/token-receipt

GitHub

Your Agent Has Expenses.Officially itemized for Codex and Claude Code.

Token Receipt turns local agent logs into your coding-agent bill with a thermal-paper PNG, share-ready post copy, and a skill-native flow that works inside the tools people already use.

Skill-first. Local-first. No extra model API in v1.

Install Token Receipt

>_
$ npx skills add ameyalambat128/token-receipt --skill token-receipt

Example output

TOKEN RECEIPT

Last 30 Days

ORDER #0001 FOR AMEYA

MONDAY, JUNE 8, 2026

QTYITEMAMT
01Context window emotional support$2,488
02MCP tool tourism$941
03Repeated shell confidence loops$422
04Docs tab multiplication$203
05One more quick refactor$96
06Agent handoff drama$58
Prompt count:184
Tool calls:612
Tokens burned:1.92M
Peak spiral:2:14 AM
TOTAL:$4,208

CARD: **** **** **** 2026

AUTH CODE: 612184

CARDHOLDER: AMEYA

THANK YOU FOR PROMPTING

Got HelpedLast 30d
MayJun

sample agentic usage stats

Codex support

Token Receipt ships a Codex skill that can be invoked from the thread with the exact workflow Codex already uses for skills. The skill calls the local runtime, reads the structured analysis, and then lets Codex write the final response in-session.

Codex prompt

$token-receipt Generate a receipt for my last 30 days of agent usage.

Claude Code support

Claude Code gets the same skill-first flow: local parsing and image generation happen in the runtime, and Claude writes the final response using your existing session instead of a separate API key.

Claude Code prompt

Use token-receipt to itemize my last 30 days of Codex and Claude Code usage.

What is Token Receipt?

Token Receipt is a screenshot-first usage artifact for coding agents.

It reads the session logs that Codex and Claude Code already write locally, turns those into structured usage facts, and lays them out as an itemized bill.

The result feels personal because it reflects your own habits: repeated file reads, subagent sprawl, context bloat, and every other expensive little ritual.

  • Reads local logs from Codex and Claude Code
  • Builds a thermal-paper PNG plus ready-to-edit post copy
  • Uses skills so the host agent can write the final roast

Why this exists

The accurate observability product is not the point.

The point is a screenshot people instantly understand: your coding agent bill, officially itemized, with a line item for every bad habit you already know you have.

Real local signals make the output feel specific instead of generic.


What it itemizes

V1 focuses on signals we can defend from the logs:

Context window emotional support
Repeated file reads
Repeated shell confidence loops
MCP tool tourism
Subagent middle management
Planning before touching a file
Cache-heavy sessions
Low-output expensive runs

Every bill is derived from local agent logs.


How it works

Token Receipt is local parsing plus agent-native copywriting, not a new hosted AI layer.

1.

The runtime scans local Codex and Claude Code session logs

2.

Deterministic heuristics turn those logs into receipt facts

3.

The skill asks Codex or Claude Code to phrase the final response using the session you are already paying for

No prompt uploads by default. No telemetry in v1.


Who this is for

  • People shipping with Codex or Claude Code every day

Open source

MIT licensed and open source.


FAQ