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 yuchenbigpen1/normies --skill discover-toolsgit clone --depth 1 https://github.com/yuchenbigpen1/normiesWrote 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/yuchenbigpen1/normies/discover-tools)<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.
<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>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 | $0.00032 | $0.03007 |
| Opus 5 | $0.00016 | $0.01503 |
| Sonnet 5 | $0.00006 | $0.00601 |
| Haiku 4.5 | $0.00003 | $0.00301 |
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 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" })
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.
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 · 338 lines · 32 tokens per session scan C 09aed378c219
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.
Other skills, from other repositories
[object Object]
Skill "[object Object]" from microsoft/apm, covering what this package does, getting started, available primitives and included workflows.
apm-usage
Activate when the user asks about APM (Agent Package Manager): installing, configuring, authoring, or troubleshooting AI-agent packages, dependencies, compilation, MCP servers, policy, or any apm CLI command.
frontend-state-management
SocialApp user frontend state management — TanStack Query, Zustand, IndexedDB persistence, cache invalidation, multi-account isolation.
dev-orchestrator
Full-stack development orchestrator -- always-on, 16 phases (0-15): read-docs -> understand -> architect -> pseudocode -> plan -> contract -> validate -> implement -> evaluate -> verify -> test -> goals -> review -> critic -> document -> report.
bot-reviewer
Review chat bot code (Telegram, Discord, Slack) for callback safety, state machines, rate limits, and production readiness.
silent-failure-hunter
Detects swallowed errors, empty catch blocks, log-and-forget patterns, and fallback masks that hide failures. Zero tolerance for silent failures. Severity-graded output with concrete fixes per language.