workflows

A system for running multi-step background processes that can keep their progress, retry failed steps, pause for human input, and continue after a restart.

In plain words
What is it for?
Use it for asynchronous processes, approval-based flows, reliable background jobs, long tasks, and API calls that must run in sequence.
Why use it?
It avoids losing progress or manually recovering when long-running jobs, approvals, or API calls fail or take time.

Skill for Claude CodeCodex

Part of the cloudflare plugin — 19 skills, 2 commands shipped together

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.

agentmods
npx agentmods add skills/null-shot/cloudflare-skills/workflows
Any agent
npx skills add null-shot/cloudflare-skills --skill workflows
Clone the repo
git clone --depth 1 https://github.com/null-shot/cloudflare-skills

Made for: Claude Code, Codex.

Or install cloudflare, the plugin that ships this one along with the rest of its 19 skills, 2 commands.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,518 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin fork From a forked repository.
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 $0.00049 $0.03518
Opus 5 $0.00024 $0.01759
Sonnet 5 $0.00010 $0.00704
Haiku 4.5 $0.00005 $0.00352

Measured 2d ago against content hash c13cfebf608a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflows scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

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

async fetch(req: Request, env: Env): Promise<Response> {
workflows/SKILL.md · 492 lines

How it starts

The opening of the file, as written. The whole thing — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cloudflare Workflows

Build durable, long-running workflows that survive restarts and handle retries automatically using Cloudflare Workflows.

When to Use

Workflows are ideal for:

  • Multi-step async tasks - Break complex processes into retriable steps
  • Human-in-the-loop workflows - Pause execution waiting for external input
  • Reliable background jobs - Automatic retries with exponential backoff
  • Long-running processes - Minutes to hours of execution with state persistence
  • Coordinated API calls - Chain multiple API calls with retry logic

Don't use Workflows for:

  • Simple request/response handlers (use Workers)
  • Real-time operations requiring <100ms response (use Workers)
  • Tasks that complete in <1 second (use Workers directly)

Quick Reference

Operation API
Define workflow class MyWorkflow extends WorkflowEntrypoint<Env, Params>
Execute step await step.do('name', async () => { ... })
Sleep/pause await step.sleep('wait', '1 minute')
Step with retries await step.do('name', { retries: { limit: 5 } }, async () => {})
Create instance await env.MY_WORKFLOW.create({ id, params })
Get instance await env.MY_WORKFLOW.get(id)
Check status await instance.status()

FIRST: wrangler.jsonc Configuration

Add workflow binding to your configuration:

{
  "name": "my-project",
  "main": "src/index.ts",
  "compatibility_date": "2025-02-11",
  "workflows": [
    {
      "name": "workflows-starter",
      "binding": "MY_WORKFLOW",
      "class_name": "MyWorkflow"
    }
  ]
}

Key points:

  • binding - Environment variable name to access workflow
  • class_name - Must match your exported Workflow class name exactly
  • Multiple workflows can be defined in the array

Critical Limits to Know

Per-Step State Limit: 1 MiB

  • Each step's return value must be under 1 MiB (1,048,576 bytes)
  • If exceeded, the step fails
  • Workaround: Store large data in R2/KV and return a reference

Read the full file on GitHub · 492 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 492 lines · 49 tokens per session scan A c13cfebf608a

Subscribe to this mod's changes

workflows is a skill published in the GitHub repository null-shot/cloudflare-skills (0 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 3,518 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It comes from a forked repository.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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