export-data

A command guide that copies a user's locally stored add-in data before their machine is rebuilt. This can include chat history, uploaded skills, MCP registrations, memory, and settings held in the browser's storage.

In plain words
What is it for?
Use it to list or export add-in data on macOS or Windows to a folder you choose before reinstalling Office or rebuilding the computer.
Why use it?
The add-in's manifest only points Office to a web page; it does not contain the user's data, and there is no server-side copy described here.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/anthropics/financial-services/export-data
Clone the repo
git clone --depth 1 https://github.com/anthropics/financial-services
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,222 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.02222
Opus 5 $0.00012 $0.01111
Sonnet 5 $0.00005 $0.00444
Haiku 4.5 $0.00002 $0.00222

Measured 2d ago against content hash c71e742c7aa5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

export-data scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

claude-for-msft-365-install/commands/export-data.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Export add-in data

Chat history, uploaded skills, MCP registrations, memory, and settings live in browser storage on the user's own machine. There is no server-side copy. These scripts make a copy of it.

Platform Script
macOS scripts/export-addin-data.sh
Windows scripts/export-addin-data.ps1

Read only. They read Office's storage and write only to the folder you name. They never modify, move, or delete anything in Office. Run with no arguments and they just print what they found.

./scripts/export-addin-data.sh                      # macOS: list
./scripts/export-addin-data.sh --out ~/claude-export
.\scripts\export-addin-data.ps1                     # Windows: list
.\scripts\export-addin-data.ps1 -Out C:\claude-export

Why reinstalling the add-in doesn't lose anything

The manifest is a pointer, not a container. It holds an <Id>, a <Version>, and a <SourceLocation> URL — and no data. Office reads it, then opens that URL in an embedded browser (WKWebView on macOS, WebView2 on Windows). From there the ordinary web rules apply: that browser gives IndexedDB to the page's originscheme://host:port — exactly as Chrome or Safari would.

So the ID and the storage live on two different keys:

  manifest.xml                       the WebView                storage bucket
  ┌──────────────────────┐           ┌───────────────┐          ┌─────────────┐
  │ <Id>  3499c065-…     │──ignored─╳│               │          │             │
  │ <Version> 1.0.0.11   │──ignored─╳│  loads  URL   │──origin─▶│ IndexedDB   │
  │ <SourceLocation>     │──────────▶│               │          │  for that   │
  │   https://host/…     │           └───────────────┘          │   origin    │
  └──────────────────────┘                                      └─────────────┘
         ▲                                                             ▲
         │ replaced / deleted / re-ID'd / version-bumped               │
         └──── none of this reaches ───────────────────────────────────┘

Read the full file on GitHub · 200 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 200 lines · 23 tokens per session scan A c71e742c7aa5

Subscribe to this mod's changes

export-data is a command published in the GitHub repository anthropics/financial-services (34,627 stars, last pushed 7d ago), licensed Apache-2.0. It adds 23 tokens to every session and 2,222 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.