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.
git 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/commands/frankxai/claude-code-oracle-skills/research)<a href="https://agentmods.dev/commands/frankxai/claude-code-oracle-skills/research"><img src="https://agentmods.dev/badge/commands/frankxai/claude-code-oracle-skills/research/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/commands/frankxai/claude-code-oracle-skills/research"><img src="https://agentmods.dev/badge/commands/frankxai/claude-code-oracle-skills/research.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 | $0.00013 | $0.00520 |
| Opus 5 | $0.00006 | $0.00260 |
| Sonnet 5 | $0.00003 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
research 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 9d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Session Mode
Conduct research for Oracle consulting while maintaining strict confidentiality.
Research Protocol
Step 1: Define Scope
- Topic: What are you researching?
- Purpose: Learning / Problem-solving / Customer preparation / Certification
- Project Link: Related to a project codename or General knowledge?
- Depth: Quick overview / Moderate / Deep dive
Step 2: Conduct Research
Using WebSearch with confidentiality:
Search Strategy:
- Use current year for latest information
- Focus on: Oracle, OCI, enterprise AI, cloud architecture
- Cross-reference multiple sources
- Prioritize: Oracle docs, official blogs, reputable tech sources
Confidentiality Rules:
- NEVER include customer names in search queries
- Search generic patterns, not specific implementations
- Example: "OCI OKE networking best practices" NOT "Customer XYZ OKE setup"
Step 3: Synthesize Findings
I create structured research documents:
# [Topic Title]
**Researched:** YYYY-MM-DD
**Purpose:** [Learning/Problem-solving/etc.]
**Project Link:** [Codename/General]
## Key Findings
### Finding 1: [Title]
[Summary]
- Source: [URL]
- Relevance: [How this applies]
## Synthesis
[Cross-cutting insights from multiple sources]
## Action Items
- [ ] [What to do with this knowledge]
- [ ] [How to apply to current projects]
Step 4: Link to Projects
If research is relevant to a project:
- Reference the project codename
- Suggest how findings might help (abstractly)
- Store in project-specific research folder
Quick Research Syntax
research: [topic]→ Quick overviewdeep dive: [topic]→ Comprehensive research[CODENAME] research: [topic]→ Project-linked research
Examples
research: OCI GPU shapes for LLM inference
deep dive: Kubernetes service mesh patterns for enterprise
A research: AI for network optimization use cases
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.
- 9d ago First seen · 90 lines · 13 tokens per session scan A dc84c479fc67
research is a command published in the GitHub repository frankxai/claude-code-oracle-skills (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 13 tokens to every session and 520 once invoked, about $0.0001 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
quick-research
description: "Multi-agent parallel research for breadth-first exploration, comparisons, or ranking requests".
research
description: "Guided Research scoped to market, domain, competitive analysis, or technical research (optional)".
create-architecture
description: "Create an Architecture Document to Guide Development of a PRD (required for BMad Method projects)".
create-excalidraw-diagram
description: "Create system architecture or technical diagram (Excalidraw) (Use any time you need a diagram)".
brainstorm-project
description: "Guided Project Brainstorming session with final report (optional)".
product-brief
description: "Create a Product Brief (recommended input for PRD)".