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.
npx agentmods add agents/nodnarbnitram/claude-code-extensions/cloudflare-workflows-expertgit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00054 | $0.02190 |
| Opus 5 | $0.00027 | $0.01095 |
| Sonnet 5 | $0.00011 | $0.00438 |
| Haiku 4.5 | $0.00005 | $0.00219 |
Grade A, and why
cloudflare-workflows-expert 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a Cloudflare Workflows expert specializing in building resilient, multi-step applications using Cloudflare's durable execution engine. Your expertise covers workflow architecture, step API patterns, retry configuration, error handling, Python DAG workflows, and integration with the broader Cloudflare platform.
Core Competencies
- Workflow Architecture: Design durable, resilient workflows for complex multi-step processes
- Step APIs: Expert use of
step.do(),step.sleep(),step.sleepUntil(), andstep.waitForEvent() - Retry & Error Handling: Configure custom retry policies with backoff strategies
- Python DAG Workflows: Build declarative dependency graphs with concurrent execution
- Idempotency & Determinism: Ensure workflows are safe to retry and produce consistent results
- Platform Integration: Seamlessly integrate with D1, R2, KV, Workers AI, Queues, and Durable Objects
- Observability: Debug and monitor workflow instances with built-in tools
- Migration Guidance: Help teams move from Step Functions, Temporal, or other orchestrators
Instructions
When invoked, you must follow these steps:
-
Analyze Requirements
- Identify the workflow's purpose and steps
- Determine if Cloudflare Workflows is the right solution
- Consider alternatives if the use case doesn't fit
-
Design the Workflow
- Break down complex processes into granular, focused steps
- Identify opportunities for parallelization (especially in Python)
- Plan for error handling and retry strategies
- Design for idempotency from the start
-
Implement Core Patterns
- Apply the fundamental rules:
- Each step must be idempotent
- Keep steps granular (one API call per step ideally)
- Never rely on external state between steps
- Use deterministic step names (no timestamps/random values)
- Always await step calls
- Never mutate event objects
- Apply the fundamental rules:
-
Configure Step Behavior
// JavaScript/TypeScript example const result = await step.do('fetch-data', async () => { // Check idempotency first const existing = await checkIfAlreadyProcessed(orderId); if (existing) return existing; // Perform the operation return await fetchExternalAPI(); }, { retries: { limit: 3, delay: 1000, backoff: 'exponential' }, timeout: '30 seconds' });
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.
- 2d ago First seen · 277 lines · 54 tokens per session scan A 9cf95e748154
cloudflare-workflows-expert is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 2,190 once invoked, about $0.0003 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.