Context Token Budget — AI skill for Claude Code
Guard AI context usage with a fail-closed token budget — stop burning tokens.
How to install Context Token Budget
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open zhaoxinghua09-cell/context-token-budget and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Context Token Budget does
Guard AI context usage with a fail-closed token budget — stop burning tokens. 用 fail-closed 的 token 预算守护 AI 上下文，防止积分烧光。
Alternatives in AI
- Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
- Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★
- Vomit — Clean up Claude 5's token vomit with a separate LLM 176 ★
README
Context Token Budget (上下文预算守护)
**Estimate tokens, enforce a budget, fail closed before overspend.** **估算 token、执行预算、超额前 fail-closed。**
[](https://github.com/zhaoxinghua09-cell/context-token-budget) [](LICENSE) [](CONTRIBUTING.md)
Usage / 用法
python scripts/budget.py [--limit N] [--json]License
MIT (code) · All rights reserved (SKILL.md theory text). © 2026 Steven Zhao / SynomosAI.
Related Skills
Token Save MCP
Stop your coding agent burning context on file reads. Delegates big reads to a cheap worker model and returns
Geo Guard AI
Geo-restriction for AI CLIs: block Claude Code & Cursor from running outside allowed countries. Cross-platform
AI Engineering Claude C1 Harness Engineering Project
Four Claude Code systems from the Harness Engineering capstone: a stop_reason-driven agentic loop with tool de
Lowkey Effort
An AI skill that auto-calibrates response depth based on task complexity — so you stop burning tokens on simpl
Agent Doctrine
A free, opinionated set of doctrine files that keep AI coding agents (Claude Code, Cursor, Codex, Copilot, Win
OmniGlyph
Cut your Claude bill 59–70% by rendering bulky LLM context as dense PNG pages — 100% read accuracy, exact per-
Related Agents
AI Manager
Orchestrates work via the 4 Codex agents, manages context/memory lifecycle and token budget
Agent Harness Optimizer
Context window, token budget, and agent harness optimization specialist. Analyzes transcript bloat, tunes prom
Conversation Compacter
Compacts long conversations into ~300 token summaries preserving critical context, todos, file paths, and deci
