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 vaisala-xweather/xweather-agent-skills --skill webhooksgit clone --depth 1 https://github.com/vaisala-xweather/xweather-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/vaisala-xweather/xweather-agent-skills/webhooks)<a href="https://agentmods.dev/skills/vaisala-xweather/xweather-agent-skills/webhooks"><img src="https://agentmods.dev/badge/skills/vaisala-xweather/xweather-agent-skills/webhooks/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/vaisala-xweather/xweather-agent-skills/webhooks"><img src="https://agentmods.dev/badge/skills/vaisala-xweather/xweather-agent-skills/webhooks.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 | $0.00144 | $0.02907 |
| Opus 5.5 | $0.00058 | $0.01163 |
| Sonnet 5.5 | $0.00029 | $0.00581 |
| Haiku 4.5 | $0.00014 | $0.00291 |
Grade A, and why
webhooks 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 16d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xweather Webhooks
Xweather pushes data sets to an HTTPS endpoint you own, instead of your application polling
data.api.xweather.com on a timer. The payload is byte-for-byte the same shape the Weather API
returns, so existing response-parsing code is reusable with almost no change.
Webhooks are a premium add-on requiring a separate subscription, and endpoints are registered by Xweather staff — not self-service. There is no API call or dashboard toggle that turns this on. Say so early: the work splits into what the user can build today (the receiver) and what needs a conversation with their account executive (the subscription and registration).
When webhooks are the right answer
Reach for them when the user is polling frequently for data that changes unpredictably — lightning strikes, hail threats, new alerts, storm cell updates. Polling that on a short interval burns accesses continuously and still adds latency; push removes both problems.
Polling via the weather-api skill stays the better fit when the data is requested on
demand (a user opens a page), when the update cadence is slow and predictable (daily normals, hourly
temperatures), or when the user can't host a public HTTPS endpoint.
How a delivery works
Xweather sends an HTTP POST to the registered URL.
| Method | POST |
Content-Type |
application/json |
x-api-key |
A client-generated shared secret, proving the delivery came from Xweather. May be a query parameter instead of a header, if preferred. |
| Body | The standard Xweather API response envelope — JSON or GeoJSON, whichever was configured |
The endpoint must answer with a 2xx status — 202 is the conventional choice — and do it
immediately. The response body is ignored.
Acknowledge first, process second. Any real work belongs in a background job, queue, or thread started after the status is written. A handler that parses, matches polygons, and sends notifications before responding will eventually exceed the delivery timeout, and a timeout is treated as a failed delivery.
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.
- 16d ago Changed 7383b98cd258
- 18d ago Changed 98176077ffe5
- 29d ago Changed d1ed32d241ef
- 1mo ago Changed 3c898003d0ec
- 1mo ago Changed f8eb14cc1e65
- 2mo ago Changed 02ae81cebf2b
- 2mo ago First seen · 244 lines · 144 tokens per session scan A cd843808fae1
webhooks is a skill published in the GitHub repository vaisala-xweather/xweather-agent-skills (6 stars, last pushed 16d ago), licensed MIT. It adds 144 tokens to every session and 2,907 once invoked, about $0.0006 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.
webhooks compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| webhooksvaisala-xweather/xweather-agent-skills | Skill | 6 | 16d ago | MIT | A | 144 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | 5d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | today | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 579 | yesterday | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 257 | 2d ago | MIT | A | 106 | Claude Code |