fdic-mcp-server: Skill for Claude Code

.agents/skills/fdic-portfolio-surveillance/SKILL.md

fdic-portfolio-surveillance is a skill for Claude Code from jflamb/fdic-mcp-server. It costs 82 tokens per session (3,590 once invoked), scanned A, original, MIT.

A workflow for screening a defined group of banks using public data from the Federal Deposit Insurance Corporation (FDIC), the U.S. agency that insures deposits and tracks bank information.

In plain words
What is it for?
Use it to screen banks by state, asset range, or CERT list; rank them by capital, earnings, funding, growth, or overall concern; and identify institutions needing attention.
Why use it?
It helps compare risk and financial health across a group of institutions instead of examining each bank without a shared ranking. It produces a watchlist and explains the reasons for escalation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents).

This is jflamb/fdic-mcp-server's own configuration. It tells Claude Code how to work on fdic-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fdic-mcp-server configures →

Part of the fdic-mcp-server plugin — 4 skills, 7 commands, 1 MCP server shipped together

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/jflamb/fdic-mcp-server/main/.agents/skills/fdic-portfolio-surveillance/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jflamb/fdic-mcp-server

Made for: Claude Code.

Or install fdic-mcp-server, the plugin that ships this one along with the rest of its 4 skills, 7 commands, 1 MCP server.

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 fdic-portfolio-surveillance

README.md
[![agentmods](https://agentmods.dev/badge/skills/jflamb/fdic-mcp-server/fdic-portfolio-surveillance/github.svg)](https://agentmods.dev/skills/jflamb/fdic-mcp-server/fdic-portfolio-surveillance)
Your own site
<a href="https://agentmods.dev/skills/jflamb/fdic-mcp-server/fdic-portfolio-surveillance"><img src="https://agentmods.dev/badge/skills/jflamb/fdic-mcp-server/fdic-portfolio-surveillance/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fdic-portfolio-surveillance

Your own site · 80×15
<a href="https://agentmods.dev/skills/jflamb/fdic-mcp-server/fdic-portfolio-surveillance"><img src="https://agentmods.dev/badge/skills/jflamb/fdic-mcp-server/fdic-portfolio-surveillance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,590 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00082 $0.03590
Opus 5 $0.00041 $0.01795
Sonnet 5 $0.00016 $0.00718
Haiku 4.5 $0.00008 $0.00359

Measured 11d ago against content hash 0258cb1f3e73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fdic-portfolio-surveillance 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 11d 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.

.agents/skills/fdic-portfolio-surveillance/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FDIC Portfolio Surveillance

Skill Type: RIGID

Follow every phase in order. Do not skip phases. Do not produce output before completing Phase 3.


When to Activate

Activate when the user asks to:

  • Screen, triage, or surveil a group of institutions
  • Build a watchlist for a state, asset tier, or peer cohort
  • Rank banks by risk, health, or deterioration across a portfolio
  • Identify which institutions in a universe warrant immediate attention
  • Compare emerging risk signals across a population of banks

Do not activate for single-institution deep dives — use the fdic-bank-deep-dive skill instead.


Inputs

Parameter Required Default Description
Universe definition Yes State (two-letter code), asset range (asset_min / asset_max in $thousands), or explicit CERT list
repdte No Most recent quarter with published data Report date in YYYYMMDD format
start_repdte No Same quarter one year prior to repdte Comparison start date for trend analysis
Ranking emphasis No Most concerning overall Focus area: capital, earnings, funding, growth, or overall
Limit No 25 Maximum institutions to return in the ranked watchlist

Dependency Table

Tool Tier Purpose On Failure
fdic_search_institutions Hard Build the screening universe roster Hard-stop. Cannot determine cohort.
fdic_detect_risk_signals Hard Surface critical and warning-level signals per institution Hard-stop. Cannot rank by risk.
fdic_compare_peer_health Hard Rank institutions by proxy composite and component scores Hard-stop. Cannot produce peer-relative health context.
fdic_compare_bank_snapshots Hard Confirm trends via two-point financial comparison Hard-stop. Cannot validate trend persistence.
fdic_analyze_bank_health Soft Detailed CAMELS-proxy assessment for escalated institutions Note "detailed assessment unavailable" for that institution; preserve watchlist placement.
fdic_analyze_funding_profile Context Funding composition for escalated institutions flagged with funding-domain signals Note "funding follow-up unavailable"; preserve triage result.
fdic_analyze_credit_concentration Context Credit concentration for escalated institutions flagged with credit-domain signals Note "credit concentration follow-up unavailable"; preserve triage result.
fdic_ubpr_analysis Context UBPR-equivalent ratios for escalated institutions needing earnings or efficiency context Note "UBPR analysis unavailable"; preserve triage result.
fdic_regional_context Soft Macro/regional economic backdrop for the universe Omit the Regional Context section or replace with a brief note; do not affect bank-level rankings.

Read the full file on GitHub · 292 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. 11d ago First seen · 292 lines · 82 tokens per session scan A 0258cb1f3e73

Subscribe to this mod's changes

fdic-portfolio-surveillance is a skill published in the GitHub repository jflamb/fdic-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 3,590 once invoked, about $0.0004 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.