Make the most out of your subscriptions. Delegate work to other harnesses and models, while keeping your main session the orchestrator. Nothing new to learn. Keep working like you do, but better.
Claude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage
Security hooks and monitoring for Claude Code — quiet overrides, SSRF protection, MCP compression, OTEL tracing
🌿 Prune your AI agent's context window. Reduce token usage by 70-95% with hierarchical memory. Replace flat MEMORY.md with a bonsai-shaped domain tree. Progressive disclosure, zero dependencies. Works with OpenClaw and any LLM agent framework.
Evaluate and optimize your AI agent context. Save tokens, save money.
Say more with less. Claude Code skill/plugin that cuts ~60-70% of output tokens while keeping natural, readable English.
Optimize Claude Code token usage — 22 skills, 8 hooks, 6 rules. One npm install. Zero manual steps. Cut costs by 67%.
Audit and reduce the hidden token overhead in every Claude Code conversation. Monthly skill + automation.
One-command bootstrap for a fully wired Claude Code workstation — installs Claude Code, RTK, context-mode, code-review-graph, caveman, hooks, MCP servers, statusline, and 39+ curated skills. macOS + Linux.
A production-ready Claude Code setup. Global CLAUDE.md, coding rules, per-project memory, and token optimization.
Token Budget 💰 — a Spec Kit extension for token-efficient SDD
Jump-start and measure token-efficient AI coding workflows for GitHub Copilot and Claude Code.
🪨 Make Claude Code talk like a smart caveman ~75% fewer output tokens, 100% accuracy. Auto-enabled + statusline.
Claude Code plugin: quiets noisy Bash output (tests, builds, buildkite, docker, bazel, big git diffs) by redirecting to a temp log and surfacing only a summary.
Local-first AI coding session health manager for Codex and Claude Code.
Token-economical, quality-first model & effort router for Claude Code — auto-delegates each task to the cheapest sufficient tier (Haiku -> Sonnet -> Opus -> Fable) with matching reasoning effort.
Hermes Agent frontend skillpack: Ponytail + Graphify + Headroom token-trim workflow
Big idea first, then fewer words, then less code. One switch for 12+ AI coding agents — measured 23% fewer tokens on long-horizon agentic runs.
A Claude Code hook that compresses tool output before it reaches your context window. Measured 65.6% token savings across 91,287 commands.
To associate your repository with the token-optimization topic, visit your repo's landing page and select "manage topics."