AI 工具AI TOOLS· CHAT-AGENT
lokikill123/codex-token-skills
为Codex CLI上的DeepSeek V4 Pro省token并保持记忆的skill包Reduce DeepSeek V4 Pro token usage on Codex CLI by up to 80% with caching-optimized tools.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
省下六到八成的费用
让回答变得简短直接
记住你的偏好和习惯
跨对话恢复项目结构和决策
减少重复描述上下文的麻烦
Cut token consumption by 60-80% on DeepSeek V4 Pro
Keep context stable across conversations with persistent memory
Force minimal output from Codex to reduce token waste
Maintain high prefix cache hit rates by freezing helpers files
Restore previous project context automatically from MEMORY.md
上手GET STARTED
git clone https://github.com/lokikill123/codex-token-skills.git选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.
静态扫描未发现明显风险,但不代表安全。The static scan found no known risk patterns in the documentation, but that does not guarantee the code is safe.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
-1.7%-1.7%
119 → 117 stars · 49 个快照119 → 117 stars · 49 snapshots
状态STATUS
长期未更新Not updated
项目刚于2026年6月15日发布,适合早期采用者抢占优化红利。DeepSeek V4 Pro's prefix cache needs stable system prompts and context files.
{
"agents": [
{
"agent": "codex",
"evidence": "readme: …> 专为 **DeepSeek V4 Pro** 优化的 Codex skill,大幅降低 token 消耗并提升前缀缓存命中率。 [![…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 1,
"ai-tools": 4,
"dev-tools": 4,
"indie-web": 0,
"skill-agent": 2,
"productivity": 4
},
"primary": "ai-tools",
"secondary": "chat-agent"
},
"localRuntime": "install: git-clone",
"skillMdTotal": 2,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 1,
"agent": 0,
"media": 0,
"design": 2,
"browser": 0,
"devtool": 4,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "2 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 2 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "name contains 'skill'",
"weight": 0.4
}
],
"scannedSources": [
"readme",
"skills/memory/SKILL.md",
"skills/token-saver/SKILL.md"
],
"skillMdFetched": 2
}