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.
/plugin marketplace add frankxai/claude-code-oracle-skillsnpx agentmods add plugins/frankxai/claude-code-oracle-skills/oracle-work-modegit clone --depth 1 https://github.com/frankxai/claude-code-oracle-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/plugins/frankxai/claude-code-oracle-skills/oracle-work-mode)<a href="https://agentmods.dev/plugins/frankxai/claude-code-oracle-skills/oracle-work-mode"><img src="https://agentmods.dev/badge/plugins/frankxai/claude-code-oracle-skills/oracle-work-mode.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
oracle-work-mode 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 6d 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.
What it actually says
{
"name": "oracle-work-mode",
"version": "1.0.0",
"description": "Oracle consulting work mode with confidentiality protocols, daily capture, and research workflows",
"author": "FrankX",
"repository": "https://github.com/frankxai/claude-code-oracle-skills",
"keywords": [
"oracle",
"consulting",
"confidentiality",
"research",
"daily-capture",
"work-tracking"
],
"commands": [
{
"name": "oracle-work",
"description": "Activate Oracle work context with confidentiality protocols"
},
{
"name": "daily-capture",
"description": "Quick capture of wins, learnings, and blockers"
},
{
"name": "research",
"description": "Start confidential research session"
}
],
"agents": [
{
"name": "oracle-cloud-coach",
"description": "OCI architecture guidance and technical coaching"
},
{
"name": "research-analyst",
"description": "Web research with confidentiality enforcement"
},
{
"name": "confidentiality-guardian",
"description": "Review content before external sharing"
}
]
}
What it installs
The manifest is a name and a version. 3 commands, 3 agents travel with it, and installing the plugin installs all of them — 462 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 6d ago First seen · 44 lines scan A 4014c9f4e17d
oracle-work-mode is a plugin published in the GitHub repository frankxai/claude-code-oracle-skills (2 stars, last pushed 9d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
hyper-mcp
A fast, secure MCP server that extends its capabilities through WebAssembly plugins.
oracle-forms
Read Oracle Forms modules (.fmb/.mmb/.pll/.olb) from a directory — blocks, items, triggers, program units, PL/SQL, and durable annotations. Needs a JDK 21+ on PATH.
faos-ai-engineer
🤖 AI Engineer — AI Engineer + LLM Systems Specialist.
faos-analyst
📊 Business Analyst — Strategic Business Analyst + Requirements Expert.
ai-architect-mcp-spec
Stateless reducer that turns a feature description into a 9-file PRD. Multi-judge verification with weighted-average + Bayesian consensus, calibrated against externally-grounded oracles (schema/math/code/spec). Closed loop: per-judge Bayesian reliability calibration, Kaplan-Meier retry budgets, Clopper-Pearson KPI…
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.