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 linhnguyen-gt/Routiform --skill routiform-cursor-setupgit clone --depth 1 https://github.com/linhnguyen-gt/RoutiformWrote 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/linhnguyen-gt/routiform/routiform-cursor-setup)<a href="https://agentmods.dev/skills/linhnguyen-gt/routiform/routiform-cursor-setup"><img src="https://agentmods.dev/badge/skills/linhnguyen-gt/routiform/routiform-cursor-setup/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/linhnguyen-gt/routiform/routiform-cursor-setup"><img src="https://agentmods.dev/badge/skills/linhnguyen-gt/routiform/routiform-cursor-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Prompt Injection · line 69 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00080 | $0.00846 |
| Opus 5 | $0.00040 | $0.00423 |
| Sonnet 5 | $0.00016 | $0.00169 |
| Haiku 4.5 | $0.00008 | $0.00085 |
Grade A, and why
routiform-cursor-setup scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s -o /dev/null -w '%{http_code}\n' https://your-domain.com/v1/models` → `200`. How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect Cursor to Routiform
Cursor has no config file to edit — the override lives in its settings UI. The part that trips people up is where the request comes from.
Read this before starting
http://localhost:20128 will not work. Cursor sends chat requests from its own servers, not
from your machine, so the base URL has to be reachable from the public internet. A localhost URL
fails Cursor's verification step with no useful error. This is a property of Cursor, not of
Routiform, and no amount of local configuration works around it.
You need one of:
- Routiform's Cloud Endpoint, enabled in Settings, which gives you a public URL;
- Routiform deployed on a host with a domain and TLS;
- a tunnel (Cloudflare Tunnel, ngrok) in front of your local instance.
Anything you expose this way is an authenticated endpoint holding provider credentials. Use a dedicated gateway key for Cursor so you can revoke it alone, and keep TLS on.
Prerequisites
- A Cursor Pro account. The custom-OpenAI-key path is a Pro feature.
- Routiform reachable at a public HTTPS URL. Confirm from somewhere that is not your machine:
curl -s -o /dev/null -w '%{http_code}\n' https://your-domain.com/v1/models→200. - At least one provider connection configured at
/dashboard/providers.
Steps
1. Create a gateway API key scoped to this use. Dashboard → API Manager, or:
routiform key create cursor
2. In Cursor: Settings → Models. Enable OpenAI API Key.
3. Set the base URL to your public Routiform URL with /v1:
https://your-domain.com/v1
4. Paste the gateway key into the API key field.
5. Add the model. Click View All Models → Add Custom Model and enter an id Routiform can
resolve — list them with
curl -H "Authorization: Bearer <key>" https://your-domain.com/v1/models. Cursor will not offer
Routiform's catalogue on its own; the model name has to match what Routiform routes.
6. Verify with Cursor's own button next to the key field. /dashboard/cli-tools walks the same
six steps with your live values filled in, if you would rather copy than type.
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 · 76 lines · 80 tokens per session scan A 32501a270066
routiform-cursor-setup is a skill published in the GitHub repository linhnguyen-gt/Routiform (12 stars, last pushed 5d ago), licensed MIT. It adds 80 tokens to every session and 846 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…