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 agentmods add skills/simota/agent-skills/oraclenpx skills add simota/agent-skills --skill oraclegit clone --depth 1 https://github.com/simota/agent-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/simota/agent-skills/oracle)<a href="https://agentmods.dev/skills/simota/agent-skills/oracle"><img src="https://agentmods.dev/badge/skills/simota/agent-skills/oracle.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.05085 |
| Opus 5 | $0.00023 | $0.02542 |
| Sonnet 5 | $0.00009 | $0.01017 |
| Haiku 4.5 | $0.00005 | $0.00509 |
Grade A, and why
oracle 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- oracle — 97% identical, 13 lines differ
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oracle
AI/ML design and evaluation specialist. Oracle designs prompt systems, RAG pipelines, guardrails, evaluation frameworks, and cost-aware delivery plans. Implementation goes to Builder; data-pipeline work goes to Stream.
What ships with it
24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _common 10 B
- reference/_common 13 B
- reference/advanced-tool-use.md 14 KB
- reference/agent-behavior-contract.md 13 KB
- reference/agent-design.md 12 KB
- reference/ai-safety-guardrails.md 7.0 KB
- reference/architect 15 B
- reference/architecture-review.md 8.2 KB
- reference/autorun-schema.md 616 B
- reference/beacon 12 B
- reference/cloak 11 B
- reference/cost-optimization.md 19 KB
- reference/embedding-strategy.md 7.5 KB
- reference/evaluation-observability.md 19 KB
- reference/human-ai-trust.md 16 KB
- reference/llm-application-patterns.md 11 KB
- reference/llm-production-anti-patterns.md 6.9 KB
- reference/nexus 11 B
- reference/omen 10 B
- reference/probe 11 B
- reference/prompt-engineering.md 17 KB
- reference/rag-design-anti-patterns.md 9.9 KB
- reference/recipes-index.md 1.8 KB
- reference/reference-index.md 2.6 KB
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.
- yesterday First seen · 262 lines · 45 tokens per session scan A c14b16d1baaf
oracle is a skill published in the GitHub repository simota/agent-skills (75 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 5,085 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
vector-memory
HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.
documentation-search
Search the internal knowledge base for runbooks, architecture documentation, ADRs, best practices, and troubleshooting guides using RAG. Use when looking for internal documentation, deployment procedures, architecture decisions, or operational runbooks.
software-ai-integration
Applies production AI integration patterns for chat, structured output, guardrails, provider routing, and AI UX. Use when adding LLM-powered features to an application.
ai-orchestration-langchain
LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing.
model-sovereignty
This skill should be used when the user asks about "local models", "custom models", "fine-tuning", "self-hosting models", "model selection", "which model should I use", "data privacy and models", "LoRA", "RAG vs fine-tuning", "Ollama", "vLLM", or wants guidance on whether to build, host, or customise their own AI…
performant-ai
Strategies for high-performance AI/LLM systems (Context Management, Prompt Engineering, RAG, Inference Tuning).