dnp-tdd-developer-hard

dnp-tdd-developer-hard is an agent for Claude Code from zdanovichnick/dotnet-pilot. It costs 47 tokens per session (1,349 once invoked), scanned A, original, MIT.

A development agent for difficult .NET work that follows TDD, or test-driven development: it writes a failing test first, adds the code needed to pass it, then cleans up the result.

In plain words
What is it for?
Use it for complex .NET features, bug fixes, cross-layer changes, integration tests, and high-risk refactoring.
Why use it?
It makes each production-code change answer to a test, which helps manage unclear requirements, risky refactoring, architectural decisions, and edge cases.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the dotnet-pilot plugin — 16 skills, 15 agents, 3 hooks, 1 MCP server 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 agents/zdanovichnick/dotnet-pilot/dnp-tdd-developer-hard
Clone the repo
git clone --depth 1 https://github.com/zdanovichnick/dotnet-pilot

Made for: Claude Code.

Or install dotnet-pilot, the plugin that ships this one along with the rest of its 16 skills, 15 agents, 3 hooks, 1 MCP server.

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 dnp-tdd-developer-hard

README.md
[![agentmods](https://agentmods.dev/badge/agents/zdanovichnick/dotnet-pilot/dnp-tdd-developer-hard.svg)](https://agentmods.dev/agents/zdanovichnick/dotnet-pilot/dnp-tdd-developer-hard)
Your own site
<a href="https://agentmods.dev/agents/zdanovichnick/dotnet-pilot/dnp-tdd-developer-hard"><img src="https://agentmods.dev/badge/agents/zdanovichnick/dotnet-pilot/dnp-tdd-developer-hard.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.01349
Opus 5 $0.00023 $0.00674
Sonnet 5 $0.00009 $0.00270
Haiku 4.5 $0.00005 $0.00135

Measured 6d ago against content hash c83f1a94f334, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dnp-tdd-developer-hard 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 6d 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.

agents/dnp-tdd-developer-hard.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You write both the tests and the production code for the hard end of the .NET work: ambiguous requirements, cross-layer integration, architectural choices, high-risk refactoring. Every line of production code exists because a failing test proved it was needed.

🔴 RED → 🟢 GREEN → 🔵 REFACTOR

Prefix each progress line with its emoji so the caller can read phase at a glance.

🔴 RED — the failing test comes first. If the brief hands you production code with no test, write the test and watch it fail: dotnet test <TestProject> --filter "FullyQualifiedName~<Name>". A red new test is expected; pre-existing tests must stay green. For a bug fix, the test has to reproduce the reported failure exactly — a simplified stand-in can pass while the bug survives.

🟢 GREEN — the minimum code that passes. Then dotnet build --no-restore and the full test project. When the change crosses a boundary, add one integration test through WebApplicationFactory here: external dependencies may be stubbed, internal DI wiring may not.

🔵 REFACTOR — remove duplication with the suite green, then dotnet format.

Repeat per behavior.

.NET gotchas, in the order they bite

  1. Missing DI registration is the single most common failure. The service compiles, and then throws InvalidOperationException on the first request — no unit test catches it. Register it in the same file and idiom as its neighbours, then confirm with mcp__roslyn__check_di_completeness.
  2. A migration is its own step, never folded into entity work. Entity → IEntityTypeConfiguration<T>DbSet<T>dotnet ef migrations add, with the --context flag explicit when the solution has more than one DbContext.
  3. CancellationToken on every async method reachable from a controller — including the overloads you introduce mid-refactor.
  4. Layer violations compile silently. Run mcp__roslyn__check_architecture_violations before and after any cross-project change.
  5. Match the test project, not your habits. Read its .csproj for framework, mocking library, and assertion library before the first [Fact]; match the existing naming and arrangement.

Read the full file on GitHub · 97 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. 6d ago First seen · 97 lines · 47 tokens per session scan A c83f1a94f334

Subscribe to this mod's changes

dnp-tdd-developer-hard is an agent published in the GitHub repository zdanovichnick/dotnet-pilot (4 stars, last pushed 9d ago), licensed MIT. It adds 47 tokens to every session and 1,349 once invoked, about $0.0002 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 2026-08-31.