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.
npx skills add huajiexiewenfeng/codex-token-usage-skill --skill codex-token-usagegit clone --depth 1 https://github.com/huajiexiewenfeng/codex-token-usage-skillWrote 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.
[](https://agentmods.dev/skills/huajiexiewenfeng/codex-token-usage-skill/codex-token-usage)<a href="https://agentmods.dev/skills/huajiexiewenfeng/codex-token-usage-skill/codex-token-usage"><img src="https://agentmods.dev/badge/skills/huajiexiewenfeng/codex-token-usage-skill/codex-token-usage/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huajiexiewenfeng/codex-token-usage-skill/codex-token-usage"><img src="https://agentmods.dev/badge/skills/huajiexiewenfeng/codex-token-usage-skill/codex-token-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.01810 |
| Opus 5.5 | $0.00021 | $0.00724 |
| Sonnet 5.5 | $0.00011 | $0.00362 |
| Haiku 4.5 | $0.00005 | $0.00181 |
Grade A, and why
codex-token-usage scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Token Usage
Overview
Use the bundled script to read local Codex session logs and produce a consistent token usage report. Prefer deterministic script output over ad hoc rg summaries.
Default: generate the fixed HTML dashboard and open it in the system's default external browser. This also applies to plain requests such as “统计本周用量” or “统计下 token”. Do not answer with only a Markdown table unless the user explicitly requests text, Markdown, JSON, or no browser. Re-read this installed file when reusing an old task; earlier task instructions may describe the old Markdown default.
Workflow
- Identify the reporting window from the user request.
- If the user asks for "one month" or "last month" without naming a calendar month, use the last 30 local calendar days ending today.
- If the user asks for "this month" or names a specific month, use that calendar month, clipped to today if it is the current month.
- Use the user's timezone from context when available; default to the local machine timezone only if no timezone is provided.
- “This week” means Monday through today in that timezone; pass explicit
--startand--enddates.
- Run the installed
scripts/codex_token_usage.pyfrom the user's workspace with the reporting dates and timezone. Resolve the script from the skill directory containing this file. Use the activeCODEX_HOMEfor logs when present; do not infer log location from a legacy skill installation path. - Unless explicitly overridden, use HTML (the CLI default). The script writes
output/token-usage-<start>-<end>.htmlunder the working directory and requests the system's default external browser to open it.--outputoverrides the file path. Keep reports outside the skill source directory. - Do not substitute an in-app browser preview. If opening fails or is blocked, provide the saved file link and accurately state that it was not opened; do not bypass host restrictions. A successful OS launch request alone is not evidence that the page rendered.
- Return a clickable absolute HTML file link, exact date range and a short summary. The dashboard contains daily counts, peak periods and metric definitions; do not replace it with a long Markdown table.
- For explicit text/Markdown requests, pass
--format markdown; for machine-readable requests, pass--format json. These formats print to stdout unless--outputis provided and do not open a browser. For automation or a user request not to open a browser, use--no-openwith HTML.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +20 lines · -38 tokens per session d50bfaa11305
- 1mo ago First seen · 87 lines · 91 tokens per session scan A 026dc422796a
codex-token-usage is a skill published in the GitHub repository huajiexiewenfeng/codex-token-usage-skill (31 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,810 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…