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.
git 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/update-user-attrs)<a href="https://agentmods.dev/commands/anthropics/financial-services/update-user-attrs"><img src="https://agentmods.dev/badge/commands/anthropics/financial-services/update-user-attrs.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 5.1 | $0.00015 | $0.01383 |
| Opus 5 | $0.00008 | $0.00691 |
| Sonnet 5 | $0.00003 | $0.00277 |
| Haiku 4.5 | $0.00002 | $0.00138 |
Grade A, and why
update-user-attrs 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 8d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Per-user config via extension attributes
The attributes are already registered on Anthropic's app (c2995f31-…) — you
don't create schema, you just write values. The add-in reads
extension_c2995f3111e74882b7a7ef9def0a0266_<key> from the user's ID token.
Requires entra_sso=1 in the manifest. Without it the add-in never
acquires an Entra token, so these attributes are never read — they silently do
nothing.
Any of the config keys can be set per-user — the add-in merges per-user attrs over manifest params, so whatever's here wins. All values are 256 chars max.
| Key | Per-user use case |
|---|---|
gateway_token |
Per-user API key (rotation) |
gateway_url |
Route different teams to different gateways |
gateway_api_format |
Gateway speaks Bedrock/Vertex pass-through, not Anthropic /v1/messages |
inference_headers |
Per-user accounting tag for the gateway (JSON; mind the 256-char cap) |
bootstrap_url |
Per-user credential-vending endpoint |
gcp_project_id |
Different teams on different GCP projects |
gcp_region |
Data-residency override |
google_client_id google_client_secret |
Different OAuth client per team (uncommon) |
aws_role_arn aws_region |
Different Bedrock roles by team |
otlp_endpoint otlp_headers otlp_resource_attributes |
Route telemetry to a team-specific OTEL collector / tag spans with team-level resource attributes |
One user
Substitute <key> with the attribute name from the table. For non-secret keys
(regions, project IDs) this is the normal path. For secrets (gateway_token,
google_client_secret) the value lands in shell history and this conversation's
transcript — use the bulk CSV path below if that's a problem.
az rest --method PATCH \
--uri "https://graph.microsoft.com/v1.0/users/<upn>" \
--body '{"extension_c2995f3111e74882b7a7ef9def0a0266_<key>":"<value>"}'
Success is silent — PATCH returns 204 with an empty body. To verify:
az rest --method GET --uri "https://graph.microsoft.com/v1.0/users/<upn>?\$select=extension_c2995f3111e74882b7a7ef9def0a0266_<key>"
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.
- 8d ago First seen · 117 lines · 15 tokens per session scan A f0fe63811503
update-user-attrs is a command published in the GitHub repository anthropics/financial-services (34,727 stars, last pushed 13d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,383 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
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.