Borrowing it
Nothing to install: this file belongs to jflamb/fdic-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jflamb/fdic-mcp-server/main/.claude/commands/fdic-bank-deep-dive.mdgit clone --depth 1 https://github.com/jflamb/fdic-mcp-serverWrote 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/jflamb/fdic-mcp-server/fdic-bank-deep-dive)<a href="https://agentmods.dev/commands/jflamb/fdic-mcp-server/fdic-bank-deep-dive"><img src="https://agentmods.dev/badge/commands/jflamb/fdic-mcp-server/fdic-bank-deep-dive.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 | $0.00109 | $0.06171 |
| Opus 5 | $0.00055 | $0.03086 |
| Sonnet 5 | $0.00022 | $0.01234 |
| Haiku 4.5 | $0.00011 | $0.00617 |
Grade A, and why
fdic-bank-deep-dive 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 — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fdic-bank-deep-dive
Skill Type: RIGID
This workflow has a fixed section order, a fixed tool chain with a fixed dependency structure, and every section is always present in the output. Sections degrade gracefully when tools return partial data or fail — the report structure is never truncated.
You MUST follow every step in order. You MUST NOT skip sections. You MUST NOT proceed to the tool chain without a confirmed CERT and validated report date.
All data in this report comes from public FDIC data and, where available, FRED macroeconomic data. There is no per-paragraph provenance attribution — every data point is public. Disclaimers appear at the top and bottom of the report only.
Step 1: Collect Input
Ask the user:
"Which institution would you like to analyze? Provide a bank name or FDIC certificate number, and optionally a report date (YYYYMMDD)."
Step 2: Resolve to CERT
You must resolve the user's input to a confirmed FDIC Certificate Number before proceeding.
Path A — CERT provided directly
If the user provides a numeric CERT:
- Call
fdic_get_institutionwith the providedcert. - If found, present the identity confirmation:
"I found [NAME] (CERT [CERT]) in [CITY], [STATE] — $[ASSET]K in total assets. Is this the institution you mean?"
- If the institution is inactive (ACTIVE: 0), add a warning:
"Note: This institution is inactive. Financial data will be historical. Do you want to proceed?"
- Proceed only after the user confirms.
- If the CERT is not found, stop: "No FDIC-insured institution found with CERT [number]. Please check the number and try again."
Path B — Bank name provided
Use a tiered search strategy. Always confirm the final selection with the user.
Tier 1 — Exact quoted search (active only):
Call fdic_search_institutions with filter NAME:"[user input]" AND ACTIVE:1, limit 10.
If results are returned, move to Candidate Ranking below.
Tier 2 — Loose token-based search (active only):
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 · 531 lines · 109 tokens per session scan A e39906c1369d
fdic-bank-deep-dive is a command published in the GitHub repository jflamb/fdic-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 109 tokens to every session and 6,171 once invoked, about $0.0005 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 2026-08-31.
Other commands, from other repositories
research
Professional equity research analysis with institutional-grade formatting.
search-flights
Search award flight availability across airlines.
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.