nueton-receipts — Claude Code & Codex plugin: what it does
nueton-receipts counts every time your agent said it was done and checks each claim against the commands in the same session: confirmed, contradicted or unverified.
MIT ★ 1,596 updated 2026-10-29
/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install nueton-receipts@awesome-codex-pluginsWhat nueton-receipts does
The skill reads session logs: Claude transcripts from ~/.claude/projects with subagent transcripts, and Claude sessions from ~/.codex/sessions with code-mode exec calls and forked sessions. For each turn it takes the agent's final message, picks out completion claims and looks back through that same turn for commands that back them. Output lands in ~/.nueton-receipts/export.json, counts go to the terminal.
Plain code does the judging, no model involved. Confirmed means a test, build, lint or typecheck ran after the last edit and passed; with --repo-check your local git has to show the commit or push instead. Contradicted covers “committed” with no such command in the session, “tests pass” with no test run, a failing check followed by a claim that it works. Unverified means the logs settle nothing. Silent stalls get their own count: turns that started work and ended with no final message.
Counts come from keyword matching, so read them before quoting them anywhere; a plan like “complete two tasks” matches too. The export holds session, project and branch ids hashed with SHA-256 and a salt you keep, timestamps, tool names, command families and claim sentences with paths, URLs, emails and long numbers masked. Anything key-shaped becomes <secret>, and --no-sentences drops claim text entirely. Prompts and code never enter the file. The stop-check hook is a separate install and the skill does not turn it on.
What it helps with
- Catch “tests pass” when no test ran in the session
- Measure how many of your agent's done claims were wrong
- Find silent stalls where the agent went quiet after tool errors
- Check a claimed commit against local git history
- Screenshot a card of your own counts
Example prompts for the agent
- Run
/nueton-receipts:receiptsand tell me how often my agent's done was actually true. - Show my receipts card for the last 30 days.
- Audit the completion claims from 2026-10-01 against my local git history.
How to install nueton-receipts
Plugin marketplace
/plugin marketplace add hashgraph-online/awesome-codex-plugins/plugin install nueton-receipts@awesome-codex-pluginsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about nueton-receipts
How do I install nueton-receipts in Claude Code?
Add the marketplace first: /plugin marketplace add hashgraph-online/awesome-codex-plugins, then install the plugin: /plugin install nueton-receipts@awesome-codex-plugins. It needs Claude 2.1.275 or later.
What does nueton-receipts do?
It reads your local Claude and Claude session logs, collects the completion claims the agent made and checks each one against commands from the same turn. You get confirmed, contradicted and unverified counts.
Does it send my logs anywhere?
No. The script runs offline on your machine and writes only ~/.nueton-receipts/export.json. Ids are hashed with a salt you hold, and key-shaped strings are replaced with <secret>.
Source text
receipts-collector · MIT
# receipts-collector
Every time your coding agent said "done", and whether its own logs back it up.
One Python file, standard library only, runs on your machine. It reads Claude Code transcripts (`~/.claude/projects`, including subagent transcripts) and Codex sessions (`~/.codex/sessions`, including code-mode `exec` tool calls and forked sessions), finds every completion claim in the agent's final message for each turn, and looks back through the same turn for evidence.
```
curl -fsSL https://receipts.nueton.ai/receipts_collect.py -o receipts_collect.py
python3 receipts_collect.py --summary
```
It writes `~/.nueton-receipts/export.json` and prints counts only. These are candidate claims found by keyword; a person (or the paid receipt's claim filter) still has to read them, because goals and plans like "Complete two tasks" also match:
```
sessions=326 claims=1355 confirmed=106 contradicted=122 unverified=1127 stalls=16
```
## Use it inside your agent
Claude Code plugin (Claude Code 2.1.275 or later):
/plugin install nueton-receipts --marketplace Kloudedge-apex/receipts-collector
Then run `/nueton-receipts:receipts`, or ask "how often was my agent's done actually true?"
Any agent with skills (Claude Code, Codex, Cursor and others):
npx skills add Kloudedge-apex/receipts-collector --skill receipts
Codex: `$skill-installer install https://github.com/Kloudedge-apex/receipts-collector/tree/main/skills/receipts`
Example prompts: "Show my receipts card for the last 30 days" · "How often was my agent's done actually true this month?" · "Audit my agent's completion claims since 2026-10-01 using local git history"
## Free stop check
The **Receipts stop check**, part of Receipts by Nueton, runs when Claude Code or Codex tries to finish a turn in which it edited files with its edit tools: if no test, build, lint or typecheck ran after the last edit, or (in Claude Code) the last one failed, it asks the agent once to run one or give a `BLOCKED:` reason. It runs locally and stores only event types, check families and results, and hashed session and turn IDs. Install it separately: [setup, privacy and limits](plugins/stop-check/README.md). Installing the receipts skill does not enable this hook.
## Share your card
```
python3 receipts_collect.py --card
```
prints a 40-column receipt of your own counts, made to be screenshotted:
```
RECEIPT receipts.nueton.ai
period 2026-09-17 .. 2026-10-19
agents claude code, codex
sessions 328
"done" candidates 1,370
----------------------------------------
confirmed 121
contradicted 122
unverified 1,127
silent stalls 15
----------------------------------------
Counts are keyword matches. Read them
before you quote them.
Check yours, free: receipts.nueton.ai
```
It contains counts and dates only: no sentences, paths, ids or tool names from your logs. `--card-out card.txt` saves it to a file.
## The rules (plain code, no model)
| Status | When |
| --- | --- |
| Confirmed | A test, build, lint or typecheck ran after the last edit and passed; or, with `--repo-check`, your local git shows the claimed commit or push |
| Contradicted | "Committed" or "pushed" with no such command in the session; "tests pass" with no test run; a check passed, then more edits, then "done"; a failing check followed by "passing" |
| Unverified | Nothing in the logs settles it |
A **silent stall** is a turn where the agent started working and then ended without a final message, or hit tool errors and went quiet. Negated or conditional sentences ("still untracked", "should I push") are not counted as claims.
## What the file contains, and what it never contains
**Contains:** session, project and branch ids hashed with SHA-256 and a salt only you hold (`~/.nueton-receipts/salt`); timestamps; tool names; command families such as "test" or "git"; token counts; and claim sentences with paths, URLs, emails, hosts, hashes and long numbers masked. Anything key-shaped is replaced with `<secret>` before the file is written. `--no-sentences` removes claim text entirely.
**Never contains:** prompts, code, file contents, command strings, tool outputs or environment values.
`verify/receipts_verify.py` checks an export without any model: shape, recomputed totals, hashing, and a scan for anything path-, URL-, email- or key-shaped. It refuses a file that leaks.
## Flags
`--since YYYY-MM-DD`, `--until`, `--claude-dir`, `--codex-dir`, `--salt`, `--out`, `--no-sentences`, `--summary`, `--repo-check` (off by default; reads your local git read-only and records only found or absent for commit and push claims).
## Tests
```
python3 -m unittest discover -s tests
```
All fixtures are synthetic.
## A receipt, read by a person
If you'd rather someone read the file and send back a one-page receipt with the evidence and the three hooks that would have caught the misses: [receipts.nueton.ai](https://receipts.nueton.ai). Made by Nueton. Not affiliated with Anthropic, OpenAI or Anysphere.
MIT licensed.
© Nikxius, Inc. · MIT · hashgraph-online/awesome-codex-plugins