consent

consent is a command for coding agents from anthropics/financial-services. It costs 18 tokens per session (679 once invoked), scanned A, original, Apache-2.0.

A guide to granting one-time Microsoft Entra administrator approval for add-in sign-in and Outlook Graph access. A Global Administrator opens a provided Microsoft login link and accepts the requested permissions.

In plain words
What is it for?
Use it to share the consent link with a tenant Global Administrator and verify that the required service principal has been created.
Why use it?
Without this tenant-wide approval, sign-in inside the add-in fails for users when the manifest uses Entra single sign-on.

Command

Part of the claude-for-msft-365-install plugin — 1 skill, 9 commands shipped together

About the project

Claude for Financial Services is a collection of agents, skills, commands, plugins, and data connectors for investment banking, equity research, private equity, and wealth-management workflows. Financial professionals use it to draft models, memos, research notes, and reconciliations for review by qualified people. The catalogue contains components from these workflows, including agents, skills, plugins, commands, and instructions.

anthropics/financial-services · 34,627 stars · on GitHub

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/consent
Clone the repo
git clone --depth 1 https://github.com/anthropics/financial-services

Or install claude-for-msft-365-install, the plugin that ships this one along with the rest of its 1 skill, 9 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for consent

README.md
[![agentmods](https://agentmods.dev/badge/commands/anthropics/financial-services/consent.svg)](https://agentmods.dev/commands/anthropics/financial-services/consent)
Your own site
<a href="https://agentmods.dev/commands/anthropics/financial-services/consent"><img src="https://agentmods.dev/badge/commands/anthropics/financial-services/consent.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 679 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 $0.00018 $0.00679
Opus 5 $0.00009 $0.00340
Sonnet 5 $0.00004 $0.00136
Haiku 4.5 $0.00002 $0.00068

Measured 5d ago against content hash d34c4dada78b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consent 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 5d 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/consent.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Only needed when entra_sso=1 in the manifest. Gateway and Vertex setups with org-wide config don't use Entra and can skip this. If you set graph_client_id (your own Entra app), this page doesn't apply either — you manage consent on your app directly.

One-time per tenant. A Global Admin opens this URL, clicks Accept, done. Until they do, NAA sign-in inside the add-in fails for every user in the tenant.

The URL

Same URL for every customer — /organizations/ resolves the tenant from whoever signs in. No substitution needed.

https://login.microsoftonline.com/organizations/adminconsent?client_id=c2995f31-11e7-4882-b7a7-ef9def0a0266&redirect_uri=https://pivot.claude.ai/auth/callback

Print it. Tell them: open in a browser where a Global Admin for their tenant is signed in. They'll see a permissions screen listing what the add-in reads (user profile, extension attributes). After they click Accept, they land on a confirmation page — "Admin consent granted, you can close this tab."

Verify

az ad sp show --id c2995f31-11e7-4882-b7a7-ef9def0a0266 --query appId -o tsv

If that returns the same GUID, the service principal exists in their tenant — consent worked. If it errors with "does not exist", consent didn't complete.

Only needed when deploying the Outlook manifest. Separate from entra_sso above; required even if entra_sso is off.

Claude for Outlook reads mail and calendar through Microsoft Graph. The Graph token stays in the user's Outlook client and is never sent to the gateway or to Anthropic, so this consent is the same regardless of which cloud serves the model. A Global Admin opens the URL, clicks Accept, done.

https://login.microsoftonline.com/organizations/v2.0/adminconsent?client_id=c2995f31-11e7-4882-b7a7-ef9def0a0266&scope=https://graph.microsoft.com/Mail.ReadWrite%20https://graph.microsoft.com/Calendars.Read%20https://graph.microsoft.com/People.Read%20https://graph.microsoft.com/User.Read%20offline_access&redirect_uri=https://pivot.claude.ai/auth/callback

Read the full file on GitHub · 60 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. 5d ago First seen · 60 lines · 18 tokens per session scan A d34c4dada78b

Subscribe to this mod's changes

consent is a command published in the GitHub repository anthropics/financial-services (34,627 stars, last pushed 9d ago), licensed Apache-2.0. It adds 18 tokens to every session and 679 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.