Know what every AI call really costs — floe-guard meters STT + TTS + LLM + telephony per call (Pipecat, LiveKit — Python & TypeScript), keeps a live ledger of real spend, and hard-stops the next turn before it crosses a USD ceiling. Free Coverage Score + 7-day history on connect. Use when an agent's spend must be seen…
Estimate the cost of a task before starting it. Analyzes task complexity, predicts token usage, and compares cost across all Claude models. Use when user says 'estimate cost', 'how much will this cost', 'cost estimate', or '/cost-estimate'.
Real-time cost tracking and budget management for Claude Code sessions. Shows current spend, burn rate, budget status, per-tool and per-model breakdown. Use when user says 'cost', 'budget', 'spending', 'how much', 'token usage', 'export', or '/cost-guardian'. Subcommands: budget, resume, reset, config, export, status.
Advanced cost intelligence: efficiency scoring, waste detection, ROI metrics, model savings calculator, anomaly detection, and GitHub badge generation. Use when user says 'insights', 'efficiency', 'waste', 'roi', 'savings', 'anomaly', 'badge', or '/cost-insights'.
Systematically test Monarch Money MCP tools in read-only mode (27 tools, 58 tests) or write-enabled mode (all 44 tools, 110 tests). Account-agnostic (discovers IDs at runtime) and self-cleaning (deletes everything it creates in write mode). Batches each phase into a subagent so large tool payloads stay out of the…
Enforce and inspect token/dollar budgets for Server OS agents. Use when the user asks about agent spend, budgets, cost ledgers, or wants to prevent runaway token usage.
A deep-research skill that splits a research task among two to eight built-in agents working in parallel. It includes citation management, lightweight numerical checks, file delivery, and progress updates.
An executive-assistant skill for planning complicated schedules and managing time across work and personal commitments. It can use Amap, a Chinese mapping service, for route planning and commute-time estimates.