token-saver

token-saver is a skill for Claude Code, Codex from OpenWorkai/codex-token-saver. It costs 0 tokens per session (1,906 once invoked), scanned B, original, MIT.

A guide to reducing token use in Codex conversations, where tokens are the units of text sent to and from the language model.

In plain words
What is it for?
It is for planning shorter prompts and sessions, avoiding cache-disrupting changes, and applying token-saving practices to Codex CLI work.
Why use it?
It explains how long conversation history, project instructions, model changes, and prompt caching can affect API usage and cost.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/openworkai/codex-token-saver/token-saver
Any agent
npx skills add OpenWorkai/codex-token-saver --skill token-saver
Clone the repo
git clone --depth 1 https://github.com/OpenWorkai/codex-token-saver

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for token-saver

README.md
[![agentmods](https://agentmods.dev/badge/skills/openworkai/codex-token-saver/token-saver.svg)](https://agentmods.dev/skills/openworkai/codex-token-saver/token-saver)
Your own site
<a href="https://agentmods.dev/skills/openworkai/codex-token-saver/token-saver"><img src="https://agentmods.dev/badge/skills/openworkai/codex-token-saver/token-saver.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,906 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01906
Opus 5 $0.00000 $0.00953
Sonnet 5 $0.00000 $0.00381
Haiku 4.5 $0.00000 $0.00191

Measured 3d ago against content hash 0069083c4b63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

token-saver scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

# ~/.codex/config.toml
token-saver/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Token Saver — OpenAI Codex CLI 省钱工具箱

基于 OpenAI API 缓存机制和 Codex CLI 架构分析,提供可立即执行的 token 优化策略。

姊妹项目:claude-token-saver — Claude Code 版本


核心原理

每轮对话的真实开销

与 Claude Code 类似,Codex CLI 每轮也将以下内容完整打包发送 API:

  1. 系统指令(角色定义、行为准则)
  2. 工具定义(Bash、文件操作、MCP 工具等)
  3. AGENTS.md 项目上下文
  4. 完整对话历史
  5. 本轮消息

第 N 条消息的实际输入 = 前 N-1 条全部内容 + 新消息(线性增长)

OpenAI 提示缓存机制

OpenAI 的 Prompt Caching 是自动的,无需手动设置断点。

特性 OpenAI Anthropic (对比)
缓存触发 自动(前缀 >= 1024 token) 手动断点
缓存折扣 50% 90%
写入溢价 +25%
TTL 5-10 分钟 5 分钟 (Pro: 1 小时)
最小前缀 1024 token 无最小限制

关键区别:OpenAI 缓存折扣只有 50%(Claude Code 是 90%),所以 Codex 用户更需要从减少总 token 量入手,而非仅依赖缓存。

Codex 支持缓存的模型

  • GPT-5.4, GPT-5.3-Codex, GPT-5.2-Codex, GPT-5.1, GPT-4o, GPT-4o-mini, o1, o3-mini
  • 不支持:GPT-4-turbo, GPT-3.5-turbo

三大缓存杀手(Codex 版)

OpenAI 缓存同样基于前缀匹配,但因为是自动管理,杀手场景略有不同。

杀手 1:切换模型

缓存绑定具体模型,与 Claude Code 相同。但 Codex config.toml 里是全局固定模型,一般不会中途切。

  • 风险场景:通过 --model 参数临时切模型
  • 做法:一个会话坚持一个模型

杀手 2:AGENTS.md 频繁修改

AGENTS.md 相当于 Claude Code 的 CLAUDE.md,注入系统提示。修改后前缀变化,缓存失效。

  • 做法:会话前写好 AGENTS.md,开始后不动

杀手 3:前缀不足 1024 token

OpenAI 要求最少 1024 token 的前缀才能触发缓存。如果系统提示 + 工具定义太短,缓存永远不会命中。

  • 做法:确保 AGENTS.md 有足够的项目上下文(这是 Codex 里 AGENTS.md 尤其值得写详细的原因)

优化策略速查

架构层(节省 40-60%)

1. 修复 auto-compact 配置

常见问题:model_auto_compact_token_limit = 9999999 等于禁用了自动压缩。

# ~/.codex/config.toml
# 建议值:模型上下文窗口的 60-70%
model_auto_compact_token_limit = 120000  # GPT-5.4 上下文 200K,设 120K 触发压缩

这比 Claude Code 的 /compact 更重要,因为 Codex 没有手动 compact 命令。

2. 一个会话一个任务

话题切换后,旧对话历史 = 每轮付费的噪音。新任务开新会话。

3. 固定模型不中途切换
# ~/.codex/config.toml
model = "gpt-5.4"

不要用 --model 参数临时切换。

4. 开会话前写好 AGENTS.md

会话中改 AGENTS.md = 前缀变化 = 缓存失效。

5. 合理使用 multi_agent
[features]
multi_agent = true

Codex 的 multi-agent 模式可以将子任务分发到独立上下文,避免主会话历史膨胀。

Read the full file on GitHub · 184 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 184 lines · 0 tokens per session scan B 0069083c4b63

Subscribe to this mod's changes

token-saver is a skill published in the GitHub repository OpenWorkai/codex-token-saver (1 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,906 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.