Agent skill

Inngest Steps

by Asymmetric-al in Asymmetric-al/core

A skill your agent uses when implementing delays that must survive process restarts (e.g., 24-hour cart abandonment, scheduled follow-ups), waiting for human approval or external events with…

AGPL-3.0Auto-check passedBackend & APIs

Install Inngest Steps

skills CLI
$ npx skills add Asymmetric-al/core --skill inngest-steps -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Asymmetric-al/core inngest-steps --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Asymmetric-al/core.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/inngest-steps .claude/skills/inngest-steps && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
inngest-steps
GitHub stars
381
Token cost
~3.2k tokens
SKILL.md length
702 words
Files
1
Skills in repo
43
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses when implementing delays that must survive process restarts (e.g., 24-hour cart abandonment, scheduled follow-ups), waiting for human approval or external events with…

  • Works in 4 steps: Confirm whether the request is… → Use inngest-brownfield-audit before… → Follow this upstream guidance under… → …
  • Implementing delays that must survive process restarts (e.g.
  • SKILL.md covers Core Concept, step.run(), step.sleep() and step.sleepUntil(), plus 11 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Inngest Steps is an agent skill from Asymmetric-al/core. Use when implementing delays that must survive process restarts (e.g., 24-hour cart abandonment, scheduled follow-ups), waiting for human approval or external events with timeouts (review gates, webhook callbacks, async API completion), polling external services without losing state on crashes, calling other functions and awaiting their results, memoizing expensive operations so they don't re-run on retry, or running async work in parallel inside a workflow. Covers Inngest step methods: step.run, step.sleep…

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Human-in-the-loop approvals and Webhooks. The repository describes itself as: A high-performance, enterprise-grade Next.js 16 application for mission-focused non-profit organizations. Built for high impact teams. The licence is AGPL-3.0.

When your agent uses it

  • Implementing delays that must survive process restarts (e.g.
  • 24-hour cart abandonment
  • Scheduled follow-ups)
  • Waiting for human approval

Example prompts

  • “/inngest-steps”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Confirm whether the request is agent-tooling guidance or product runtime
  2. Use inngest-brownfield-audit before changing existing app workflows or
  3. Follow this upstream guidance under OpenSpec, root AGENTS.md, repo
  4. Keep runtime packages, app code, migrations, and INNGEST_* env

What it can do on your machine

Read from SKILL.md and the folder at commit c30c8ff. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • inngest.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Inngest Steps loads about 3.2k tokens when it runs. Until then it costs about 163 tokens; SKILL.md has 702 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~163
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Asymmetric-al/core at commit c30c8ff, republished under its AGPL-3.0 licence (© Asymmetric-al). 702 words, ~3,177 tokens.

Download SKILL.mdSave it as .claude/skills/inngest-steps/SKILL.md (or your agent's skills folder).
name
inngest-steps
description
Use when implementing delays that must survive process restarts (e.g., 24-hour cart abandonment, scheduled follow-ups), waiting for human approval or external events with timeouts (review gates, webhook callbacks, async API completion), polling external services without losing state on crashes, calling other functions and awaiting their results, memoizing expensive operations so they don't re-run on retry, or running async work in parallel inside a workflow. Covers Inngest step methods: step.run, step.sleep, step.waitForEvent, step.waitForSignal, step.sendEvent, step.invoke, step.ai, plus patterns for loops and parallel execution.

Inngest Steps

Build robust, durable workflows with Inngest's step methods. Each step is a separate HTTP request that can be independently retried and monitored.

These skills are focused on TypeScript. For Python or Go, refer to the Inngest documentation for language-specific guidance. Core concepts apply across all languages.

Core Concept

🔄 Critical: Each step re-runs your function from the beginning. Put ALL non-deterministic code (API calls, DB queries, randomness) inside steps, never outside.

📊 Step Limits: Every function has a maximum of 1,000 steps and 4MB total step data.

typescript
// ❌ WRONG - will run 4 times
export default inngest.createFunction(
  { id: "bad-example", triggers: [{ event: "test" }] },
  async ({ step }) => {
    console.log("This logs 4 times!"); // Outside step = bad
    await step.run("a", () => console.log("a"));
    await step.run("b", () => console.log("b"));
    await step.run("c", () => console.log("c"));
  },
);

// ✅ CORRECT - logs once each
export default inngest.createFunction(
  { id: "good-example", triggers: [{ event: "test" }] },
  async ({ step }) => {
    await step.run("log-hello", () => console.log("hello"));
    await step.run("a", () => console.log("a"));
    await step.run("b", () => console.log("b"));
    await step.run("c", () => console.log("c"));
  },
);

step.run()

Execute retriable code as a step. Each step ID can be reused - Inngest automatically handles counters.

typescript
// Basic usage
const result = await step.run("fetch-user", async () => {
  const user = await db.user.findById(userId);
  return user; // Always return useful data
});

// Synchronous code works too
const transformed = await step.run("transform-data", () => {
  return processData(result);
});

// Side effects (no return needed)
await step.run("send-notification", async () => {
  await sendEmail(user.email, "Welcome!");
});

✅ DO:

  • Put ALL non-deterministic logic inside steps
  • Return useful data for subsequent steps
  • Reuse step IDs in loops (counters handled automatically)

❌ DON'T:

  • Put deterministic logic in steps unnecessarily
  • Forget that each step = separate HTTP request

step.sleep()

Pause execution without using compute time.

typescript
// Duration strings
await step.sleep("wait-24h", "24h");
await step.sleep("short-delay", "30s");
await step.sleep("weekly-pause", "7d");

// Use in workflows
await step.run("send-welcome", () => sendEmail(email));
await step.sleep("wait-for-engagement", "3d");
await step.run("send-followup", () => sendFollowupEmail(email));

step.sleepUntil()

Sleep until a specific datetime.

typescript
const reminderDate = new Date("2024-12-25T09:00:00Z");
await step.sleepUntil("wait-for-christmas", reminderDate);

// From event data
const scheduledTime = new Date(event.data.remind_at);
await step.sleepUntil("wait-for-scheduled-time", scheduledTime);

step.waitForEvent()

🚨 CRITICAL: waitForEvent ONLY catches events sent AFTER this step executes.

  • ❌ Event sent before waitForEvent runs → will NOT be caught
  • ✅ Event sent after waitForEvent runs → will be caught
  • Always check for null return (means timeout, event never arrived)
typescript
// Basic event waiting with timeout
const approval = await step.waitForEvent("wait-for-approval", {
  event: "app/invoice.approved",
  timeout: "7d",
  match: "data.invoiceId", // Simple matching
});

// Expression-based matching (CEL syntax)
const subscription = await step.waitForEvent("wait-for-subscription", {
  event: "app/subscription.created",
  timeout: "30d",
  if: "event.data.userId == async.data.userId && async.data.plan == 'pro'",
});

// Handle timeout
if (!approval) {
  await step.run("handle-timeout", () => {
    // Approval never came
    return notifyAccountingTeam();
  });
}

✅ DO:

  • Use unique IDs for matching (userId, sessionId, requestId)
  • Always set reasonable timeouts
  • Handle null return (timeout case)
  • Use with Realtime for human-in-the-loop flows

❌ DON'T:

  • Expect events sent before this step to be handled
  • Use without timeouts in production
Expression Syntax

In expressions, event = the original triggering event, async = the new event being matched. See Expression Syntax Reference for full syntax, operators, and patterns.

step.waitForSignal()

Wait for unique signals (not events). Better for 1:1 matching.

typescript
const taskId = "task-" + crypto.randomUUID();

const signal = await step.waitForSignal("wait-for-task-completion", {
  signal: taskId,
  timeout: "1h",
  onConflict: "replace", // Required: "replace" overwrites pending signal, "fail" throws an error
});

// Send signal elsewhere via Inngest API or SDK
// POST /v1/events with signal matching taskId

When to use:

  • waitForEvent: Multiple functions might handle the same event
  • waitForSignal: Exact 1:1 signal to specific function run

step.sendEvent()

Fan out to other functions without waiting for results.

typescript
// Trigger other functions
await step.sendEvent("notify-systems", {
  name: "user/profile.updated",
  data: { userId: user.id, changes: profileChanges },
});

// Multiple events at once
await step.sendEvent("batch-notifications", [
  { name: "billing/invoice.created", data: { invoiceId } },
  { name: "email/invoice.send", data: { email: user.email, invoiceId } },
]);

Use when: You want to trigger other functions but don't need their results in the current function.

step.invoke()

Call other functions and handle their results. Perfect for composition.

typescript
const computeSquare = inngest.createFunction(
  { id: "compute-square", triggers: [{ event: "calculate/square" }] },
  async ({ event }) => {
    return { result: event.data.number * event.data.number };
  },
);

// Invoke and use result
const square = await step.invoke("get-square", {
  function: computeSquare,
  data: { number: 4 },
});

console.log(square.result); // 16, fully typed!

// For cross-app invocation (when you can't import the function directly):
import { referenceFunction } from "inngest";

const externalFn = referenceFunction({
  appId: "other-app",
  functionId: "other-fn",
});

const result = await step.invoke("call-external", {
  function: externalFn,
  data: { key: "value" },
});

Warning: v4 Breaking Change: String function IDs (e.g., function: "my-app-other-fn") are no longer supported in step.invoke(). Use an imported function reference or referenceFunction() for cross-app calls.

Great for:

  • Breaking complex workflows into composable functions
  • Reusing logic across multiple workflows
  • Map-reduce patterns

Patterns

Loops with Steps

Reuse step IDs - Inngest handles counters automatically.

typescript
const allProducts = [];
let cursor = null;
let hasMore = true;

while (hasMore) {
  // Same ID "fetch-page" reused - counters handled automatically
  const page = await step.run("fetch-page", async () => {
    return shopify.products.list({ cursor, limit: 50 });
  });

  allProducts.push(...page.products);

  if (page.products.length < 50) {
    hasMore = false;
  } else {
    cursor = page.products[49].id;
  }
}

await step.run("process-products", () => {
  return processAllProducts(allProducts);
});
Parallel Execution

Use Promise.all for parallel steps. In v4, parallel step execution is optimized by default

typescript
// Create steps without awaiting
const sendEmail = step.run("send-email", async () => {
  return await sendWelcomeEmail(user.email);
});

const updateCRM = step.run("update-crm", async () => {
  return await crmService.addUser(user);
});

const createSubscription = step.run("create-subscription", async () => {
  return await subscriptionService.create(user.id);
});

// Run all in parallel
const [emailId, crmRecord, subscription] = await Promise.all([
  sendEmail,
  updateCRM,
  createSubscription,
]);

// Parallel steps are optimized by default in v4
export default inngest.createFunction(
  {
    id: "parallel-heavy-function",
    triggers: [{ event: "process/batch" }],
  },
  async ({ event, step }) => {
    const results = await Promise.all(
      event.data.items.map((item, i) =>
        step.run(`process-item-${i}`, () => processItem(item)),
      ),
    );
  },
);

// ⚠️ Promise.race() behavior with v4's optimized parallelism:
// All promises settle before race resolves. Use group.parallel() for true race:
const winner = await group.parallel(async () => {
  return Promise.race([
    step.run("fast-service", () => callFastService()),
    step.run("slow-service", () => callSlowService()),
  ]);
});

// To disable optimized parallelism if needed:
// At the client level: new Inngest({ id: "app", optimizeParallelism: false })
// At the function level: { id: "fn", optimizeParallelism: false, triggers: [...] }

See inngest-flow-control for concurrency and throttling options.

Chunking Jobs

Perfect for batch processing with parallel steps.

typescript
export default inngest.createFunction(
  { id: "process-large-dataset", triggers: [{ event: "data/process.large" }] },
  async ({ event, step }) => {
    const chunks = chunkArray(event.data.items, 10);

    // Process chunks in parallel
    const results = await Promise.all(
      chunks.map((chunk, index) =>
        step.run(`process-chunk-${index}`, () => processChunk(chunk)),
      ),
    );

    // Combine results
    await step.run("combine-results", () => {
      return aggregateResults(results);
    });
  },
);
Show full SKILL.md (296 more words)Show less

Key Gotchas

🔄 Function Re-execution: Code outside steps runs on every step execution ⏰ Event Timing: waitForEvent only catches events sent AFTER the step runs 🔢 Step Limits: Max 1,000 steps per function, 4MB per step output, 32MB per function run in total 📨 HTTP Requests: Checkpointing is enabled by default in v4, reducing HTTP overhead. For serverless platforms, configure maxRuntime on the client 🔁 Step IDs: Can be reused in loops - Inngest handles counters ⚡ Parallelism: Use Promise.all for parallel steps (optimized by default in v4). Note that Promise.race() waits for all promises to settle — use group.parallel() for true race semantics

Common Use Cases

  • Human-in-the-loop: waitForEvent + Realtime UI
  • Multi-step onboarding: sleep between steps, waitForEvent for user actions
  • Data processing: Parallel steps for chunked work
  • External integrations: step.run for reliable API calls
  • AI workflows: step.ai for durable LLM orchestration
  • Function composition: step.invoke to build complex workflows

Remember: Steps make your functions durable, observable, and debuggable. Embrace them!

This Repository

These upstream Inngest instructions are vendored for agent tooling and integration work in this monorepo.

Repository Triggers

Use this skill when inngest-steps matches the current Inngest task. If the right skill is unclear, start with docs/ai/skills/inngest/SKILL.md.

Repository Workflow

  1. Confirm whether the request is agent-tooling guidance or product runtime integration.
  2. Use inngest-brownfield-audit before changing existing app workflows or fragile background work.
  3. Follow this upstream guidance under OpenSpec, root AGENTS.md, repo rulebooks, framework docs, and runtime evidence.
  4. Keep runtime packages, app code, migrations, and INNGEST_* env requirements out of agent-tooling-only changes.

Repository Checklist

  • The task has explicit product-runtime scope before adding Inngest app code or dependencies.
  • Existing workflows were audited before introducing or changing durable workflow behavior.
  • Any MCP usage is backed by a running Inngest dev server on the configured port.
  • Upstream source and license attribution remain documented in docs/ai/skills/inngest/references/upstream.md.

© Asymmetric-al, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/inngest-steps of Asymmetric-al/core.

Open the folder on GitHubat commit c30c8ff

Compare with similar skills

Inngest Steps next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Inngest Steps compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Inngest Steps this skillAsymmetric-al/core381—~3.2kAutomated safety check: PassAGPL-3.0
Build With SimplepdfSimplePDF/simplepdf-embed407—~7kAutomated safety check: PassMIT
Hitl ProtocolLeoYeAI/openclaw-master-skills2.2k—~5.3kAutomated safety check: PassApache-2.0
Zalo AgentPhucMPham/zalo-agent-cli166—~2.3kAutomated safety check: PassMIT
AWS Lambda Durable Functionsawslabs/agent-plugins916—~2.3kAutomated safety check: PassApache-2.0
GitLab MCP Skillzereight/gitlab-mcp2k—~2.2kAutomated safety check: PassMIT

Similar skills

  • Build With Simplepdf

    SimplePDF/simplepdf-embed

    Integrate SimplePDF into a web application for PDF viewing, editing, filling, signing, programmatic control, AI-agent interaction, human-in-the-loop form prefilling, submissions, webhooks, or…

    407 GitHub stars~7k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Hitl Protocol

    LeoYeAI/openclaw-master-skills

    HITL Protocol — the open standard for human decisions in autonomous agent workflows.

    2.2k GitHub stars~5.3k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Zalo Agent

    PhucMPham/zalo-agent-cli

    Automate Zalo messaging, Official Account (OA), and MCP server integration via zalo-agent-cli.

    166 GitHub stars~2.3k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • AWS Lambda Durable Functions

    awslabs/agent-plugins

    Official

    Build resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions.

    916 GitHub stars~2.3k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • GitLab MCP Skill

    zereight/gitlab-mcp

    A skill your agent uses when working with the GitLab MCP server tools for merge requests, issues, repositories, pipelines, work items, variables, dependency proxy, vulnerabilities, webhooks, search…

    2k GitHub stars~2.2k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • AWS Lambda Durable Functions

    aws/agent-toolkit-for-aws

    Official

    Builds resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions.

    2.8k GitHub stars~2.3k tokensUpdated yesterday
    Backend & APIsAuto-check passed

More from Asymmetric-al/core

All 43 skills in this repo
  • Idempotency Handling

    Asymmetric-al/core

    Implement idempotency keys and handling to ensure operations can be safely retried without duplicate effects.

    381 GitHub stars~867 tokensUpdated today
    Auto-check passed
  • Accessibility Review

    Asymmetric-al/core

    Audit and fix accessibility in Core UI. An agent skill from Asymmetric-al/core.

    381 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Email Inbox

    Asymmetric-al/core

    A skill your agent uses when building any system where email content triggers actions — AI agent inboxes, automated support handlers, email-to-task pipelines, or any workflow processing untrusted…

    381 GitHub stars~4.1k tokensUpdated today
    Auto-check: notes
  • Components Build

    Asymmetric-al/core

    Build modern, composable, and accessible React UI components following the components.build specification.

    381 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Create Agent

    Asymmetric-al/core

    Guides a one-question-at-a-time design interview, captures alignment in agent/EVE-BRIEF.md, then scaffolds and implements a runnable eve agent with verbose teaching comments.

    381 GitHub stars~2.6k tokensUpdated today
    Auto-check: notes
  • Emil Design Engineering

    Asymmetric-al/core

    Design engineering principles and patterns for building polished, accessible web interfaces.

    381 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Questions about Inngest Steps

What does Inngest Steps do?

A skill your agent uses when implementing delays that must survive process restarts (e.g., 24-hour cart abandonment, scheduled follow-ups), waiting for human approval or external events with…. Inngest Steps is an agent skill from Asymmetric-al/core., 24-hour cart abandonment, scheduled follow-ups), waiting for human approval or external events with timeouts (review gates, webhook callbacks, async API completion), polling external services without losing state on crashes, calling other functions and awaiting their results, memoizing expensive operations so they don't re-run on retry, or running async work in parallel inside a workflow.

When should I use Inngest Steps?

Inngest Steps fits situations like: implementing delays that must survive process restarts (e.g; 24-hour cart abandonment; scheduled follow-ups); waiting for human approval.

How do I install Inngest Steps in Claude Code?

Run `npx skills add Asymmetric-al/core --skill inngest-steps -a claude-code`. Or copy the skill folder (.agents/skills/inngest-steps in Asymmetric-al/core) into .claude/skills/inngest-steps in your project. Claude Code loads it when a task matches its description.

How do I install Inngest Steps in Codex?

Run `npx skills add Asymmetric-al/core --skill inngest-steps -a codex`. Or copy the skill folder (.agents/skills/inngest-steps in Asymmetric-al/core) into .agents/skills/inngest-steps in your project. Codex loads it when a task matches its description.

Can I use Inngest Steps in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Asymmetric-al/core --skill inngest-steps -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/inngest-steps, .gemini/skills/inngest-steps, .github/skills/inngest-steps and .opencode/skills/inngest-steps in your project.

What does Inngest Steps need to run?

SKILL.md names no scripts, command-line tools or credentials: Inngest Steps is instructions for the agent only. Our summary lists: Python 3.

Does Inngest Steps access the network?

SKILL.md names 1 domain. As links in the text: inngest.com. This is read from the text; nothing was executed.

Is Inngest Steps safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Inngest Steps use?

Inngest Steps is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Inngest Steps use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Inngest Steps?

Skills that share tags, products or a category with Inngest Steps: Build With Simplepdf (SimplePDF/simplepdf-embed, 407 stars), Hitl Protocol (LeoYeAI/openclaw-master-skills, 2.2k stars), Zalo Agent (PhucMPham/zalo-agent-cli, 166 stars) and AWS Lambda Durable Functions (awslabs/agent-plugins, 916 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Inngest Steps?

Asymmetric-al (a GitHub organization) maintains it in Asymmetric-al/core, which has 381 GitHub stars. The repository holds 43 skills in this directory. The repository was last updated on October 9, 2026.

Source: Asymmetric-al/core on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.