Best LLM cost and token optimization skills for Claude Code, Codex and other agents.

Uses the Defuddle CLI to pull clean, readable Markdown, JSON or metadata from web pages, stripping navigation, ads and clutter to save tokens.

kepano/obsidian-skills

Finds every LLM workflow in a repository, proposes a labeling table and, once you agree, wires labels so Caveman Cloud groups spend per workflow.

JuliusBrussee/caveman

Read-only review of Caveman Cloud data to explain where LLM spend goes: cost, score, workflows, traces, latency, errors, routing and verified savings.

JuliusBrussee/caveman

Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue.

JuliusBrussee/caveman

Mines local Copilot CLI session logs for dotnet/maui to rank costly or failing runs, tag recurring failure modes, propose repo edits and emit guard evals.

dotnet/maui

Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

mksglu/context-mode

This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve…

guanyang/open-agent-hub

CodexBar read. Provider usage, limits, credits, config health. JSON. No writes.

steipete/CodexBar

Hands simple, deterministic tasks such as typo fixes, tests and small refactors to cheaper models through the ccs CLI, choosing a profile from your config.

kaitranntt/ccs

Routing rules for using context-mode MCP tools in Antigravity CLI: sandboxed code runs, file analysis, indexed search and web fetches that keep large output out of the conversation.

mksglu/context-mode

Configures OpenClaw to use free OpenRouter models, setting the best one as primary and adding ranked fallbacks so rate limits do not interrupt work.

Shaivpidadi/FreeRide

Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.

lobehub/lobehub

This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped…

guanyang/open-agent-hub

A skill your agent uses when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain.

DenisSergeevitch/agents-best-practices

Converts large PDF, DOCX, PPTX, XLSX and CSV files into markdown or CSV plus an index before the agent reads them, so tokens go to the compressed copy.

NateBJones-Projects/OB1

A professional AI bounty hunter persona named Atlas. An agent skill from 1sadjlk/bounty-hunter-skill.

1sadjlk/bounty-hunter-skill

Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.

JuliusBrussee/caveman

Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".

JuliusBrussee/caveman

Refactor a too-long SKILL.md by progressive disclosure: measure token cost, classify every section KEEP/CUT/MOVE, shorten the body into references/ and scripts/, verify nothing was lost.

luongnv89/asm

A skill your agent uses when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.

mikehasa/agentacct

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

Audit local AI coding-agent sessions with agenttrace. An agent skill from luoyuctl/agenttrace.

luoyuctl/agenttrace

A skill your agent uses when maintaining or optimizing OpenClaw workspace files — AGENTS.md, TOOLS.md, SOUL.md, USER.md, IDENTITY.md, HEARTBEAT.md, BOOT.md, MEMORY.md, and related checklists and…

win4r/openclaw-workspace

Estimates what a codebase would cost a traditional human team to rebuild, with P10, P50 and P90 ranges cross-checked by COCOMO II, Function Points and LOCOMO.

jbarbier/claude-code-cost-estimate

Switches the agent to a terse reply style that gives the answer first, drops filler, and keeps every technical fact, command and number exact.

JuliusBrussee/caveman

A skill your agent uses when installing, verifying or configuring OMNI, when command output carries an [OMNI: ...] marker, or when output looks shorter than expected.

fajarhide/omni

Visualize and diagnose OpenClaw context window usage. An agent skill from jzOcb/context-doctor.

jzOcb/context-doctor

Cross-system agent token/cost audit (Claude Code, Codex, OpenClaw, Hermes, OpenCode): idle burns, model misrouting, config bloat, with dollar savings.

alexgreensh/token-optimizer

Sends one prompt to Claude, GPT through the Codex CLI and Gemini, then tabulates response time, token use and cost, with an optional judged quality score.

garrytan/gstack

Give the human an off switch and a cost meter for the coding agents on this machine, using ClawMetry.

vivekchand/clawmetry

Toolkit for creating and validating skills and subagents. An agent skill from rfxlamia/skillkit.

rfxlamia/skillkit

Weekly multi-agent audit for serious bugs (data integrity, silent caps, staleness, timestamp math, trust boundaries).

VasiHemanth/tokentelemetry

Connect any AI agent to MCP servers through mcptoon — one config synced everywhere, one stdio gateway, 99.2% fewer tokens on tool discovery.

activeing123/mcptoon

Audit an agent's context layout against the four places: system prompt, tools, history, tail.

undefined-ui/second-brain-os

Integrate and use Jev, TypeSafe AI's System One decision model, in production codebases.

disler/ten-levels-of-jev

Picks a small, graph-based slice of source with Trailmark and hands a focused code task to a smaller or local model without exposing the whole repository.

trailofbits/skills

Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle.

yuting0624/antigravity-for-claude-code

Checks and tunes token-saver output compression: reads stats, explains why a command was or was not compressed, and edits config files or environment variables.

ppgranger/token-saver

Acts on a Caveman learn report: reviews ranked token sinks, applies cost-lowering edits one at a time with your consent, and reports what each fix returned.

JuliusBrussee/caveman

Turns the lead model into a foreman that plans, routes and verifies while cheaper Claude, Codex or Grok workers do the typing, using a per-machine routing card.

olsenbrands/fable-foreman

Read your own agent telemetry from ClawMetry (waste, progress, cost) and act on it before finishing a task.

vivekchand/clawmetry

Answers token usage and cost questions from the Claude Command Center throughput dashboard and shares its link, for the last 7 days or one session.

amirfish1/claude-command-center

SmartCrusher + CCR context compression — crunch large JSON arrays, tool outputs, and search results to save tokens.

momori777/Artemis

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

diegosouzapw/OmniRoute

Guidelines for driving a workspace's embedded browser with the fewest tool calls, smallest state reads and no needless screenshots or waits.

holaboss-ai/holaOS

Guides building, debugging and tuning apps on the Claude API and Anthropic SDK, including prompt caching, and migrating code between Claude model versions.

warpdotdev/warp

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

Audit and optimize frontmatter description fields across documentation pages to keep them concise and token-efficient.

lynx-family/lynx-website