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 ashish7802/awesome-api-skills --skill pineconegit clone --depth 1 https://github.com/ashish7802/awesome-api-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/ashish7802/awesome-api-skills/pinecone)<a href="https://agentmods.dev/skills/ashish7802/awesome-api-skills/pinecone"><img src="https://agentmods.dev/badge/skills/ashish7802/awesome-api-skills/pinecone/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/ashish7802/awesome-api-skills/pinecone"><img src="https://agentmods.dev/badge/skills/ashish7802/awesome-api-skills/pinecone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00625 |
| Opus 5 | $0.00000 | $0.00313 |
| Sonnet 5 | $0.00000 | $0.00125 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
pinecone 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 7d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pinecone API Skill
Quick Start
Pinecone stores vector embeddings for fast similarity search, serving as the memory layer for RAG (Retrieval-Augmented Generation) applications.
npm install @pinecone-database/pinecone
Common Workflows
RAG (Retrieval-Augmented Generation)
- Convert a user query to a vector embedding (e.g., using OpenAI
text-embedding-3-small). - Query Pinecone for the top 5 most similar vectors.
- Inject the retrieved metadata text into the LLM system prompt.
Production Patterns
Metadata Filtering
Do not rely entirely on vector similarity if exact categorical constraints exist. Attach metadata (e.g., tenant_id, document_type) to your vectors and use Pinecone's filter syntax to restrict the search space before calculating cosine similarity.
Error Recovery
Handle rate limits (HTTP 429) and index initialization delays. Serverless indexes scale automatically but may temporarily reject massive, sudden bursts of write operations. Use backoff retries for upserts.
Security Notes
Pinecone Serverless environments do not support VPC peering. Ensure data is encrypted at rest and secure your API keys tightly. Segment tenant data utilizing namespaces or strict metadata filters.
Performance Considerations
Vector search latency scales with dimensionality and index size. Batch your upsert operations in chunks of 100-500 vectors. Query latency is typically <50ms; if slower, ensure you are querying the correct geographic region.
Testing Guidance
Mock the Pinecone client in unit tests. For integration tests, utilize an isolated namespace (e.g., test_run_123) to prevent test data from contaminating the primary index, and delete the namespace post-test.
Troubleshooting
If similarity search returns irrelevant results, verify that the embedding model used for the query is exactly the same model used during the upsert phase. Mismatched dimensions or models will produce garbage results.
References
What ships with it
7 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.
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.
- 7d ago First seen · 63 lines · 0 tokens per session scan A d6c9715cca91
pinecone is a skill published in the GitHub repository ashish7802/awesome-api-skills (13 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 625 tokens. 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
wshobson-rag-implementation
Skill "wshobson-rag-implementation" from ItamarZand88/awesome-agent-conventions, covering rag implementation, when to use this skill, core components, 1. vector databases and 2. embeddings.
dify-workflow
Use when dify AI workflow platform — LLM apps, knowledge bases, agents, workflow orchestration, API deployment. Use when working with dify workflow.
ai-expertise-engine
Comprehensive AI/ML expertise covering prompt engineering, LLM architecture, AI agent design, RAG systems, fine-tuning, AI safety, and cutting-edge AI research for building and leveraging AI systems.
context-retrieval
Retrieves and synthesizes relevant information from a knowledge base using RAG techniques to provide grounded context for a given query.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
hybrid-search-implementation
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.