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 skills add JoelLewis/finance_skills --skill privacy-data-securitygit clone --depth 1 https://github.com/JoelLewis/finance_skillsWrote 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/skills/joellewis/finance_skills/privacy-data-security)<a href="https://agentmods.dev/skills/joellewis/finance_skills/privacy-data-security"><img src="https://agentmods.dev/badge/skills/joellewis/finance_skills/privacy-data-security/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.
<a href="https://agentmods.dev/skills/joellewis/finance_skills/privacy-data-security"><img src="https://agentmods.dev/badge/skills/joellewis/finance_skills/privacy-data-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00141 | $0.07874 |
| Opus 5 | $0.00071 | $0.03937 |
| Sonnet 5 | $0.00028 | $0.01575 |
| Haiku 4.5 | $0.00014 | $0.00787 |
Grade A, and why
privacy-data-security 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 10d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Privacy and Data Security
Regulatory status current as of June 2026 — verify effective dates, dollar thresholds, and pending rulemakings against current SEC/FINRA/FinCEN sources before advising.
Core Concepts
Regulation S-P (Privacy of Consumer Financial Information)
Regulation S-P (17 CFR Part 248, Subparts A and B) implements Title V of the Gramm-Leach-Bliley Act (GLBA) for entities registered with the SEC. It applies to SEC-registered investment advisers, broker-dealers, investment companies, and transfer agents. The regulation has three core components:
Privacy Notice Requirements. Firms must provide an initial privacy notice to each customer at the time of establishing the customer relationship (17 CFR 248.4). The notice must describe: (a) categories of nonpublic personal information (NPI) collected, (b) categories of NPI disclosed to third parties, (c) categories of affiliates and nonaffiliated third parties to whom NPI is disclosed, (d) the customer's right to opt out of certain disclosures, (e) the firm's policies and practices for protecting confidentiality and security of NPI, and (f) any disclosures required under the Fair Credit Reporting Act. Annual privacy notices must be delivered once during each 12-month period for the duration of the customer relationship (17 CFR 248.5). The FAST Act of 2015 (Pub. L. 114-94, Section 75001) created an exception to the annual notice requirement: firms that (i) share NPI only under the exceptions in 17 CFR 248.14 and 248.15, and (ii) have not changed their privacy policies and practices since the most recent notice, may satisfy the annual requirement by posting the privacy notice continuously on their website in a clear and conspicuous manner rather than mailing it to each customer.
Opt-Out Requirements. Before sharing NPI with nonaffiliated third parties, firms must provide customers with a reasonable opportunity to opt out (17 CFR 248.7 and 248.10). The opt-out notice must be clear, conspicuous, and delivered along with or as part of the privacy notice. Exceptions to the opt-out requirement include: (a) disclosures necessary to effect, administer, or enforce a transaction requested by the customer, (b) disclosures to service providers and joint marketing partners under written contractual agreements that restrict the third party's use of NPI, (c) disclosures with customer consent, (d) disclosures to protect against fraud, and (e) disclosures required by law (17 CFR 248.14 and 248.15). Joint marketing agreements must include written contracts specifying that the third party will maintain the confidentiality of NPI and will use it only for the purposes for which it was disclosed.
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.
- 10d ago First seen · 160 lines · 141 tokens per session scan A 019d47675ca8
privacy-data-security is a skill published in the GitHub repository JoelLewis/finance_skills (184 stars, last pushed 1mo ago), licensed MIT. It adds 141 tokens to every session and 7,874 once invoked, about $0.0007 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 skills, from other repositories
EU AI Act High-Risk Obligations
PASS/FAIL/N/A checklist for the high-risk AI obligations under Articles 8-15 of the EU AI Act, plus the quality management system, conformity assessment, registration, post-market monitoring, and incident reporting.
EU AI Act Risk Classification
Decision tree for classifying an AI system into the EU AI Act risk tier (unacceptable/high/limited/minimal) and identifying the actor role (provider/deployer/importer/distributor).
EU AI Act General-Purpose AI
Checklist for the general-purpose AI (GPAI) obligations under Articles 51-55 — technical documentation, copyright policy, training-data summary, and systemic-risk obligations (evaluation, adversarial testing, incident reporting, cybersecurity).
EU AI Act Transparency
Checklist for the Article 50 transparency obligations — chatbot AI disclosure, machine-readable marking of synthetic content, emotion-recognition/biometric-categorisation notice, and deepfake/public-interest-text labelling.
Exception Documentation
The template for documenting a deliberate, approved deviation from an infrastructure invariant — rationale, compensating control, approver, and expiry — instead of a silent workaround.
fsi-compliance-checker
Maps code, architecture, and infrastructure changes to specific control IDs in PCI-DSS v4.0 and MAS TRM (Singapore financial regulator), producing an audit-traceable findings report with per-control remediation.