triggers

triggers is a skill for Claude Code, Codex from unclutter-pro/atlas. It costs 28 tokens per session (4,721 once invoked), scanned B, original, MIT.

A system for starting separate agent sessions when events happen. Events can follow a schedule, arrive through an HTTP webhook, or be started manually; integrations include Signal, WhatsApp, and email.

In plain words
What is it for?
Use it to run scheduled jobs, receive events from services such as GitHub or Stripe, or start an agent session from the web interface or command line.
Why use it?
It removes the need to start routine agent work by hand and can pass incoming event data into the agent's instructions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/agent/secrets/email-password.

Good fit Use it to run scheduled jobs, receive events from services such as…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 triggers

README.md
[![agentmods](https://agentmods.dev/badge/skills/unclutter-pro/atlas/triggers.svg)](https://agentmods.dev/skills/unclutter-pro/atlas/triggers)
Your own site
<a href="https://agentmods.dev/skills/unclutter-pro/atlas/triggers"><img src="https://agentmods.dev/badge/skills/unclutter-pro/atlas/triggers.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,721 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00028 $0.04721
Opus 5 $0.00014 $0.02361
Sonnet 5 $0.00006 $0.00944
Haiku 4.5 $0.00003 $0.00472

Measured 6d ago against content hash 08d08f1f53d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

triggers scanned grade B with 2 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 6d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 /home/agent/secrets/email-password

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL "https://github.com/AsamK/signal-cli/releases/download/v${SIGNAL_VERSION}/signal-cli-${SIGNAL_VERSION}-Linux-${ARCH}.tar.gz" \
app/defaults/skills/triggers/SKILL.md · 633 lines

How it starts

The opening of the file, as written. The whole thing — 633 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triggers

Triggers are autonomous agent sessions that fire on events — scheduled (cron), HTTP (webhook), or on-demand (manual). Each trigger runs its own Claude session that can handle the event directly or escalate to the main session.

Trigger Types

Cron

Scheduled execution using standard cron syntax.

Schedule Meaning
*/15 * * * * Every 15 minutes
0 * * * * Every hour
0 9 * * 1-5 Weekdays at 9:00
0 6 * * * Daily at 6:00

Webhook

Webhooks connect external services to the agent via a self-hosted relay (smee.io). No ports need to be opened — the agent connects outbound via SSE.

How it works:

  1. trigger create --type=webhook generates a unique channel and returns the relay URL
  2. Register that URL with your external service (GitHub, Stripe, etc.)
  3. The webhook SSE listener connects outbound and fires triggers when events arrive
  • Payload replaces {{payload}} in the prompt file
  • Optional authentication via X-Webhook-Secret header or middleware filter
  • Relay URL configurable in config.yml (default: webhooks.unclutter.pro)

Manual

No schedule, no endpoint. Fired via the web-ui "Run" button or by request.

Session Modes

Mode Behavior Use Case
ephemeral New session per run Cron jobs, one-off webhooks
persistent Resume by session key Signal/WhatsApp contacts, email threads

Persistent triggers maintain separate sessions per key (e.g., per contact, per thread). If no key is provided, a single default session is used per trigger.

CLI Commands

Command Use
trigger create ... Create trigger
trigger update ... Update trigger fields
trigger delete --name=foo Delete trigger
trigger enable --name=foo Enable trigger
trigger disable --name=foo Disable trigger
trigger list List all triggers

Creating Triggers

Cron Trigger

trigger create \
  --name=daily-report \
  --type=cron \
  --schedule="0 9 * * *" \
  --description="Daily morning report" \
  --channel=internal

Read the full file on GitHub · 633 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. 6d ago First seen · 633 lines · 28 tokens per session scan B 08d08f1f53d9

Subscribe to this mod's changes

triggers is a skill published in the GitHub repository unclutter-pro/atlas (2 stars, last pushed 18d ago), licensed MIT. It adds 28 tokens to every session and 4,721 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens