inngest-steps

inngest-steps is a skill for Claude Code from inngest/inngest-skills. It costs 130 tokens per session (2,729 once invoked), scanned A, original, no licence file.

Step-handling guidance for Inngest workflows, where individual steps can pause, retry, wait, or call other functions while keeping their progress. It covers waits that remain scheduled even if the process restarts.

In plain words
What is it for?
Use it for delayed reminders, cart-abandonment messages, approval gates, webhook callbacks, external API polling, and calls between functions.
Why use it?
It prevents delayed tasks, polls, and approval waits from losing their place during restarts. It also makes it possible to pause a workflow until a person or external service responds.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the inngest-skills plugin — 10 skills shipped together

Good fit Use it for delayed reminders, cart-abandonment messages, approval gates, webhook callbacks, external API polling, and calls between functions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/inngest/inngest-skills/inngest-steps
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 inngest/inngest-skills --skill inngest-steps
Clone the repo
git clone --depth 1 https://github.com/inngest/inngest-skills

Made for: Claude Code.

Or install inngest-skills, the plugin that ships this one along with the rest of its 10 skills.

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 inngest-steps

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/inngest/inngest-skills/inngest-steps"><img src="https://agentmods.dev/badge/skills/inngest/inngest-skills/inngest-steps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,729 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. Third-party audits
  • Socket pass 7 May 2026
  • Snyk pass 7 May 2026
How audits are shown
Origin unknown 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 $0.00130 $0.02729
Opus 5 $0.00065 $0.01365
Sonnet 5 $0.00026 $0.00546
Haiku 4.5 $0.00013 $0.00273

Measured 12d ago against content hash 8745ab2abccd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

inngest-steps 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 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.

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.

skills/inngest-steps/SKILL.md · 367 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. 12d ago First seen · 367 lines · 130 tokens per session scan A 8745ab2abccd

Subscribe to this mod's changes

inngest-steps is a skill published in the GitHub repository inngest/inngest-skills (28 stars, last pushed 2mo ago), with no licence file. It adds 130 tokens to every session and 2,729 once invoked, about $0.0006 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

apideck-best-practices

Best practices for building Apideck integrations. Covers authentication patterns, pagination, error handling, connection management with Vault, webhook setup, and common pitfalls. Use when designing or reviewing any Apideck integration regardless of language.

apideck-libraries/api-skills · 52 tokens

apideck-mcp

Front-door skill for the Apideck MCP server — 330 unified-API tools across 10 domains plus 4 intent-grouped workflow tools, exposed via dynamic discovery. Use when the user is building an MCP-based agent (Claude Code, OpenAI Agents SDK, Pydantic AI, LangChain) and wants to integrate with any of the 200+ SaaS…

apideck-libraries/api-skills · 118 tokens

apideck-node

Apideck Unified API integration patterns for TypeScript and Node.js. Use when building integrations with accounting software (QuickBooks, Xero, NetSuite), CRMs (Salesforce, HubSpot, Pipedrive), HRIS platforms (Workday, BambooHR), file storage (Google Drive, Dropbox, Box), ATS systems (Greenhouse, Lever), e-commerce…

apideck-libraries/api-skills · 119 tokens

apideck-portman

API contract testing with Portman by Apideck. Use when generating Postman collections from OpenAPI specs, writing contract tests, variation tests, integration tests, fuzz testing, or setting up CI/CD API test pipelines. Portman converts OpenAPI 3.x specs into Postman collections with auto-generated test suites.

apideck-libraries/api-skills · 69 tokens

apideck-rest

Apideck Unified REST API reference for any language. Use when building integrations with accounting software (QuickBooks, Xero, NetSuite), CRMs (Salesforce, HubSpot, Pipedrive), HRIS platforms (Workday, BambooHR), file storage (Google Drive, Dropbox, Box), ATS systems (Greenhouse, Lever), e-commerce, or any of…

apideck-libraries/api-skills · 143 tokens

apideck-unified-api

Apideck Unified API — one set of methods for 146+ SaaS connectors across CRM (21 connectors), Accounting (34), HRIS (58), ATS (11), File Storage (5), Issue Tracking (6), and Ecommerce (17). Route to Salesforce, HubSpot, QuickBooks, Xero, NetSuite, BambooHR, Workday, Greenhouse, SharePoint, Google Drive, Jira, Shopify…

apideck-libraries/api-skills · 167 tokens