# Cost per solved task: the one-sheet agent cost check (free sample)

> The one number to track for agent spend, a usage sheet, three rules for testing a change and a prompt that compares two runs honestly.

- URL: https://paperchasewebb.ai/bots/marketplace/items/cost-per-solved-task-agent-cost-check-free-sample/
- Type: Prompt pack
- Category: Vibe coding
- By: PaperChaseWebb
- Works with: Claude Code, Codex, Cursor (named in the listing); Plain .md
- Price: Free USD
- Difficulty: Beginner
- Setup time: 15 min
- Time to result: Fifteen minutes
- Format: Markdown (.md) file, cost-per-solved-task-agent-cost-check-free-sample.md
- Version: 1.0, updated 2026-10-26
- License: Personal and commercial use.

## What you end up with

You see what a finished task costs before you try to cut anything.

## What you get

- The formula
- The usage sheet
- Three rules
- A check prompt

## Who it is for

Anyone who wants to know what their coding agent really costs per job.

## Tools needed

- Claude Code: reports session usage and reads CLAUDE.md
- Codex: reports session usage and reads AGENTS.md
- Cursor: reads the project rule
- You need: Any coding agent that reports usage

Cost to run: Free.

## Sample prompt: Compare two runs honestly (Claude Code, Codex, Cursor)

```
Here are the baseline and the new run for the same ten tasks [paste both]. Compute cost per solved task and the pass count for each, and the change.
If the pass count dropped, say so first. Do not call anything a saving if quality fell.
```

Run it after every lever you try.

## Free preview of cost-per-solved-task-agent-cost-check-free-sample.md

````markdown
# Cost per solved task: the one-sheet agent cost check (free sample)

A free sample from Agent Cost Levers by PaperChaseWebb. Works with Claude Code, Codex, Cursor or any agent tool that reports usage.

Most agent cost advice starts with the model price. Start with what you control: how many tasks actually get done for the money.

## The number

**cost per solved task = total spend on a batch / tasks that passed a check you wrote before the run**

- A task is solved only when a check says so: a test, a script, a lint pass, a two-minute reviewer checklist.
- Failed and abandoned runs stay in the total.
````

## Worth knowing

- Measure on real tasks. Toy prompts give misleading numbers.

## Questions

**What is in the full pack?** Five levers that move the number, a rules block for CLAUDE.md, AGENTS.md and Cursor, a claim discipline checklist and 10 prompts.

## How to get it

Free sample. Download it directly at https://paperchasewebb.ai/bots/marketplace/items/cost-per-solved-task-agent-cost-check-free-sample/, no signup.

Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com