You can see your cloud bill. Can you see what your AI agent's context costs?

A developer released tokenscope, an open-source CLI tool that estimates the token footprint of an AI agent's context across prompts, tools, and configs, helping developers identify cost-heavy files before they inflate cloud bills. The tool, available via npx, can be integrated into pre-commit hooks or CI pipelines to gate prompt changes, addressing the hidden cost of resending accumulated context on every model call.

You can see your cloud bill. You can see your CI minutes tick down. But the fastest-growing line item in an AI-agent app is the one number you can't see: how many tokens your agent's context is worth on every single model call . It's invisible because it never shows up as one big charge. It's a few thousand tokens, resent hundreds of times a day, quietly compounding. By the time it's a real number on the invoice, it's baked into every request you make. Here's how to read it in ten seconds — no account, no logs, no config: npx @wartzar-bee/tokenscope scan . Point it at the directory that holds your agent's prompts, tools, and configs. It prints the token footprint and the files responsible: tokenscope scan — src Estimated token footprint: 8,454 tokens across 6 files estimate ≈ 4 chars/token — a tokenizer-free proxy for relative comparison, not a billing figure Top files by estimated tokens: 2991 share.mjs 2134 scan.mjs 1092 core.mjs 835 report.mjs 718 pricing.mjs 684 benchmark.mjs That's the whole point: the top file is usually a system prompt, a tool schema, or a wall of few-shot examples that someone added "just to be safe." Now you can see which one, and how much it weighs, before it's part of every call. Most agent frameworks resend the accumulated context on each step — memory, history, tool definitions, the lot. So a prompt that's 2,000 tokens heavier isn't a one-time cost; it's 2,000 tokens × every call × every user. The per-call log looks fine. The monthly bill does not. I watched an agent on a timer burn 136M tokens overnight doing almost nothing https://dev.to/wartzarbee/i-put-an-ai-agent-on-a-timer-overnight-it-burned-136m-tokens-doing-almost-nothing-2ae2 — same root cause. tokenscope gives you a single, reproducible footprint number so a "let's just add this to the prompt" PR stops being invisible. 1. Ad-hoc, right now — measure any repo before you ship a prompt change: npx @wartzar-bee/tokenscope scan ./agent 2. As a local cost gate — fail your own commit if the footprint blows a budget, so a runaway prompt never leaves your machine: .git/hooks/pre-push chmod +x npx @wartzar-bee/tokenscope scan . --max-total 50000 || { echo "Context footprint over budget — trim it before pushing."; exit 1; } Using the pre-commit https://pre-commit.com framework? It's a four-line entry — no hook scripting. 3. On every PR, in CI — the same check as a GitHub Action that comments the token-cost delta on the responsible files and optionally blocks the merge: - uses: wartzar-bee/ci-guardrail@v1 with: github-token: ${{ secrets.GITHUB TOKEN }} mode: warn report-only until you trust it; switch to block later That's ci-guardrail https://github.com/wartzar-bee/ci-guardrail — tokenscope wired into your pipeline. npx @wartzar-bee/tokenscope scan . It's free, open-source, and tokenizer-free — an estimate for relative comparison, not a billing oracle, so you can run it on any codebase without wiring up a provider SDK. If it saves you one "why is the bill up 40%?" afternoon, it did its job.