Usage Cap Check: see the month coming before the agent bill does

What you end up with

No surprise at month end: the client owner sees the projection early and decides, in one line, what happens near the cap.

What you get

• The method: one cap and one over-cap rule agreed before the month, a weekly count, a decision before the cap, not after
• usagecap.py: 5 plan checks, 4 findings (heading over the cap, job over its daily budget, unplanned job, no off switch) and 4 reply checks
• A one-page usage sheet with spend, pace, month-end projection, spend by job and a one-line reply
• Owner decisions refused inside an agent session, from anyone but the client owner, or after the plan or the log changes
• AGENTS.md, CLAUDE.md, a Grok Bot standing order and a Hermes skill, a fictional example, and 28 tests

Who it is for

Providers who bill usage and want no month-end surprises, and owners who want to see the bill coming.

Works with

Solid chips: the agent is named in this listing's own tools list. Dashed chip: One Python script, a plan and log template, a fictional plumbing company example, and agent rules for each harness. Tested on Linux.

Tools needed

Cost to run: Free. Python is free.
Time to result: First status line in about 15 minutes

How it works

1. Run the example

   Unpack the file and run python3 usagecap.py status example/plan.json --today 2026-11-14.

   Expected: $171.90 spent of $300, month end near $409, 4 findings.

2. Write your plan

   Fill in templates/plan.json with the cap, alert points, over-cap rule and every job that spends, then copy rows into the usage log.

   Expected: usagecap.py check shows plan OK.

3. Sheet and send

   Run sheet and send usage-sheet.md to the client owner.

   Expected: usage-sheet.md with one numbered item per finding.

4. Reply once, then act

   The client owner answers in one line at their own terminal, then run plan and hand usage-actions.md to the provider.

   Expected: usage-actions.md with only the approved steps, each with a done test.

Sample prompts, free to use

Follow AGENTS.md. Copy last week's rows from the provider's usage export into the log, run usagecap.py status, and if it needs a decision, run sheet and send the client owner usage-sheet.md with the reply line. Do not pause a job, change a limit, raise the cap or edit the plan.

Free preview of the file

# Usage Cap Check

**Know where the month will land before the bill does. One plan with a cap and a rule for going over, a log copied from the provider's usage export, and a one-page sheet the client owner can read and answer in one line.**

Version 1.0, 2026-11-03. By PaperChaseWebb Inc. Free. Works with Grok Bot, Claude Code, Codex and Hermes, or by hand. Python 3.8 or newer, no installs.

## The problem

Agent work is billed by use, and use drifts. A follow-up job starts running twice a day. Someone adds a research task that was never in the plan. Nobody notices until the invoice, and then the conversation is about blame instead of choices.

The fix is boring and it works: agree a cap and a rule before the month starts, count against it every week, and ask the client owner before the cap, not after.

## What you get out of it

- One plan: the monthly cap, alert points, what happens at the cap, and every job that spends with its priority, daily budget and off switch.
- A status line any time: spent so far, the last 7 days' pace, and where the month ends at that pace.
- A one-page usage sheet in plain words, with a numbered decision per problem and a reply line like `1: pause 2: limit 3: add`.
- An action list of only what the client owner approved, each with a done test.

## Who it is for

Providers and small agencies who bill agent or model usage to clients and want no surprises at month end. Owners who pay for that usage and want to see it coming.

Not a billing system. I

Worth knowing

• It knows only what the log says. Copy rows from the provider's own export; a missing row is missing spend.
• The month-end figure is the last 7 days' pace carried forward, not a quote.
• On 2026-11-03: 28 tests passed on Python 3.8, 3.9, 3.11, 3.12 and 3.13 on Linux, run from the files unpacked out of the pack. Agent rules guide; they were not loaded inside each harness for this release.
• Not accounting or legal advice, and not a substitute for the usage terms in a contract.

Details

Version 1.0 · Updated Nov 3, 2026 · Markdown version of this page
License: Personal and commercial use. Download terms

Related

Prompt pack$29

Retainer Scope Sheet: itemize what an agent monthly covers

by PaperChaseWebb

One sheet per client that says line by line what your monthly agent retainer covers: the desks it runs and how many runs each, included hours and what happens over the limit, response times with covered hours, what is not included, what needs the client's yes, the reports they get and how changes are asked for. A checker fails every vague line ("ongoing support", "as needed", "ASAP"), an overage with no rate, a desk that sends or books with no yes row, and checks your proposals, change requests and invoices against the sheet. You approve each sheet at your own terminal.

Works withClaude CodeCodexGrok BotHermesPlain Markdown files, a small Python checker, and rules for AGENTS.md and CLAUDE.md, Claude Code and Codex notes, Hermes notes and a Grok Bot standing order. The agent files were checked by the checker on Linux; they were not loaded inside each agent for this release

Solo business · Intermediate · 30 min setup

Prompt pack$24

Agent Cost Levers: cut cost per solved task without cutting quality

by PaperChaseWebb

A Markdown pack plus a small checker that measures what your coding agent spends per finished task, then works five levers one at a time: thinking depth, context curation, direct tool routing, cache and reuse, and a verified stop. Includes a run sheet that splits cached input the way each provider bills it, cost_check.py to compare runs and check savings claims, AGENTS.md with six owner stops, and 12 prompts.

Works withClaude CodeCodexGrok BotHermes+1Plain .md; the optional checker needs Python 3.8 or newer

Vibe coding · Intermediate · 45 min setup

Prompt packFree

Pilot Scorecard: agree the pass line before an agent pilot starts

by PaperChaseWebb

A free kit for providers who offer a trial before a monthly plan, and for owners who want to try one. Write one page of terms: one workflow, 30 days at most, up to 5 measures with today's number, a target and where each number comes from, plus data limits, an off switch, the refund rule and the next step after a pass or a fail. The client owner signs it at their own terminal, the pass lines lock, and the end report says pass or fail per measure without an argument.

Works withClaude CodeCodexGrok BotHermesOne Python script, terms and results templates, a fictional dental practice example, and agent rules for each harness. Tested on Linux

Solo business · Beginner · 15 min setup

Prompt packFree

Clean Handover: keep running if your agent provider stops tomorrow

by PaperChaseWebb

A free kit for anyone who pays for agent or automation work, and for the providers who do it. List every account, data store, automation, schedule and bill the work touches in one register. A checker finds each place the client would be stranded: an account in the provider's name, no client admin, an export never tested, a job with no runbook or off switch, a bill the provider pays. Then it turns every gap into one decision sheet the client owner answers in a single reply.

Works withClaude CodeCodexGrok BotHermesOne Python script, a register template, a fictional bakery example with a runbook, and agent rules for each harness. Tested on Linux

Solo business · Beginner · 15 min setup