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 instructions/pinecone-io/gemini-cli-extension/gemini-mdgit clone --depth 1 https://github.com/pinecone-io/gemini-cli-extensionWrote 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/instructions/pinecone-io/gemini-cli-extension/gemini-md)<a href="https://agentmods.dev/instructions/pinecone-io/gemini-cli-extension/gemini-md"><img src="https://agentmods.dev/badge/instructions/pinecone-io/gemini-cli-extension/gemini-md.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 | $0.00569 | $0.00569 |
| Opus 5 | $0.00284 | $0.00284 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
gemini-cli-extension GEMINI.md 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 3d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pinecone Extension for Gemini CLI
You have access to the Pinecone MCP server and a suite of specialized Agent Skills for managing vector indexes, performing semantic search, and building document Q&A assistants.
Available Agent Skills
This extension bundles several Agent Skills under skills/. Gemini CLI is configured to auto-invoke these skills based on your intent. If you experience routing issues, you can explicitly request a skill by name (e.g., "Use the quickstart skill").
| Skill | Description |
|---|---|
quickstart |
Interactive onboarding for new developers. Choose between Database (vector search) or Assistant (document Q&A) paths. |
query |
Search integrated indexes (those with built-in embedding models) using natural language text via the Pinecone MCP. |
cli |
Guide for using the Pinecone CLI (pc) for terminal-based management of all index types and advanced vector operations. |
assistant |
Create, manage, and chat with Pinecone Assistants for document Q&A with citations. |
mcp |
Reference for all available Pinecone MCP server tools and their parameters. |
pinecone-docs |
Curated links to official Pinecone documentation, organized by topic. |
help |
Overview of all available Pinecone skills and setup requirements. |
Key Concepts & Setup
- Integrated Indexes: These use Pinecone's hosted embedding models. You can pass raw text, and Pinecone handles embedding automatically.
- PINECONE_API_KEY:
- Required for MCP: Must be configured in your Gemini CLI / MCP settings.
- Required for Skills: Many skills run bundled Python scripts. You must also export the key in your terminal (
export PINECONE_API_KEY="your-key") for these scripts to function.
- Tools: Use the
cliskill if you need to manage standard (non-integrated) indexes or perform bulk vector operations that the MCP does not yet support.
Available MCP Tools
list-indexes— List all Pinecone indexes.describe-index— Get index configuration and namespaces.describe-index-stats— Get statistics (record counts, namespaces).search-records— Search with optional metadata filtering and reranking.cascading-search— Search across multiple indexes with deduplication and reranking.create-index-for-model— Create an index with integrated embeddings.upsert-records— Insert or update records.rerank-documents— Rerank using a specialized model.search-docs— Search Pinecone documentation.
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.
- 3d ago First seen · 40 lines · 569 tokens per session scan A abe27930cc63
gemini-cli-extension GEMINI.md is an instructions file published in the GitHub repository pinecone-io/gemini-cli-extension (23 stars, last pushed 19d ago), licensed MIT. It adds 569 tokens to every session, about $0.0028 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 instructions, from other repositories
FileSearchStore-extension GEMINI.md
Instructions for tanaikech/FileSearchStore-extension: You are an expert in managing File Search Stores for Gemini API using all tools of the MCP server "file-search-store-extension".
RAGLight CLAUDE.md
Instructions for Bessouat40/RAGLight, covering claude.md, commands, install dependencies, run all tests and run a single test module.
rag AGENTS.md
Instructions for NVIDIA-AI-Blueprints/rag, covering nvidia rag blueprint, project structure, development commands, backend (python) and optional: ragas benchmark cli (see scripts/eval/readme.md).
rag CLAUDE.md
Instructions for NVIDIA-AI-Blueprints/rag, covering nvidia rag blueprint, project structure, development commands, backend (python) and optional: ragas benchmark cli (see scripts/eval/readme.md).
pinecone-claude-code-plugin CLAUDE.md
Instructions for pinecone-io/pinecone-claude-code-plugin, covering claude code plugin — skill conventions, context, skill naming, askuserquestion and environment variables.
skills CLAUDE.md
Instructions for pinecone-io/skills, covering skills repo — authoring guidelines, generalization rules and linting.