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 toolbeltai/toolbelt-skills --skill toolbeltgit clone --depth 1 https://github.com/toolbeltai/toolbelt-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/toolbeltai/toolbelt-skills/toolbelt)<a href="https://agentmods.dev/skills/toolbeltai/toolbelt-skills/toolbelt"><img src="https://agentmods.dev/badge/skills/toolbeltai/toolbelt-skills/toolbelt/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/toolbeltai/toolbelt-skills/toolbelt"><img src="https://agentmods.dev/badge/skills/toolbeltai/toolbelt-skills/toolbelt.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00219 | $0.04321 |
| Opus 5 | $0.00110 | $0.02160 |
| Sonnet 5 | $0.00044 | $0.00864 |
| Haiku 4.5 | $0.00022 | $0.00432 |
Grade A, and why
toolbelt 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 12d 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 — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Toolbelt — A collaborative substrate for your agents
Your data. Your agents. One shared brain.
Toolbelt is a collaborative substrate over your data. Discover documents, structured data, events, entities, and relationships across agents and sessions. Better answers. Fewer tokens. Curated context, not raw access.
Three things make it different:
- Knowledge extraction. Upload any document — entities and relationships extracted automatically, queryable immediately.
- Hybrid retrieval. Ask questions that span structured tables, documents, and relationships in a single call. No stitching databases together. Orchestrates semantic, structured, and hybrid retrieval.
- Shared workspaces. Share the URL and any agent can query the same workspace — like a shared Google Doc for your data.
Two surfaces — keep them straight
Toolbelt has exactly two surfaces. Knowing which is which is the most important thing in this skill:
| Surface | URL | Who uses it | When |
|---|---|---|---|
| MCP server (the agentic surface) | https://mcp.toolbelt.ai/mcp |
Agents | Every data operation. This is where the agentic flow happens — search, SQL, knowledge graph, record findings, read timeline. |
| app.toolbelt.ai (the human web UI) | https://app.toolbelt.ai |
Humans (in a browser) | Sign in, view/manage namespaces, billing, Pro/Team upgrade. Plus a small HTTP API at /api/onboard* used once during setup. |
Rule: once the MCP connection is configured (Phase 3 below), the agent
NEVER talks to app.toolbelt.ai again — every subsequent action goes
through MCP. The only reason to mention app.toolbelt.ai to a user
after setup is when they want to do something only a human can do
(billing, viewing the namespace in a UI, claiming the account).
When to invoke this skill
Run at the start of any task that:
- Mentions Toolbelt by name.
- Needs persistent memory across turns or sessions.
- Needs natural-language access to structured or unstructured data.
- Involves multiple agents collaborating on the same data.
- Would otherwise require wiring up several separate MCP tools.
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.
- 12d ago First seen · 403 lines · 219 tokens per session scan A afdc73e71bd8
toolbelt is a skill published in the GitHub repository toolbeltai/toolbelt-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 219 tokens to every session and 4,321 once invoked, about $0.0011 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
ac-tools-video-query
Analyzes video files using Google Gemini API and answers questions about content. Triggers on keywords: video query, analyze video, video analysis, query video.
pinecone-quickstart
Interactive Pinecone quickstart for new developers. Choose between two paths - Database (create an integrated index, upsert data, and query using Pinecone MCP + Python) or Assistant (create a Pinecone Assistant for document Q&A). Use when a user wants to get started with Pinecone for the first time or wants a guided…
pinecone-n8n
Build n8n workflows using the Pinecone Assistant node or Pinecone Vector Store node. Use when building RAG pipelines, chat-with-docs workflows, configuring Pinecone nodes in n8n, troubleshooting Pinecone n8n nodes, or asking about best practices for Pinecone in n8n.
pinecone-full-text-search
Create, ingest into, and query a Pinecone full-text-search (FTS) document index using the graduated document-schema API (Python SDK 10.0.0, API version 2026-07). Use when the user or agent asks to build a text search index on Pinecone, add dense or sparse vector fields, ingest documents, construct scoreby clauses…
pinecone-cli
Guide for using the Pinecone CLI (pc) to manage Pinecone resources from the terminal. The CLI supports ALL index types (standard, integrated, sparse) and all vector operations — unlike the MCP which only supports integrated indexes. Use for batch operations, vector management, backups, namespaces, CI/CD automation…
pinecone-help
Overview of all available Pinecone skills and what a user needs to get started. Invoke when a user asks what skills are available, how to get started with Pinecone, or what they need to set up before using any Pinecone skill.