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 tealight-uk/u301-mcp --skill u301-url-shortenergit clone --depth 1 https://github.com/tealight-uk/u301-mcpWrote 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/tealight-uk/u301-mcp/u301-url-shortener)<a href="https://agentmods.dev/skills/tealight-uk/u301-mcp/u301-url-shortener"><img src="https://agentmods.dev/badge/skills/tealight-uk/u301-mcp/u301-url-shortener/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/tealight-uk/u301-mcp/u301-url-shortener"><img src="https://agentmods.dev/badge/skills/tealight-uk/u301-mcp/u301-url-shortener.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 | $0.00020 | $0.00474 |
| Opus 5.5 | $0.00008 | $0.00190 |
| Sonnet 5.5 | $0.00004 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
U301 URL Shortener 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 2mo 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.
What it actually says
U301 SKILL
Use this skill to keep the repository's runtime behavior, MCP-facing contract, and user-facing setup instructions in sync.
Quick Start
Read these files before changing behavior:
README.mdpackage.jsonsrc/index.ts
Treat this repository as a small, single-tool stdio MCP server. Prefer minimal, contract-preserving edits unless the user explicitly asks for broader changes.
Core Workflow
If not already authenticated, ask the user to provide a valid U301_API_KEY
Set U301_API_KEY as an env var.
Optional defaults: DOMAIN, WORKSPACE_ID.
Always call the U301 API (no heuristics, no caching).
If the token is missing, give the user these steps:
Create a U301 API KEY: https://u301.com/app/api-key Set U301_API_KEY as an environment variable in their system. Never ask the user to paste the full token in chat. Ask them to set it locally and confirm when ready.
- Classify the task as either usage/setup help or repository maintenance.
- For usage/setup help, explain the current contract exactly as implemented:
- Required env var:
U301_API_KEY - Optional env vars:
DOMAIN,WORKSPACE_ID - Package entrypoint:
npx -y @u301/mcp - MCP tool:
u301_shortening_urls_in_bulk - Accepted item fields:
url,slug,expiredAt,password,comment
- Required env var:
- For repository maintenance, update the same behavior in every place it is represented:
- Zod input schema in
src/index.ts - Tool description text in
src/index.ts - Request body mapping in
src/index.ts - README examples and parameter documentation
- Zod input schema in
- Preserve current behavior unless the user asks to change it:
- Reject empty input
- Reject batches over 200 URLs
- Return formatted plain-text results with
---separators
Typical Requests
Use this skill for requests such as:
- "Shorten the following URLs: https://www.google.com, https://www.bing.com"
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.
- 2mo ago First seen · 55 lines · 20 tokens per session scan A 6201fa84d1db
U301 URL Shortener is a skill published in the GitHub repository tealight-uk/u301-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 20 tokens to every session and 474 once invoked, about $0.0001 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 2026-08-31.
U301 URL Shortener compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| U301 URL Shortenertealight-uk/u301-mcp | Skill | 0 | 8mo ago | MIT | A | 20 | Claude Code, Codex |
| ai-first-pastebinjoustonhuang/ai-first-pastebin | Skill | 0 | 6mo ago | MIT | A | 116 | Claude Code, Codex |
| picsee-short-linkPicSeeInc/picsee-short-link | Skill | 2 | 3mo ago | none | C | 93 | Claude Code, Codex |
| opik-diagnosecomet-ml/opik-mcp | Skill | 226 | 2d ago | Apache-2.0 | A | 187 | Claude Code |
| ue-mcp-epic-routingdb-lyon/ue-mcp | Skill | 480 | yesterday | MIT | A | 81 | Claude Code, Codex |
| qa-knowledgegriddynamics/rosetta | Skill | 373 | today | Apache-2.0 | A | 32 | Claude Code, Codex |
| apitapn1byn1kt/apitap | Skill | 131 | 18d ago | Apache-2.0 | A | 0 | Claude Code, Codex |