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/oracle-devrel/oracle-ai-developer-hub/build-pathsnpx skills add oracle-devrel/oracle-ai-developer-hub --skill build-pathsgit clone --depth 1 https://github.com/oracle-devrel/oracle-ai-developer-hubWrote 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/oracle-devrel/oracle-ai-developer-hub/build-paths)<a href="https://agentmods.dev/skills/oracle-devrel/oracle-ai-developer-hub/build-paths"><img src="https://agentmods.dev/badge/skills/oracle-devrel/oracle-ai-developer-hub/build-paths.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 5.1 | $0.00057 | $0.01145 |
| Opus 5 | $0.00028 | $0.00573 |
| Sonnet 5 | $0.00011 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
build-paths 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
56 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.
- advanced/project-ideas.md 16 KB
- advanced/SKILL.md 19 KB
- archive/advanced-ideas.md 8.3 KB
- archive/beginner-ideas.md 6.8 KB
- archive/intermediate-ideas.md 6.9 KB
- archive/README.md 2.3 KB
- beginner/project-ideas.md 8.1 KB
- beginner/SKILL.md 12 KB
- docs/screenshots/intermediate-nl2sql-chat.png 76 KB
- GETTING_STARTED.md 16 KB
- intermediate/project-ideas.md 11 KB
- intermediate/SKILL.md 17 KB
- OVERVIEW.md 11 KB
- PLAN.md 28 KB
- README.md 6.0 KB
- shared/interview.md 5.6 KB
- shared/references/ai-vector-search.md 3.7 KB
- shared/references/exemplars.md 8.7 KB
- shared/references/hybrid-search.md 4.2 KB
- shared/references/json-duality.md 5.5 KB
- shared/references/langchain-oracledb.md 11 KB
- shared/references/oamp.md 13 KB
- shared/references/oci-genai-openai.md 7.7 KB
- shared/references/ollama-local.md 3.7 KB
- shared/references/onnx-in-db-embeddings.md 6.7 KB
- shared/references/oracle-26ai-free-docker.md 5.9 KB
- shared/references/oracledb-python.md 3.8 KB
- shared/references/property-graph.md 5.0 KB
- shared/references/sources.md 2.4 KB
- shared/references/sqlcl-tee.md 2.5 KB
- shared/references/visual-oracledb-features.md 5.1 KB
- shared/snippets/forbidden_imports.txt 280 B
- shared/snippets/in_db_embeddings.py 2.6 KB runs code
- shared/snippets/memory_manager.py 7.4 KB runs code
- shared/snippets/metadata_monkeypatch.py 1.9 KB runs code
- shared/snippets/oamp_helpers.py 11 KB runs code
- shared/snippets/oci_chat_factory.py 3.0 KB runs code
- shared/snippets/oci_cohere_embeddings.py 3.1 KB runs code
- shared/snippets/onnx_loader.py 2.5 KB runs code
- shared/snippets/oracle_chat_history.py 4.7 KB runs code
- shared/snippets/README.md 3.5 KB
- shared/snippets/sql_runner.py 6.0 KB runs code
- shared/snippets/sqlcl_tee.py 3.8 KB runs code
- shared/snippets/web_fetch_tool.py 2.8 KB runs code
- shared/templates/docker-compose.oracle-free.yml 2.8 KB
- shared/templates/env.example 3.8 KB
- shared/templates/notebook.template.ipynb 4.1 KB
- shared/templates/pyproject.toml.template 1.8 KB
- shared/templates/readme.template.md 1.5 KB
- shared/templates/verify.template.py 4.0 KB runs code
- shared/verify.md 3.0 KB
- skills/langchain-oracledb-helper/SKILL.md 11 KB
- skills/oracle-aidb-docker-setup/SKILL.md 11 KB
- skills/oracle-mcp-server-helper/SKILL.md 16 KB
- skills/README.md 3.9 KB
- tests/.gitkeep 0 B
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 · 87 lines · 57 tokens per session scan A f935a69d343e
build-paths is a skill published in the GitHub repository oracle-devrel/oracle-ai-developer-hub (4,364 stars, last pushed yesterday), with no licence file. It adds 57 tokens to every session and 1,145 once invoked, about $0.0003 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
langchain_patterns
Implement Retrieval-Augmented Generation (RAG) systems with LangChain4j. Build document ingestion pipelines, embedding stores, vector search strategies, and knowledge-enhanced AI applications. Use when creating question-answering systems over document collections or AI assistants with external knowledge bases.
langchain_patterns
Implement Retrieval-Augmented Generation (RAG) systems with LangChain4j. Build document ingestion pipelines, embedding stores, vector search strategies, and knowledge-enhanced AI applications. Use when creating question-answering systems over document collections or AI assistants with external knowledge bases.
qdrant
Vector search engine for production RAG systems.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.