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 frankxai/claude-skills-library --skill oracle-confidentialitygit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/frankxai/claude-skills-library/oracle-confidentiality)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/oracle-confidentiality"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/oracle-confidentiality/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/frankxai/claude-skills-library/oracle-confidentiality"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/oracle-confidentiality.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00049 | $0.01113 |
| Opus 5.5 | $0.00020 | $0.00445 |
| Sonnet 5.5 | $0.00010 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
oracle-confidentiality 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 1mo 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oracle Confidentiality Guardian
Purpose: Enforce confidentiality protocol across all Oracle AI Architect deliverables. Scope: Pre-delivery audit, codename enforcement, content sanitization. Authority: This skill has VETO power. If it fails, delivery is blocked.
When to Use This Skill
Invoke:
- Before delivering ANY document to a customer
- Before committing client-folder content to git
- When generating content that references customer context
- As the final step of /oracle-solution-design Phase 5
Trigger: /oracle-confidentiality or automatically at end of solution design workflow
The Codename Protocol
Rules (Non-Negotiable)
- Codenames are OPAQUE -- A, B, E, K, O, P, R, V have no inherent meaning
- Never persist context -- Industry, scope, employee count, revenue NEVER in committed files
- Conversation-only context -- Tell Claude what the codename means at session start, it stays in memory only
- README.md is the only committable file per client -- contains ONLY: status, role, codename
- clients/.gitignore blocks: deliverables/, notes/, docs/, SOLUTION-DESIGN.md, auto-CLAUDE.md
- Research goes to research/topics/ -- NEVER to research/projects/[CODE]/ (would link codename to topic)
What CAN Be in Committed Files
- Codename letter only (A, B, K, etc.)
- Status (Active, Prospect, Completed)
- Role (AI/Cloud Architecture)
- Generic dates and milestones
What MUST NEVER Be in Committed Files
- Real customer name
- Industry vertical
- Geographic region or country
- Employee count or revenue
- Contract value or pricing
- Specific technology stack of the customer
- Names of customer employees
- Internal Oracle pricing or discounts
Pre-Delivery Audit Checklist
Run this checklist before any deliverable leaves the workspace:
Step 1: Content Scan
Search all output files for:
- Real customer names (from conversation context)
- Industry-specific terms that could identify the client
- Geographic identifiers tied to the client
- Internal Oracle pricing not on public price list
- Competitor names used in attack mode (not just comparison)
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.
- 1mo ago First seen · 151 lines · 49 tokens per session scan A 95ffd08f4e79
oracle-confidentiality is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 1,113 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
recipe-create-events-from-sheet
Read event data from a Google Sheets spreadsheet and create Google Calendar entries for each row.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
recipe-save-email-to-doc
Save a Gmail message body into a Google Doc for archival or reference.
notion
Notion workspace operations - create, read, and update pages, databases, and blocks via the Notion API.
obsidian
Obsidian vault management - create, edit, and search markdown notes in the user's local vault.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.