What is you-discover?

An integration-planning guide for connecting You.com to an agent SDK, IDE, automation platform, or other developer tool. It checks available connection and documentation resources before recommending setup steps.

Use it to plan and verify You.com integrations with tools such as agent frameworks, coding environments, and automation systems.

It reduces guesswork when deciding which You.com resource to use and what access or installation is required.

you-discover — Skill for Claude Code by youdotcom-oss

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 youdotcom-oss/agent-skills --skill you-discover

Clone the repo

git clone --depth 1 https://github.com/youdotcom-oss/agent-skills

Made for: Claude Code.

Or install you, the plugin that ships this one along with the rest of its 8 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/youdotcom-oss/agent-skills/you-discover/github.svg)](https://agentmods.dev/skills/youdotcom-oss/agent-skills/you-discover)

Your own site

<a href="https://agentmods.dev/skills/youdotcom-oss/agent-skills/you-discover"><img src="https://agentmods.dev/badge/skills/youdotcom-oss/agent-skills/you-discover/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/youdotcom-oss/agent-skills/you-discover"><img src="https://agentmods.dev/badge/skills/youdotcom-oss/agent-skills/you-discover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,170 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 5 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Agent Snooping · line 3
Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
medium Data Exfiltration · line 7
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
medium Data Exfiltration · line 20
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
medium Data Exfiltration · line 48
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
medium Excessive Agency · line 22
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.01170
Opus 5	$0.00013	$0.00585
Sonnet 5	$0.00005	$0.00234
Haiku 4.5	$0.00003	$0.00117

Measured 10d ago against content hash 8d005d6c93ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

you-discover 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 10d 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.

skills/you-discover/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You.com Discovery

Use this skill while planning how to integrate You.com with an agent SDK, IDE, automation platform, MCP client, API script, or other developer tool.

Required resources

Check whether the standard You.com MCP server exposes you-discover at https://api.you.com/mcp.
Check whether the You.com Docs MCP tool searchDocs is available at https://you.com/docs/_mcp/server.
If either server is missing, connect or install the missing MCP server(s): provide the server name, URL, and auth requirement from the metadata.mcp_servers field in the frontmatter above; point to the MCP setup mechanism for the current agent or MCP client; do not connect or install or modify configuration without approval.
Once both you-discover and Docs MCP are available, enter the planning loop: use you-discover to explore candidate resources for the target, draft a plan naming the selected resource and why it fits, then return to Docs MCP to verify auth, install, and setup steps before recommending.

Discovery workflow

Restate the integration target, for example "Pi", "OpenCode", "LangChain", "Vercel AI SDK", "Claude", or "Cursor".
When available, use you-discover to search You.com's AI Catalog, and any catalogs it links to when supported, for resources that match the target task.
Use searchDocs to verify official You.com docs for API References, MCP setup, Python SDK, auth, and install commands.
Compare available you-discover results and docs, then recommend the smallest integration path.
If no discovered resource fits, recommend a small direct API script or thin MCP bridge rather than reimplementing catalog crawling in the skill.

When planning paid direct API or MCP integrations, keep payment protocol guidance endpoint-specific: search and contents use x402 for keyless paid retries, while research and finance research can use MPP or x402.

Planning loop

Use you-discover and Docs MCP as part of the integration planning loop, not as a one-time preflight check:

Read the full file on GitHub · 71 lines

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.

10d ago First seen · 71 lines · 25 tokens per session scan A 8d005d6c93ef

Subscribe to this mod's changes

you-discover is a skill published in the GitHub repository youdotcom-oss/agent-skills (67 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 1,170 once invoked, about $0.0001 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.

Building agents agent-skills ai-agents ai-integration content-extraction developer-tools mcp-server

object-modify

Modify a Unity UnityEngine.Object's serializable fields/properties. Three modification surfaces are available (objectDiff, pathPatches, jsonPatch) — see the skill body. Use 'object-get-data' first to inspect the object structure.

IvanMurzak/Unity-MCP · 57 tokens

assets-get-data

Get asset data from the asset file in the Unity project — every serializable field and property. Supports token-saving path-scoped reads via paths or viewQuery. Use 'assets-find' to find the asset first.

IvanMurzak/Unity-MCP · 50 tokens

editor-selection-get

Get information about the current Selection in the Unity Editor — active object, active transform, selected GameObjects, transforms, instance IDs, and asset GUIDs (each enrichment is opt-in). Pair with 'editor-selection-set' to change the selection.

IvanMurzak/Unity-MCP · 53 tokens

gameobject-create

Create a new GameObject in the currently opened Prefab or active Scene, optionally parented under another GameObject and pre-positioned. Pass primitiveType to spawn a Unity primitive (Cube, Sphere, etc.) instead of an empty GameObject.

IvanMurzak/Unity-MCP · 55 tokens

object-get-data

Get serialized data for a Unity UnityEngine.Object — all serializable fields and properties. Supports token-saving path-scoped reads via paths or viewQuery. Pair with 'object-modify' when you need to write back.