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 youdotcom-oss/agent-skills --skill you-discovergit clone --depth 1 https://github.com/youdotcom-oss/agent-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/youdotcom-oss/agent-skills/you-discover)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00074 | $0.01266 |
| Opus 5.5 | $0.00030 | $0.00506 |
| Sonnet 5.5 | $0.00015 | $0.00253 |
| Haiku 4.5 | $0.00007 | $0.00127 |
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 25d 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 — 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 keyless You.com discover MCP profile exposes
you-discoverathttps://api.you.com/mcp?profile=discover(noYDC_API_KEYor OAuth required). - Check whether the You.com Docs MCP tool
searchDocsis available athttps://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_serversfield 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-discoverand Docs MCP are available, enter the planning loop: useyou-discoverto 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-discoverto search You.com's AI Catalog, and any catalogs it links to when supported, for resources that match the target task. - Use
searchDocsto verify official You.com docs for API References, MCP setup, Python SDK, auth, and install commands. - Compare available
you-discoverresults 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. For a keyless direct x402 REST client (no API key, pay USDC on Base), see x402 direct client.
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.
- 25d ago Changed · +49 tokens per session 34b71397dcc9
- 1mo ago Changed 21bb2c28a969
- 1mo ago First seen · 71 lines · 25 tokens per session scan A 8d005d6c93ef
you-discover is a skill published in the GitHub repository youdotcom-oss/agent-skills (94 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 1,266 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
MeiGen
Compose MeiGen image/video and five dedicated image tools inside an existing workflow, or opt into creative planning. Preserves caller prompts, parameters, approved count and budget; includes discovery and recoverable task handles.
MeiGen Visual Creative Expert
Optional visual planning assistant. Use when the user asks MeiGen to develop a creative idea, explore visual directions, improve a prompt, or build a mood board. An existing upstream script, prompt, model choice or generation plan can call MeiGen tools directly without activating this creative workflow.
Product Photoshoot Workflow
A workflow for turning one product photo into a set of four e-commerce images from different visual directions.
Social Thumbnail Workflow
A workflow for creating vertical images for short-video platforms and mobile social feeds, where content is usually viewed in a 9:16 portrait layout.
last30days-cn
A research workflow for studying the past 30 days of content on eight Chinese platforms, including Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu, and Toutiao.
last30days-cn
A research workflow for studying the past 30 days of content on eight Chinese platforms, including Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu, and Toutiao.