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 john-walkoe/pinecone_assistant_mcp --skill pinecone-assistantgit clone --depth 1 https://github.com/john-walkoe/pinecone_assistant_mcpWrote 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/john-walkoe/pinecone_assistant_mcp/pinecone-assistant)<a href="https://agentmods.dev/skills/john-walkoe/pinecone_assistant_mcp/pinecone-assistant"><img src="https://agentmods.dev/badge/skills/john-walkoe/pinecone_assistant_mcp/pinecone-assistant.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 | $0.00115 | $0.02488 |
| Opus 5 | $0.00057 | $0.01244 |
| Sonnet 5 | $0.00023 | $0.00498 |
| Haiku 4.5 | $0.00012 | $0.00249 |
Grade A, and why
pinecone-assistant 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 8d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pinecone Assistant MCP - Research Skill
Available Tools
| Tool | Cost Tier | Best For |
|---|---|---|
assistant_context |
Context tokens (cheapest) | Raw document retrieval, most queries |
assistant_strategic_multi_search_context |
Context tokens | Multi-angle research, comprehensive coverage |
assistant_strategic_multi_search_chat |
Input tokens (expensive) | When AI synthesis across patterns is needed |
assistant_chat |
Input + output tokens (most expensive) | Complex follow-up, AI-powered analysis |
get_configuration_status |
Free | Check current assistant name and model |
update_configuration |
Free | Switch between assistants mid-conversation |
Tool Selection Decision Tree
Always start with the cheapest tool that meets the need:
User wants to find information
├── Simple lookup / single topic
│ └── assistant_context (top_k=3-5)
│
├── Multi-angle / comprehensive topic
│ └── assistant_strategic_multi_search_context (context tokens)
│ └── Follow up with assistant_context for specific gaps
│
├── Need AI to reason across multiple search results
│ └── assistant_strategic_multi_search_chat (input tokens)
│ └── Only when synthesis/reasoning is explicitly needed
│
└── Complex conversation / targeted follow-up
└── assistant_chat (most expensive - use last)
└── Stateless by default - only add history when new
question contains pronouns referencing prior answer
Never start with assistant_chat when assistant_context would suffice.
Token Budget Management
Free Tier Limits (LIFETIME — do NOT reset monthly)
- Context tokens: 500K lifetime — used by
assistant_contextand*_contextvariants - Input tokens: 1.5M lifetime — used by
assistant_chatandassistant_strategic_multi_search_chat - Output tokens: 200K lifetime
⚠️ These are one-time lifetime allocations, not monthly quotas. Once exhausted, upgrade to a paid plan.
Strategy
Maximize context token usage. Minimize input token usage.
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.
- 8d ago First seen · 253 lines · 115 tokens per session scan A fb0c1237de08
pinecone-assistant is a skill published in the GitHub repository john-walkoe/pinecone_assistant_mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 115 tokens to every session and 2,488 once invoked, about $0.0006 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 skills, from other repositories
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
qi-cli
Guide for using qi, a local knowledge search CLI for macOS and Linux. Use this skill when the user wants to index documents into a searchable knowledge base, search or retrieve from one, configure qi's collections or embedding providers (Ollama, OpenAI-compatible), choose between its search modes (BM25, hybrid…
retrieval-workflow
Retrieve ranked evidence bundles from the published DocMason knowledge base.
ingest
Populate the gnosis-mcp knowledge base — from local files, git history, or a crawled website. Handles the full matrix of flags (--force, --prune, --wipe, --embed, --include-crawled) in one place.