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.
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.
npx agentmods add commands/anthropics/financial-services/consentgit clone --depth 1 https://github.com/anthropics/financial-servicesWrote 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.
[](https://agentmods.dev/commands/anthropics/financial-services/consent)<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>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.
| Model | Per session | Once 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 |
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.
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.
Azure admin consent
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.
Outlook — Microsoft Graph consent
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
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.
- 5d ago First seen · 60 lines · 18 tokens per session scan A d34c4dada78b
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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.