TokenOracle

Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.

Judges Panel

45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.

agenttrace-session-audit

Audit local AI coding-agent sessions with agenttrace. Use when the user asks to inspect Claude Code, Codex CLI, Gemini CLI, Qwen Code, Aider, Cursor, OpenCode, Oh My Pi, Kimi, Copilot-style, or generic JSON/JSONL sessions for cost, tokens, tool failures, latency, anomalies, health, diffs, or CI gates.

accelerate

Use when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.

Io.Github.Iris Eval/Mcp Server

The agent eval standard for MCP. Score every agent output for quality, safety, and cost.

Sundr Repair Advisor

Repair or replace? Get device repair costs, local shops, trade-in values.

haiku-pilot

Haiku-first execution playbook: through deliberate prompt structure, sub-agent delegation, and quantitative escalation gates, get Haiku 4.5 to produce near-Opus quality on most tasks. Escalate to Sonnet/Opus only when gates trigger. Triggers: "haiku", "Haiku", "Haiku mode", "haiku-pilot". Do NOT use for: cost-only token optimization, file-count cognitive heuristic, agent dispatch table, CLAUDE.md / rules audit, harness health check. This SKILL is a runtime router + escalation gate, not a decision tree or directory.

context-monitor

Monitor conversation context and prevent MAX mode by warning at token thresholds and generating handoff summaries. Use when context approaches 100K/150K/180K tokens or when working with high-cost files.

ClawWork Economic Survival Protocol

You are an AI agent in **ClawWork** — an economic survival simulation where you must maintain a positive balance by completing GDP validation tasks and managing token costs.

bom

BOM (Bill of Materials) management for electronics projects — the primary orchestrator skill that coordinates DigiKey, Mouser, LCSC, element14, JLCPCB, PCBWay, and KiCad skills into a unified workflow. Create, update, and maintain BOMs with part numbers, costs, quantities stored as KiCad symbol properties. ALWAYS trigger this skill for any task involving component sourcing, pricing, ordering, distributor searches, BOM export, or fabrication preparation — even if the user names a specific distributor or fab house (e.g. "search DigiKey for...", "generate JLCPCB BOM", "order from Mouser"). This skill decides which distributor/fab skills to invoke and in what order. Also trigger on phrases like "what parts do I need", "order components", "how much will this cost", "export for JLCPCB", "find parts for this board", "cost estimate", "compare pricing", or "check stock".

agent-project-development

This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches. NOT for evaluating agent quality or building evaluation rubrics (use agent-evaluation), NOT for multi-agent coordination or agent handoffs (use multi-agent-patterns).

10 Claude sessions running. What are they doing? Live dashboard — monitor, cost tracking, search, sub-agent visibility.

sidecar

Spawn conversations with other LLMs (Gemini, GPT, ChatGPT, Codex, o3, DeepSeek, Qwen, Grok, Mistral, etc.) and fold results back into your context. TRIGGER when: user asks to talk to, chat with, use, call, or spawn another LLM or model; user mentions Gemini, GPT, ChatGPT, Codex, o3, DeepSeek, Claude (as a sidecar target), Qwen, Grok, Mistral, or any non-current model by name; user asks to get a second opinion from another model; user wants parallel exploration with a different model; user says "sidecar", "fork", or "fold". CRITICAL RULES: (1) ALWAYS launch sidecar CLI commands with Bash tool's run_in_background: true. Never run sidecar start/resume/continue in the foreground. (2) The fold summary returns on stdout when the user clicks Fold in the GUI or the headless agent finishes. Use TaskOutput to read it when the background task completes. (3) Use --prompt for the start command (NOT --briefing). --briefing is only for subagent spawn. (4) NEVER use o3 or o3-pro unless the user explicitly asks for it by name. These models are extremely expensive ($10-60+ per request). If the user asks for o3, warn them about the cost before proceeding. Default to gemini for most tasks. (5) When the user asks to query MULTIPLE LLMs simultaneously (e.g., "ask Gemini AND ChatGPT", "compare Gemini vs GPT"), ALWAYS use --no-ui (headless) for all of them unless the user explicitly requests interactive. Opening multiple Electron windows at once is disruptive. Launch them all in parallel with run_in_background: true.

claude-api-cost-optimization

Save 50-90% on Claude API costs with Batch API, Prompt Caching & Extended Thinking. Official techniques, verified.

exploring-llm-traces

ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace URL (e.g. /llm-observability/traces/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs.

Philadelphia Restoration

Philadelphia water and fire damage restoration: assessment, insurance, costs, and knowledge search.

Robot Resources Router

Intelligent LLM routing proxy — 60-90% cost savings by auto-selecting the cheapest model

Session Monitoring

Provides awareness of claudectl session state, health checks, and cost tracking. Activated when the user asks about session health, spending, brain decisions, or multi-session coordination.

algorithm-selection

Implements candidate-model selection logic that runs after a routing decision matches, including model ranking, cost-aware routing, and latency-aware model choice. Use when reading or modifying how the router picks which model serves a matched decision.

benchmark-context

Automatically benchmark your custom memory implementation against established systems like Supermemory. Set up a public benchmark, or create your own. Compare solutions against quality, latency, features and cost, easily, with a simple UI and CLI.

Io.Github.Dewars30/Fulcrum

AI governance MCP server for policy enforcement, cost control, and observability.

Io.Github.Jeff Atriumn/Tokencost Dev

LLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM

bigquery-cost-optimization

Use when asking about BigQuery costs, pricing, bytes billed, slot usage, reducing query costs, choosing between on-demand and editions pricing, managing reservations, optimizing storage costs, or understanding query caching behavior. Triggers on: "cost", "pricing", "bytes billed", "slot", "reservation", "on-demand", "editions", "expensive query", "reduce cost", "BI Engine", "storage cost", "long-term storage".

Mcp

Connect AI assistants to Warpmetrics — query runs, calls, costs, and outcomes.

Mcp Server

Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains.

cost-report

Query and report on API usage costs across LLM, embedding, and tool providers

OCI Pricing

Oracle Cloud Infrastructure pricing data with cost calculators and comparisons

Mcp Cost Tracker Router

Real-time cost awareness for MCP agent workflows

Deepseek

MCP server for DeepSeek AI with chat, reasoning, sessions, function calling, and cost tracking

Io.Github.Soulmaten7/Potal

Total landed cost API for cross-border commerce. 240 countries, 113M+ tariff records.

oak

Find out what happened, what was decided, and what depends on what in your codebase. Use this skill whenever you need to: recall past decisions or discussions ("what did we decide about X?"), check what might break before refactoring ("what depends on this module?"), find conceptually similar code that grep would miss ("all the retry/backoff logic"), look up past bugs, gotchas, or learnings, query session history or agent run costs, store observations about the codebase, or understand how components connect end-to-end. Powered by semantic search, memory lookup, and direct SQL against the Oak CI database (.oak/ci/activities.db). Also use when the user mentions oak_search, oak_context, oak_remember, oak_resolve_memory, or asks to run queries against activities.db or oak.

azure-adr

Creates Azure Architecture Decision Records with WAF mapping, alternatives, and consequences. USE FOR: ADR creation, architecture decisions, trade-off analysis, WAF pillar justification. DO NOT USE FOR: Bicep/Terraform code generation, diagram creation, cost estimates.

Agent Observability

Agent observability: structured logging, cost tracking, and compliance audit trails

analyzing-usage

Analyze Claude Code usage, cost, efficiency, and burn rate using ccusage and termgraph. Use when user says "usage", "cost", "spending", "tokens", "analyze usage", "how much did I spend", "usage report", "budget", "burn rate", "efficiency", "cache hits", "ccusage", "ccw", "ccp".

context-doctor

Visualize and diagnose OpenClaw context window usage. Generates a terminal-rendered breakdown showing workspace files (status, chars, tokens), installed skills inventory, and token budget allocation across bootstrap components. Use when: (1) user asks about context window health or token usage, (2) debugging agent quality degradation ("agent got dumber"), (3) after editing workspace files to verify impact, (4) auditing bootstrap overhead. NOT for: conversation history analysis, model selection, or cost tracking.

bounty-hunter

A professional AI bounty hunter persona named Atlas. Use when seeking, evaluating, or executing paid tasks (bounties, freelance, bug hunting) to maximize profit while minimizing token costs and ensuring secure payouts.

agent-session-monitor

Real-time agent conversation monitoring - monitors Higress access logs, aggregates conversations by session, tracks token usage. Supports web interface for viewing complete conversation history and costs. Use when users ask about current session token consumption, conversation history, or cost statistics.

Llmkit

AI cost tracking: 14 tools for spend, budgets, Claude Code + Cline costs, Notion sync

Io.Github.Gammell53/Clawwork

AI agent project management — task boards, progress tracking, and cost reporting.

cost-mode

Cost-conscious Claude Code mode. Reduces token usage 40-70% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.

MedRates

Search US hospital prices, compare costs, and find insurance-negotiated rates.

ai-image-creator

Generate PNG images using AI (multiple models via OpenRouter including Gemini, FLUX.2, Riverflow, SeedDream, GPT-5 Image, proxied through Cloudflare AI Gateway BYOK). Use when user asks to "generate an image", "create a PNG", "make an icon", "make it transparent", or needs AI-generated visual assets for the project. Supports model selection via keywords (gemini, riverflow, flux2, seedream, gpt5), configurable aspect ratios/resolutions, transparent backgrounds (-t), reference image editing (-r), and per-project cost tracking (--costs).

codealive-context-engine

Semantic code search and AI-powered codebase Q&A across indexed repositories. Use when understanding code beyond local files, exploring dependencies, discovering cross-project patterns, planning features, debugging, or onboarding. Queries like "How does X work?", "Show me Y patterns", "How is library Z used?". Provides search (fast, returns file locations and descriptions) and chat-with-codebase (slower, costs more, but returns synthesized answers).

model-hierarchy

Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity. Use this skill when: (1) deciding which model to use for a task, (2) spawning sub-agents, (3) considering cost efficiency, (4) the current model feels like overkill for the task. Triggers: "model routing", "cost optimization", "which model", "too expensive", "spawn agent".

Agentic Platform

Free MCP tools: the only MCP linter, health checks, cost estimation, and trust evaluation.

tma1

Query TMA1 observability data. Use when the user asks: how much did I spend, token usage, what has my agent been doing, agent cost, show me traces, show me events, check for errors, model comparison, tool usage.

💰 Meeting Cost Calculator

Analyzes your calendar to compute exactly how much time you spend in meetings over a given period. Breaks down total hours, percentage of your work week consumed, average meeting duration, attendee-hours (a proxy for organizational cost), and ranks your most expensive recurring meetings so you can m

Mcp Server Agent Analytics

Track AI agent fleet performance, costs, anomalies, and trends.

pinion-balance

Get ETH and USDC balances for any Ethereum address on Base. Costs $0.01 USDC via x402.

Aristocles Data API

Subscription pricing, trade costs, and financial data for AI agents across 5 countries.