DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use Bough: what you can do with it

What is Bough? bough reads your Claude Code, Codex CLI and Pi session transcripts locally and shows what you built, broken into days, tasks and prompts, with what each piece would have cost at published API rates.

How do I use it? Install Bough with brew install nickelsec/tap/bough on macOS, or use the install script for your platform from the README; then run bough to open your projects in the browser; open a project and hover a task to see its token and dollar breakdown. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

4 use cases

  • Price each feature built with an AI coding agent

    See the rough API-rate cost of each task inside a project, not just each session.

    View prompt
    Using the bough repo at github.com/nickelsec/bough, run `bough <project-name> --text` for the project at <project-name> and list the three most expensive tasks with their dollar figures. Verify that each figure is labelled as API-rate cost, not a bill.
  • Get a plain text cost summary for a project

    Print a project's sittings, tasks and costs to the terminal or a file.

    View prompt
    In the bough repo at github.com/nickelsec/bough, run `bough --list` and then `bough <project-name> --text -o summary.txt` for the project named <project-name>. Confirm that summary.txt exists and contains a total dollar figure labelled as API-rate cost.
  • Export agent work history as JSON for other tools

    Write the full task and cost structure of a project to JSON for your own analysis.

    View prompt
    Using the bough repo at github.com/nickelsec/bough, run `bough <project-name> --json -o work.json` for the project <project-name>. Check that work.json parses as valid JSON and that it contains task entries with cost fields.
  • Compare agent costs between Claude Code and Codex

    Filter a project's history to one agent at a time to compare what each cost.

    View prompt
    In the bough repo at github.com/nickelsec/bough, run `bough --agent=claude --text` and `bough --agent=codex --text`. Report the total API-rate cost from each output and state which agent's figures the README says deserve more suspicion.

Quick start with Bough

  1. Check you have what it needs: A Claude Code, OpenAI Codex CLI or Pi installation with existing session history on this machine; Homebrew on macOS, or the install script on Linux or Windows, or Go installed; A terminal to run bough in.
  2. Open nickelsec/bough on GitHub and read the README and license.
  3. Install Bough with brew install nickelsec/tap/bough on macOS, or use the install script for your platform from the README.
  4. Run bough to open your projects in the browser.
  5. Open a project and hover a task to see its token and dollar breakdown.
  6. Click a task to open the full prompt record beside the drawing.

These steps come from our top use case, Price each feature built with an AI coding agent, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for nickelsec/bough

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Bough alternatives · Best AI repos for Money

About this repo

  • Who it is forDevelopers who use Claude Code, Codex CLI or Pi and want to know what each feature or session cost them, without sending any data off their machine.
  • Why it is hot128 stars, launched 54 days ago
  • LanguageGo
  • Sourcegithub.com/nickelsec/bough · Back to Hot repos

Requirements

  • A Claude Code, OpenAI Codex CLI or Pi installation with existing session history on this machine
  • Homebrew on macOS, or the install script on Linux or Windows, or Go installed
  • A terminal to run bough in

Add this badge to your README

Maintain Bough? Show readers where to find these use cases. Use cases on Deduped

Markdown

[![Use cases on Deduped](https://dedupedai.com/badge/nickelsec/bough.svg)](https://dedupedai.com/use-cases/nickelsec-bough/?utm_source=github&utm_medium=badge&utm_campaign=nickelsec-bough)

HTML

<a href="https://dedupedai.com/use-cases/nickelsec-bough/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=nickelsec-bough"><img src="https://dedupedai.com/badge/nickelsec/bough.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Bough

What is Bough?

bough reads your Claude Code, Codex CLI and Pi session transcripts locally and shows what you built, broken into days, tasks and prompts, with what each piece would have cost at published API rates. It is an open-source project on GitHub: https://github.com/nickelsec/bough.

How do I use Bough?

Install Bough with brew install nickelsec/tap/bough on macOS, or use the install script for your platform from the README; then run bough to open your projects in the browser; open a project and hover a task to see its token and dollar breakdown. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Bough for?

Developers who use Claude Code, Codex CLI or Pi and want to know what each feature or session cost them, without sending any data off their machine.

What can I do with Bough?

4 use cases so far, for example: Price each feature built with an AI coding agent; Get a plain text cost summary for a project; Export agent work history as JSON for other tools. Each has steps and a copy-paste agent prompt.

What do I need to run Bough?

A Claude Code, OpenAI Codex CLI or Pi installation with existing session history on this machine; Homebrew on macOS, or the install script on Linux or Windows, or Go installed; A terminal to run bough in.

What are alternatives to Bough?

Other hot AI repos in Money: Fincept Terminal, Freqtrade, Vibe Trading, Day Trader Skill, Tick Stock Panel.

Is Bough safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.