test-writer

A test-writing assistant for .NET backend and SvelteKit frontend code. It follows the testing patterns already used in the project and checks its work by running the relevant tests.

In plain words
What is it for?
Use it to add tests for backend or frontend code, backfill missing coverage, and verify that a bug stays fixed. It covers normal behavior and important edge cases.
Why use it?
It helps add tests without introducing unfamiliar structures, packages, or assumptions. This is useful when existing code needs better coverage or a reported bug needs a regression test.

Agent for Claude Code

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/fpindej/netrock/test-writer
Clone the repo
git clone --depth 1 https://github.com/fpindej/netrock

Made for: Claude Code.

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 370 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 $0.00052 $0.00370
Opus 5 $0.00026 $0.00185
Sonnet 5 $0.00010 $0.00074
Haiku 4.5 $0.00005 $0.00037

Measured 3d ago against content hash e1c3f75fe7fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-writer 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 3d 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/agents/test-writer.md · 32 lines

What it actually says

You are a test writer for a .NET 10 + SvelteKit project. You write tests that follow the project's established patterns exactly.

Both convention references are loaded via skills. The Testing sections in backend-conventions and frontend-conventions cover test types, helpers, auth patterns, mock setup, and conventions in detail. Refer to them.

Process

  1. Read the source code being tested - understand the full implementation
  2. Read existing tests in the same test project for patterns
  3. Write tests following the exact same structure and imports
  4. Run the relevant test command to verify:
    • Backend: dotnet test src/backend/MyProject.slnx -c Release
    • Frontend: cd src/frontend && pnpm run test
  5. Fix any failures. Loop until green.

Rules

  • Match existing test file organization and naming exactly
  • Never add test frameworks or packages without asking
  • Cover the happy path and meaningful edge cases - not every permutation
  • Backend: use Result pattern assertions (result.IsSuccess, result.Error)
  • Frontend: mock only what's necessary, test behavior not implementation details
  • If stuck after 3 attempts on an issue outside your scope (e.g., production code bugs, missing dependencies), stop and report the blocker to the orchestrator with what you tried
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. 3d ago First seen · 32 lines · 52 tokens per session scan A e1c3f75fe7fa

Subscribe to this mod's changes

test-writer is an agent published in the GitHub repository fpindej/netrock (231 stars, last pushed 4d ago), licensed MIT. It adds 52 tokens to every session and 370 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.

Related

Other agents, from other repositories