agentmods.dev

durabletask-extensions: Instructions file for Claude Code

CLAUDE.md

durabletask-extensions CLAUDE.md is an instructions file for Claude Code from lucaslorentz/durabletask-extensions. It costs 682 tokens per session, scanned A, original, MIT.

A set of coding instructions for a .NET library that extends Azure Durable Task Framework, with a React and TypeScript web interface. It describes the required build, test, service-startup, and UI checks.

In plain words
What is it for?
Building the library, running in-memory tests across supported .NET versions, starting the sample services, and smoke-testing the UI with Playwright.
Why use it?
It gives agents a repeatable validation process for a project with multiple .NET versions, background services, and a browser interface.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is lucaslorentz/durabletask-extensions's own configuration. It tells Claude Code how to work on durabletask-extensions itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything durabletask-extensions configures →

not rated 67repo 4d ago A scan 682 tokens original MIT
View source ↗ lucaslorentz/durabletask-extensions
Reuse

Borrowing it

Nothing to install: this file belongs to lucaslorentz/durabletask-extensions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lucaslorentz/durabletask-extensions/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/lucaslorentz/durabletask-extensions

Made for: Claude Code.

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 durabletask-extensions CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lucaslorentz/durabletask-extensions/claude-md/github.svg)](https://agentmods.dev/instructions/lucaslorentz/durabletask-extensions/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lucaslorentz/durabletask-extensions/claude-md"><img src="https://agentmods.dev/badge/instructions/lucaslorentz/durabletask-extensions/claude-md/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 durabletask-extensions CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lucaslorentz/durabletask-extensions/claude-md"><img src="https://agentmods.dev/badge/instructions/lucaslorentz/durabletask-extensions/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 682 This file is loaded in full into every session.
When invoked 682 The same file — it is already loaded in full.
Security scan A 0 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 $0.00682 $0.00682
Opus 5.5 $0.00273 $0.00273
Sonnet 5.5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured 2mo ago against content hash 33bebd5bf68c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

durabletask-extensions CLAUDE.md 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 2mo 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.

CLAUDE.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions

Language

English for everything: code, commits, PR titles/bodies, issue/PR comments, and docs.

Project Overview

This is a .NET library (NuGet packages) extending Azure Durable Task Framework. Multi-target: net10.0, net9.0, net8.0. Frontend: React 18 + MUI 5 + TypeScript + Vite.

Development Workflow

Before every commit, follow this sequence:

1. Build

dotnet build

Must pass with 0 warnings and 0 errors.

2. Unit Tests

dotnet test --filter "FullyQualifiedName~InMemory" --no-build

InMemory tests run without Docker. All 3 TFMs (net10.0, net9.0, net8.0) must pass.

3. UI Smoke Test via Aspire

Start all services at once using the Aspire AppHost:

dotnet run --project samples/AppHost/AppHost.csproj

This starts: Server, Api, Ui, OrchestrationWorker, CarWorker, FlightWorker, HotelWorker, BpmnWorker.

Then use Playwright to verify the UI:

  1. Navigate to the UI (https://localhost:5002)
  2. Verify the home page loads ("Welcome to Durable Task UI")
  3. Navigate to Orchestrations page - verify table renders
  4. Create a BookParallel orchestration (Name: BookParallel, Version: v1, Input: {})
  5. Wait a few seconds for workers to process it
  6. Refresh and verify Status changes to Completed
  7. Check the History tab - verify the full execution flow is visible
  8. Take screenshots as evidence

After verification, stop the Aspire process.

4. Commit

Only commit after all steps above pass successfully.

Package Versioning Rules

Since src/ projects are published NuGet libraries:

  • Microsoft.Extensions.* and Microsoft.EntityFrameworkCore.* must stay at the minimum compatible version for each TFM (e.g., 10.0.0 not 10.0.3 for net10.0). This maximizes compatibility for consumers.
  • Non-framework packages (DurableTask.Core, gRPC, Protobuf, SourceLink, etc.) should be updated to latest stable versions.
  • Test, sample, and benchmark projects (not published) can use latest versions freely.

Read the full file on GitHub · 92 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. 2mo ago First seen · 92 lines · 682 tokens per session scan A 33bebd5bf68c

Subscribe to this mod's changes

durabletask-extensions CLAUDE.md is an instructions file published in the GitHub repository lucaslorentz/durabletask-extensions (67 stars, last pushed 4d ago), licensed MIT. It adds 682 tokens to every session, about $0.0027 per session on Opus 5.5. 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 2026-09-01.

Backend and APIsFrontend
Related

durabletask-extensions CLAUDE.md compared with instructions from other repositories

durabletask-extensions CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
durabletask-extensions CLAUDE.mdlucaslorentz/durabletask-extensionsInstructions file674d agoMITA682Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode