logs only.
Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗lot-map is a Claude Code mod that renders a live map in a pane beside the chat, pulsing from the agent to stations like Files, Shell, Network and Agents on every tool call.

A Claude Code plugin that opens a live local HTML page showing every change Claude makes, including diffs, edit reasons, checks, and before/after behavior flows.

A globe of everything your Claude session talks to: tool calls, sockets and bytes traced to hosts, countries and orgs, with a deny-list that blocks before a call runs.
Structured logging, distributed tracing, and metrics — correlate agent swarm activity with application telemetry. As a mod (ADR-445): a tighten-only guard on its tools, /observe-mod, and a status file the console shows
Records which real checks ran and which files changed after them; status line, /evidence, and an evidence tool Claude reads before claiming tested.
BazaarLink is an OpenAI-compatible AI API gateway: one key for 140+ AI models, pay as you go, with budget limits.
bazaarlink.aiVisit sponsor ↗A Claude Code hooks-module flag probe that logs whether hooks modules are ON per session and reconciles inferred OFF states.
One live line above the prompt per running subagent: time, tool count and what it's doing. /radar shows every agent and its messages.

Visual components for [Claude Code](https://claude.com/claude-code) mods: sparklines, gauges, KPI tiles, heatmaps, and live agent observability (tool timeline, token burn, subagent tree, context map). They draw in the terminal and the desktop app.

A k9s-style Kubernetes pod pane that lives beside Claude Code
