‘Technology pulls itself up by the bootstraps by giving scientific researchers vastly more powerful tools to work with’
For millennia, humans have sought tools to make ourselves more productive. That is no different today, as Joel Mokyr, the 2025 Nobel Prize winner, suggested in a 2018 paper. Artificial intelligence – Claude Code, Codex, and there’ll probably be many other alternatives soon – has accelerated this to a new level. In the process of using Claude Code, I’ve developed several tools that might be useful for others. They can be downloaded for free from my GitHub page.
EconGuru
A simulated peer review system for economics working papers. EconGuru creates a panel of independent referee agents – each with a distinct subspecialisation, personality, and fictitious university affiliation – who review your paper in isolation, with strict information barriers mirroring real peer review. Referees cannot see each other’s reports or the editorial deliberations. An editor synthesises their feedback into a prioritised briefing, weighting senior referees’ judgement more heavily. You choose which changes to implement, and the tool revises your LaTeX files accordingly. Referees persist in a local library that grows over time: you rate their reports after each round, building a roster of hundreds of specialists with track records and seniority scores. Use /econguru analytics for a dashboard of your library. Grounded in the refereeing principles of Berk, Harvey, and Hirshleifer (2017).
TannieDi
A LaTeX-to-Word round-trip tool for language editing. Many economics papers are written in LaTeX, but professional copy-editors typically work in Word. TannieDi automates the conversion: pack converts your LaTeX project into a clean Word manuscript (with figures and tables in a separate file), and unpack applies the editor’s tracked changes back into your original .tex files – preserving all LaTeX formatting, equations, and cross-references. Named after Di Kilpert, a language editor who has copy-edited many LEAP papers.
Kabbo
A workflow tracker and productivity advisor for Claude Code, named after //Kabbo (/Han≠kass’o, 1815–1876), the /Xam visionary whose narrative wisdom was preserved in the Bleek and Lloyd archive. Kabbo logs your session activity – tasks, tools, projects, token intensity – and analyses patterns over time using economic frameworks: comparative advantage for task allocation, marginal cost curves for token spending, Markowitz diversification for project portfolios. It recommends skills to build, agents to deploy, and workflows to automate. Run /kabbo quick for four headline numbers, /kabbo analytics for a full dashboard, or /kabbo deep for a monthly executive briefing. Every session closes with a line from a /Xam narrative.
Download
The tools are available at github.com/johanfourieza/econtools. To install a tool in Claude Code, download the relevant skill.md file and place it in your .claude/skills/{toolname}/ directory (e.g., .claude/skills/econguru/skill.md). Each tool’s folder contains instructions for use.