by sshah03
A spreadsheet you share with your AI agents: every cell can hold a value, a formula, a terminal command, or a Claude Code or Codex agent.
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
# Add to your Claude Code skills
git clone https://github.com/sshah03/recalcGuides for using ai agents skills like recalc.
See how recalc compares with popular alternatives.
[!WARNING] recalc is in early beta. It's very, very early in development, so expect bugs, rough edges, and changes between versions that break things. Keep copies of anything you can't afford to lose, and please tell us what breaks.
Spreadsheets are still a great way to organize and analyze data. While it would be possible to just let Claude Code or Codex take control of Excel or Google Sheets, this felt like an opportunity to reimagine the spreadsheet for the agentic AI age from the ground up (though most of it should still feel familiar). This is still very experimental and very much a work in progress.
In its current form, recalc gives you and your agents one shared grid. Every cell can hold a number, a formula, a terminal command, or an AI agent. Agents write their plans and results into cells while you watch. Commands in other cells check their work and turn red when something's wrong. When you want something changed, you edit a cell instead of interrupting the chat. The different Claude Code or Codex instances running in recalc understand how recalc works via an MCP server.
Check an agent's "done". Put a cell that runs your tests next to the cell where the agent says it's finished. The test cell re-runs by itself whenever the code changes. If the agent says done while a test is failing, you see it straight away. You can even stop a Claude Code session from finishing until its row goes green.
Ask a hundred documents the same questions. Put files down the side and questions across the top, then press Run. An agent answers every cell, and each answer links to the exact passage it came from. Click a cell to see the quote highlighted in the document. Mark the answers you've checked. Agents can't overwrite them after that. Export the result to Excel when you're done, or to share it.
Run a few agents at once without losing track. Give each agent its own row and watch them all on one screen. Anything that needs you (a question, an error, a finished answer) lands in one list called Needs You. Or let the Driver, an agent that works the board for you, set things up from a prompt.
Keep your work on your computer. There's no account, no server and no tracking. The only request recalc makes on its own is a once-a-day check for a new version, which you can turn off. A board is just a folder of files. The agents you connect send what they always send to their own providers. For private documents, you can run the agents on a local model.
(1:22) Every kind of cell, an agent column on Haiku, review and Needs You, the Driver, sheets and sharing.
https://github.com/user-attachments/assets/72b60b54-946b-4236-acd5-4850befe0b27
(1:40) Twelve public contracts and six questions: 72 cited answers, a wrong one caught from its own source, flagged, and fixed by re-running with the note.
https://github.com/user-attachments/assets/705e7993-eddb-477b-ae0f-c0442f809a3d
(4:16) Five fictional clients' books carried onto the IRS's draft 2026 Form 1120-S: agents classify each account, formulas build and check each return, and an action fills the PDF only once the checks pass. Run it yourself with recalc demo scorp.
https://github.com/user-attachments/assets/f3d12576-151d-4f5b-a0ab-e836d094aeb4
(0:53) Sixteen figures pulled from a public annual report, each with the line it came from, and formulas that check they agree, down to a $14.4 million difference the notes explain.
https://github.com/user-attachments/assets/571af978-53cb-4d08-84ad-3d151bb19a89
(2:37) Models predicting FDA decisions from dossiers frozen before each decision: add a new model as a contestant, score it against the others, then open one of its answers in Terminal and ask it why.
https://github.com/user-attachments/assets/6208594e-8072-4a30-9dd7-fd4f22c50499
Install recalc. In a terminal on a Mac (Apple silicon or Intel):
curl -fsSL https://raw.githubusercontent.com/sshah03/recalc/main/install.sh | sh
It puts recalc in your Applications folder and a recalc command on your PATH. It's a short script; read it first if you like. Run it again any time to reinstall. On Linux the same line installs the AppImage, but Linux support is experimental.
Download the .dmg for your Mac from Releases and drag recalc to Applications. The beta isn't signed by Apple yet, so macOS refuses to open a downloaded copy until you clear its quarantine flag once:
xattr -dr com.apple.quarantine /Applications/recalc.app
(Or try to open it, then click Open Anyway in System Settings → Privacy & Security.) recalc → Install Command Line Tool… adds the recalc command.
Make sure you have an agent. recalc runs the agents you already use. Install Claude Code, Codex or pi (experimental) and sign in once. Agent → Connect an Agent shows what recalc found.
Try an example. File → New Board… → Examples. "Legal due diligence" is a good first one: select the empty answer cells and choose Cell → Run Selection (⇧⌘↩) to watch agents fill them in.
Your agent can also work on the board from its own chat. To connect a Claude Code you run yourself, run this in your project's folder:
claude mcp add recalc -- recalc mcp
(Without the recalc command, Agent → Connect an Agent shows the same line with the app's full path.) After that, just work as usual: the agent knows the board is there and uses it.
The first character of a cell says what it is:
| You type | It's | What happens |
|---|---|---|
42 |
a value | It just sits there |
= {passed} > 0 |
a formula | Updates when the cells it reads change |
$ npm test |
a command | Runs in your terminal, and its output becomes the value. Re-runs when its inputs change. ($1,200 is just an amount) |
! git push |
an action | Only runs when you run it. Use it for anything that changes things |
@claude('summarize {A2}') |
an agent | Asks Claude (or @codex, @pi) and puts the answer in the cell. Only runs when you run it |
{A2} pulls in another cell's value. That's most of what you need to know.
! actions and agent cells only run when you say so, and an agent can't be the first to run an action it wrote. recalc isn't a sandbox, though. Commands run with your permissions, so run it where you'd run them anyway.~/Documents/recalc boards, and everything saves as you go. Click a board's name at the top of the window to rename or move it..recalc folder you can commit or ignore. To open boards from a terminal, type recalc in any project folder (the install script adds the command; after a hand install, choose recalc → Install Command Line Tool…).This is a beta, so your bug reports and ideas shape what comes next. Open an issue with what you did, what you expected, and what happened. If recalc crashes, it writes a log to `~/Library/
recalc is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by sshah03. A spreadsheet you share with your AI agents: every cell can hold a value, a formula, a terminal command, or a Claude Code or Codex agent. It has 55 GitHub stars.
recalc's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/sshah03/recalc" and add it to your Claude Code skills directory (see the Installation section above).
recalc is primarily written in Rust. It is open-source under sshah03 on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh recalc against similar tools.
No comments yet. Be the first to share your thoughts!