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 kellykampen/agent-skills --skill check-model-usagegit clone --depth 1 https://github.com/kellykampen/agent-skillsWrote 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/kellykampen/agent-skills/check-model-usage)<a href="https://agentmods.dev/skills/kellykampen/agent-skills/check-model-usage"><img src="https://agentmods.dev/badge/skills/kellykampen/agent-skills/check-model-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/kellykampen/agent-skills/check-model-usage"><img src="https://agentmods.dev/badge/skills/kellykampen/agent-skills/check-model-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00174 | $0.02593 |
| Opus 5 | $0.00087 | $0.01296 |
| Sonnet 5 | $0.00035 | $0.00519 |
| Haiku 4.5 | $0.00017 | $0.00259 |
Grade A, and why
check-model-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 8d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Model Usage
Runs scripts/check_model_usage.py (a single self-contained Python script, stdlib only), which prints one
consolidated report covering current usage plus session (5h) and weekly pacing across the configured harnesses/providers.
Just run it (takes ~20s; most of that is codexbar's Claude fetch):
python3 scripts/check_model_usage.py
Use --only= to check a subset (comma-separated): --only=claude,codex, --only=glm,kimi, etc. Accepted
names: claude, codex, agy (alias for antigravity), glm (alias for zai), kimi, openrouter, xai/grok (if CodexBar exposes those provider IDs) -- plus any other codexbar provider id (e.g. gemini) if explicitly requested.
How it works
The only data source is CodexBar
(brew install steipete/tap/codexbar), a community-maintained CLI that reaches each provider's usage data
itself (OAuth token files, provider web APIs, API tokens) and returns clean JSON. If CodexBar does not yet expose xAI/Grok, OpenRouter, or GPT-5.6 split-out windows, report those pools as not visible to this quota checker rather than probing provider APIs directly. This skill never opens cmux
panes, never drives any harness TUI, never calls provider APIs directly, and never writes codexbar config
(no config enable, no set-api-key -- all 5 providers are already configured in codexbar; a piped
set-api-key from an earlier version once corrupted a working stored key). If you're tempted to do any of
those to fill a gap, stop: fix it inside codexbar instead (see references/data-sources.md). The script:
- Installs
codexbarvia Homebrew if missing (the only mutation it ever performs, and only when absent). - Fetches
codexbar usage --provider <x> --jsonfor each requested harness in parallel -- read-only. - Renders the report: each returned window (
primary/secondary/tertiary, or Antigravity'sextraRateWindows) is classified into session / daily / weekly / monthly buckets by actual window length -- not by slot name, because codexbar's slot naming doesn't map consistently across providers (z.ai'sprimaryis weekly; seereferences/data-sources.md).
What ships with it
2 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.
- 8d ago First seen · 158 lines · 174 tokens per session scan A b72e136b86c9
check-model-usage is a skill published in the GitHub repository kellykampen/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 174 tokens to every session and 2,593 once invoked, about $0.0009 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…