Browse the directory

A practical walkthrough of token and spend accounting in the Claude Agent SDK. Read total_cost_usd from the result message, deduplicate parallel tool calls that share an assistant id, break spend down per model with modelUsage, sum cost across query() calls yourself, and read cache_creation/cache_read tokens.

Expert husky capability pack for lightweight local quality gates, commit message enforcement, and low-friction contributor workflows.

Design and validate model routing strategies that reduce cost and latency while preserving output quality.

Expert OpenClaw operator capability skill for secure deployment, policy governance, tool boundaries, and production observability.

Open-source semantic cache for LLM applications that stores and reuses model responses through embedding similarity to cut API cost and latency, with modular embedding, vector-store, cache-storage, and eviction components.

Official AWS Labs MCP server for AWS Billing and Cost Management that lets AI assistants analyze costs and usage, monitor budgets and anomalies, and surface Cost Optimizer, Savings Plans, and Reserved Instance recommendations.

Community reusable agent prompt for Claude Code and agent spend governance using official costs documentation: budgets, model tier policy, caching awareness, anomaly triage, and team reporting workflows.

Expert prompt caching cost audit capability pack for measuring Claude Code cache hit rates, identifying cache invalidation triggers, and reducing token spend from CLAUDE.md edits, model switches, and startup load changes.

Read-only AWS FinOps MCP server that lets Claude query Cost Explorer cost and usage data, compare AWS CLI profiles, filter by tags or dimensions, check AWS Budgets, and audit for stopped EC2 instances, unattached EBS volumes, and unassociated Elastic IP addresses across selected regions.

Open-source observability platform and SDK for tracing, debugging, replaying, and cost-monitoring AI agent and LLM application runs.

Local CLI for analyzing Claude Code and other coding-agent token usage, costs, sessions, and billing-window activity from local usage data.

Delega hosted MCP server that creates AWS cost estimates and shareable AWS Pricing Calculator links from natural language without leaving your AI client.

Troubleshoot Claude Code prompt caching: cache invalidation triggers, prefix stability, cost spikes, and verifying cache hits during long sessions.

Team cost governance for Claude Code: budgets, model selection policy, prompt caching awareness, anomaly review, and communicating spend with engineering leads.

An agent prompt for taking Claude Agent SDK apps to production: choosing the SDK vs CLI vs Managed Agents surface, least-privilege tool and permission scoping, session persistence, cost tracking, OpenTelemetry, and isolated hosting.

A reusable agent prompt that vets a Claude Code plugin or marketplace before a team installs it. It walks source trust, the plugin's Will-install list and bundled components (skills, agents, hooks, MCP servers, commands), the context-window cost, version pinning, and the user/project/local/managed install scope.

Claude Code statusline that reads Anthropic Claude Code Analytics Admin API data and shows daily estimated cost, hourly pace, sessions, and budget pressure.

Real-time burn rate monitor showing cost per minute, tokens per minute, and projected daily spend to prevent budget overruns during Claude Code sessions.

Claude Code session health aggregator providing A-F grade based on cost efficiency, latency performance, productivity velocity, and cache utilization with actionable recommendations.

Analyze and optimize token costs with real-time budget tracking. Provides cost projection, usage analytics, and model selection recommendations using Sonnet/Haiku pricing.

An agent persona for designing multi-cloud infrastructure across AWS, GCP, and Azure using their Well-Architected frameworks: cost optimization, reliability (high availability and disaster recovery), security, and operational excellence.

Real-time AI cost tracking statusline with per-session spend analytics, model pricing, and budget alerts

Feature-rich statusline using Python's Rich library for beautiful formatting, progress bars, and real-time token cost tracking

Time-tracking statusline showing elapsed session duration, tokens per minute rate, and estimated cost with productivity metrics

Expert zero-budget launch capability pack for building and shipping SaaS using free-tier infrastructure and constrained execution plans.

Decide when Claude Code fast mode (/fast) is worth the higher Opus per-token cost: toggle steps, pricing tradeoffs, rate-limit fallback, admin controls, and workflows where standard mode is safer.

Source-backed agent that reduces token cost and latency in Claude Code by improving prompt-cache hit rates, advising on stable context ordering, lean CLAUDE.md, on-demand skills, and MCP tool-search, grounded in the official docs.

A practical walkthrough of the Claude Code context window: what consumes it (system prompt, memory, CLAUDE.md, MCP tools, skills, file reads, history), how each piece loads, and how the /context view helps you design leaner prompts and setups.

Diagnose and fix Claude Code 429 errors, session and weekly usage limits, and high token consumption using built-in commands and documented settings.

A Claude Code statusline that reads prompt-cache token metrics from session JSON and renders a color-coded hit-rate bar with an estimated token-savings readout.