Discover Tools

Discover Tools is a skill for Claude Code, Codex from yuchenbigpen1/normies. It costs 32 tokens per session (3,007 once invoked), scanned C, original, Apache-2.0.

An integration-finding guide for connecting an agent to outside tools, services, or APIs. It searches available servers and community skills, evaluates matches, and translates their setup details.

In plain words
What is it for?
Finding an MCP server, skill, or API integration for a business problem; checking existing connections; and preparing configuration for an external service.
Why use it?
It helps when the needed connection is not already available, so you do not have to search registries or work out configuration formats alone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Finding an MCP server, skill, or API integration for a business problem; checking existing connections; and preparing configuration for an external service.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yuchenbigpen1/normies/discover-tools
Install

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.

Any agent
npx skills add yuchenbigpen1/normies --skill discover-tools
Clone the repo
git clone --depth 1 https://github.com/yuchenbigpen1/normies

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Discover Tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/yuchenbigpen1/normies/discover-tools/github.svg)](https://agentmods.dev/skills/yuchenbigpen1/normies/discover-tools)
Your own site
<a href="https://agentmods.dev/skills/yuchenbigpen1/normies/discover-tools"><img src="https://agentmods.dev/badge/skills/yuchenbigpen1/normies/discover-tools/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.

agentmods 80×15 button for Discover Tools

Your own site · 80×15
<a href="https://agentmods.dev/skills/yuchenbigpen1/normies/discover-tools"><img src="https://agentmods.dev/badge/skills/yuchenbigpen1/normies/discover-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,007 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.03007
Opus 5 $0.00016 $0.01503
Sonnet 5 $0.00006 $0.00601
Haiku 4.5 $0.00003 $0.00301

Measured 12d ago against content hash 09aed378c219, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

Discover Tools scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s "https://registry.modelcontextprotocol.io/v0.1/servers?search={query}&limit=10" | python3 -m json.tool

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://registry.modelcontextprotocol.io/v0.1/servers?search={query}&limit=10" | python3 -m json.tool
packages/shared/assets/workspace-template/skills/discover-tools/SKILL.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discover Tools

You are an expert at finding integrations for any tool or business problem. When a user mentions a tool, service, or workflow need that isn't already connected, use this skill to find and recommend the right integration.

When to Use This Skill

  • User mentions a tool or service not yet connected as a source
  • User describes a workflow problem that might be solved with an integration
  • User asks "is there a way to connect X?" or "can you work with Y?"
  • User wants to automate something involving an external service

Decision Framework

Follow this order. Stop as soon as you find a good match.

Step 1: Check What Normies Already Has

Before searching externally, check if Normies has a built-in guide or existing source:

mcp__craft-agents-docs__SearchCraftAgents({ query: "{service name} source setup" })

Available built-in guides: GitHub, Linear, Slack, Gmail, Google Calendar, Google Drive, Google Docs, Google Sheets, Outlook, Microsoft Calendar, Teams, SharePoint, Craft, Filesystem, Brave Search, Memory

Also check if the user already has this source connected (look at the active sources in the session).

If a built-in guide exists, follow the source setup process in ~/.normies/docs/sources.md instead of searching externally.

Step 2: Search MCP Registries

If no built-in guide exists, search for an MCP server. Try both registries:

A. Official MCP Registry (free, no auth needed):

curl -s "https://registry.modelcontextprotocol.io/v0.1/servers?search={query}&limit=10" | python3 -m json.tool

B. Smithery Registry (larger catalog, needs API key):

curl -s "https://registry.smithery.ai/servers?q={query}&pageSize=10" \
  -H "Authorization: Bearer {SMITHERY_API_KEY}" | python3 -m json.tool

If the user doesn't have a Smithery API key, use web search instead:

WebSearch({ query: "smithery.ai {service name} MCP server" })

C. GitHub search for community servers:

WebSearch({ query: "site:github.com {service name} MCP server" })

Read the full file on GitHub · 338 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 12d ago First seen · 338 lines · 32 tokens per session scan C 09aed378c219

Subscribe to this mod's changes

Discover Tools is a skill published in the GitHub repository yuchenbigpen1/normies (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 3,007 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.