Loading...
Loading...
Stretches OpenAI Codex (CLI, IDE extension, cloud) 5-hour and weekly usage limits or credits while keeping output quality. Use when the user hits or nears a Codex limit, sees fast usage in /status, has a long session, asks to audit or tune config.toml (model, reasoning effort, verbosity, compaction, tool output limits, MCP servers, profiles) or AGENTS.md, or asks how to use Codex more efficiently. Triggers include "usage limit", "rate limit", "5-hour limit", "weekly limit", "credits", "token saving", "reduce cost", "使用量", "トークン節約", "節約", "5時間制限", "週間制限", "上限", "クレジット".
npx skill4agent add otnc/skills_ai-agent-saving-tech token-saver-codexgit status -sgit diff --statgit log --oneline -n 20lstail -n 40grep -E "FAIL|Error|error:"path:linepath:linelowmediumhighxhighproject_doc_max_bytes| Situation | Suggest |
|---|---|
| Starting unrelated work | |
| Long session, same task | |
| Want to try an alternative without losing this thread | |
| Routine task on a high effort or large model | |
| Unsure how much is left | |
| Speed not needed | Leave fast mode off (it consumes more credits per request) |
node <this skill's directory>/scripts/audit.mjs --agent codex~/.codex/config.toml.codex/config.tomlAGENTS.md~/.codex/AGENTS.md