LLM cost and token optimization

Controls the RTK filter set and context-handling settings in OmniRoute, with endpoints to try compression on sample text and read back retained output.

diegosouzapw/OmniRoute

Queries OmniRoute call logs, usage history and analytics, filters them by provider, model, status or cost, and reads or sets usage budgets.

diegosouzapw/OmniRoute

Verifies how Cline marks Anthropic prompt-cache breakpoints on the wire, then adds a tools breakpoint and tunes the cache TTL in its AI SDK code.

OnlyTerp/prompt-cache-skills

Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5.5 default fallback, full 1M context at standard price)

egorfedorov/claude-context-optimizer

Builds an explorable HTML report of Claude Code usage over a chosen period: tokens, cache behavior, subagents, skills and costly prompts.

anthropics/claude-plugins-official

Always-on context compression for OpenClaw. An agent skill from Supercompress/Supercompress.

Supercompress/Supercompress

Estimate Kubernetes infrastructure costs by querying cluster node, pod, PVC/PV, and LoadBalancer data, applying cloud pricing models, and producing cost attribution reports with storage and…

initializ/forge

Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.

cobusgreyling/loop-engineering

Patch guide for adding a stable per-task prompt_cache_key to Cline's OpenAI native provider so cached token counts stop reading as zero.

OnlyTerp/prompt-cache-skills

This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending…

guanyang/open-agent-hub

This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and…

guanyang/open-agent-hub

Designs, tests and refines LLM prompts: zero-shot, few-shot and chain-of-thought patterns, system prompts, structured output schemas and evaluation test suites.

Jeffallan/claude-skills

An advanced skill for L3 autonomous loops. An agent skill from cobusgreyling/loop-engineering.

cobusgreyling/loop-engineering

Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI.

pydantic/pydantic-ai

Prepares many-file, single-turn transforms such as translating or rewriting as a plan, then submits it to the asynchronous, half-price DashScope Batch API through the qwen batch CLI.

QwenLM/qwen-code

Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn.

Archive228/loopkit

A skill your agent uses when the user wants to capture AI tool costs, review spending trends, set cost budgets, or integrate cost data into health snapshots — guides quarterly cost capture, records…

Habitat-Thinking/ai-literacy-superpowers

Specifies how quota-axi reads LLM subscription quota windows, derives pace and runway, computes a selection signal and renders output in TOON, JSON and TUI tiers.

kunchenguid/quota-axi

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache…

davila7/claude-code-templates

Guide for debugging OhMyCode issues. An agent skill from AlphaLab-USTC/OhMyCode.

AlphaLab-USTC/OhMyCode

Checks every subagent prompt before spawning, swapping pasted files and context for paths and short summaries and trimming the brief, to avoid multiplied token cost.

LichAmnesia/lich-skills

追蹤並計算當前 session 的 Token 使用量和花費（USD）。產出前後對比報告，幫助使用者了解 workspace 優化的實際效益。

zeuikli/claude-code-workspace

Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log.

affaan-m/ECC

Continue's prompt caching is opt-in via config and off by default.

OnlyTerp/prompt-cache-skills

Track session costs, set budget alerts, and optimize token spend.

rohitg00/pro-workflow

A skill your agent uses when the user asks to optimize prompts, design prompt templates, evaluate LLM outputs with an eval set, measure RAG retrieval quality, validate agent/tool configurations…

alirezarezvani/claude-skills

Generate a concise daily infrastructure briefing. An agent skill from bolivian-peru/os-moda.

bolivian-peru/os-moda

A skill your agent uses to classify the documentation impact of a pull request diff, returning one of three verdicts -- no-change, in-place edit, or structural change -- with bounded LLM cost.

microsoft/apm

This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal…

guanyang/open-agent-hub

This skill should be used when a model gets read-write control over its own live context window instead of a harness-scheduled compaction policy: the context exposed as an editable file the model…

guanyang/open-agent-hub

AI Build Cost Tracker — track how much AI is costing you per feature.

Houseofmvps/ultraship

A skill your agent uses when context compression is imminent, when resuming a session, or when preserving critical decisions across long tasks.

vibeeval/vibecosystem

Context window management and token optimization guide. An agent skill from jh941213/my-cc-harness.

jh941213/my-cc-harness

Analyze markdown files for token efficiency and reduce context-window bloat.

Azure/azure-sdk-tools

Get RED metrics + service maps + frontend RUM + AI/LLM monitoring out of Grafana Cloud — Application Observability (tracesspanmetrics from OTel traces, p50/p95/p99 latency, exemplar-to-trace…

grafana/skills

Analyze and reduce token consumption in agentic workflows — guardrail-specific entry points, measurement, and optimization techniques.

github/gh-aw

Monitor LLMs and agentic apps: performance, token/cost, response quality, and workflow orchestration.

aspectrr/deer

Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost).

Tommy-yw/RunbookHermes

Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear).

sickn33/agentic-awesome-skills

Implement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching.

sickn33/agentic-awesome-skills

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation)

sickn33/agentic-awesome-skills

OpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.

OnlyTerp/prompt-cache-skills

Optimize LLM prompt caching hit rate to reduce API costs and improve latency.

affaan-m/ECC

Ranked symbol map of a codebase within a token budget — a compact "what matters in this repo" before reading files.

AnastasiyaW/codex-claude-code-config

Master the four operations of context engineering — Write, Select, Compress, Isolate.

rohitg00/pro-workflow

Send images, audio, video, or documents into an AG2 beta Agent alongside text.

ag2ai/build-with-ag2

Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions.

PostHog/posthog

Orchestrate free opencode workers from Claude Code to cut token costs.

alirezarezvani/claude-skills