event-triggers

event-triggers is a skill for Claude Code, Codex from Cloudgeni-ai/opengeni. It costs 61 tokens per session (1,788 once invoked), scanned A, original, Apache-2.0.

An event-trigger setup runs work when something happens in another app, such as a new pull request, message, email, issue, or MCP event. An event is a notification from a connected service that something changed.

In plain words
What is it for?
Use it for automations that react to events from connected apps. It helps set up actions for events such as opened pull requests, Slack messages, emails, Linear issues, or meeting events.
Why use it?
It removes the need to repeatedly check for changes or use a scheduled polling workaround. You can choose the narrowest event type and, when needed, wake this chat only once.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for automations that react to events from connected apps. It helps set up actions for events such as opened pull requests, Slack messages, emails, Linear issues, or meeting events.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cloudgeni-ai/opengeni/event-triggers
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 Cloudgeni-ai/opengeni --skill event-triggers
Clone the repo
git clone --depth 1 https://github.com/Cloudgeni-ai/opengeni

Made for: Claude Code, Codex.

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.

agentmods badge for event-triggers

README.md
[![agentmods](https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/event-triggers/github.svg)](https://agentmods.dev/skills/cloudgeni-ai/opengeni/event-triggers)
Your own site
<a href="https://agentmods.dev/skills/cloudgeni-ai/opengeni/event-triggers"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/event-triggers/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.

agentmods 80×15 button for event-triggers

Your own site · 80×15
<a href="https://agentmods.dev/skills/cloudgeni-ai/opengeni/event-triggers"><img src="https://agentmods.dev/badge/skills/cloudgeni-ai/opengeni/event-triggers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,788 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.01788
Opus 5.5 $0.00024 $0.00715
Sonnet 5.5 $0.00012 $0.00358
Haiku 4.5 $0.00006 $0.00179

Measured 7d ago against content hash 15da60e2dde1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

event-triggers 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 7d 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.

packages/runtime/src/bundled_schedule_skills/event-triggers/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

React to events

An automation (a scheduled task) can run when an event arrives, instead of or as well as on a schedule. Each run receives the events that caused it, listed after its instructions.

Find the source and event type

  1. event_sources_list lists the sources you can use, and under readyToAdd the ones that need no setup: MCP servers the user is signed in to that offer events, their Gmail, and This workspace for meetings. A readyToAdd id works wherever a source id does; the user's source is added the first time it is used. If the app the user means is in neither list and it sends webhooks, add it yourself with event_sources_create_webhook (below). A person adds GitHub and Slack sources in Automations. Do not build a workaround such as polling on a schedule unless they ask for one.
  2. event_sources_list with a sourceId lists that source's event types and the fields conditions can match. Pick the narrowest type, for example pull_request.opened rather than every pull request event.

Add a webhook source

event_sources_create_webhook adds any app that sends JSON webhooks. Pass preset for linear, sentry or tailscale. For any other app, read its webhook docs and write format:

  • signature, how the app proves a delivery is its own:
    • { "scheme": "standard_webhooks" }: webhook-id, webhook-timestamp and webhook-signature headers with a whsec_ secret (Svix-based apps).
    • { "scheme": "hmac_sha256", "header": "X-Hub-Signature-256", "prefix": "sha256=" }: an HMAC-SHA256 of the body, "encoding": "hex" (default) or "base64". When the app signs more than the body, add signedContent, such as "v0:{header:X-Request-Timestamp}:{body}".
    • { "scheme": "timestamped_hmac_sha256", "header": "Stripe-Signature" }: a t=…,v1=… header over <t>.<body>.
    • { "scheme": "token", "header": "X-Gitlab-Token" }: the secret itself in a header, after an optional prefix such as "Bearer ".
    • { "scheme": "ed25519", "header": "X-Signature-Ed25519", "signedContent": "{header:X-Signature-Timestamp}{body}" }: the secret is the app's public key.
    • { "scheme": "url_token" } only for an app that can't sign at all: the secret goes in the address as ?token=… (parameter renames it).
  • type, the event type: { "path": "type" }, { "header": "X-Event-Key" }, { "value": "page.changed" } when every delivery is the same, or { "parts": [{ "header": "X-Resource" }, { "path": "action" }] }, joined with ..
  • Optional: deliveryId (a header or path) so retries are kept once; eventId, each event's own id so an event sent again runs once (a path, a list of paths, or parts joined like type, such as an alert's status, fingerprint and startsAt; an event missing a part has no id); occurredAt; summary, subject, url and actor (a path, or a list of paths where the first with text wins); actorKind, such as { "path": "actor.type", "person": ["user"] }; freshness, such as { "header": "X-Timestamp", "toleranceSeconds": 300 }, when the app sends a timestamp, so old deliveries can't be sent again; batch ({} or { "path": "events" }) when one delivery holds a list of events.

Read the full file on GitHub · 123 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.

  1. 7d ago Changed · +51 lines 15da60e2dde1
  2. 11d ago First seen · 72 lines · 61 tokens per session scan A 5528e5e35d89

Subscribe to this mod's changes

event-triggers is a skill published in the GitHub repository Cloudgeni-ai/opengeni (216 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 1,788 once invoked, about $0.0002 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 2026-10-26.

Related

event-triggers compared with skills from other repositories

event-triggers next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
event-triggersCloudgeni-ai/opengeniSkill216todayApache-2.0A61Claude Code, Codex
output-meta-project-contextgrowthxai/outputSkill4444d agoApache-2.0A54Claude Code
output-dev-eval-testinggrowthxai/outputSkill4444d agoApache-2.0A47Claude Code
output-eval-error-analysisgrowthxai/outputSkill4444d agoApache-2.0A38Claude Code
output-build-workflowgrowthxai/outputSkill4444d agoApache-2.0A52Claude Code
output-dev-create-skeletongrowthxai/outputSkill4444d agoApache-2.0A35Claude Code
output-dev-folder-structuregrowthxai/outputSkill4444d agoApache-2.0A31Claude Code