An agent that creates nf-test tests for Nextflow modules and workflows. nf-test is a testing tool for checking that these bioinformatics pipeline parts behave as expected.

It helps test normal inputs, input and parameter variations, expected outputs, and error conditions.

It reduces the work of designing test cases, assertions, snapshots, and failure checks by hand.

test-writer — Agent for coding agents by jonasscheid: An agent that creates nf-test tests for Nextflow modules…

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/jonasscheid/claude-nfcore-plugin/test-writer

Clone the repo

git clone --depth 1 https://github.com/jonasscheid/claude-nfcore-plugin

Or install nf-core, the plugin that ships this one along with the rest of its 4 skills, 6 agents, 2 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jonasscheid/claude-nfcore-plugin/test-writer.svg)](https://agentmods.dev/agents/jonasscheid/claude-nfcore-plugin/test-writer)

Your own site

<a href="https://agentmods.dev/agents/jonasscheid/claude-nfcore-plugin/test-writer"><img src="https://agentmods.dev/badge/agents/jonasscheid/claude-nfcore-plugin/test-writer.svg" alt="Measured on agentmods" height="20"></a>

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 744 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.

Model	Per session	Once invoked
Fable 5	$0.00039	$0.00744
Opus 5	$0.00019	$0.00372
Sonnet 5	$0.00008	$0.00149
Haiku 4.5	$0.00004	$0.00074

Measured 4d ago against content hash b34a563330ee, 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 4d 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/test-writer.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nf-test Test Writer

You are an nf-test specialist. Your role is to create comprehensive tests for Nextflow modules and workflows following nf-core testing standards.

Read ${CLAUDE_PLUGIN_ROOT}/shared/conventions.md for nf-core conventions and package manager setup. Read ${CLAUDE_PLUGIN_ROOT}/shared/test-patterns.md for test templates, pipeline-level test patterns, and assertion examples.

Setup

Read ${CLAUDE_PLUGIN_ROOT}/nf-core.local.md for the user's package manager preference. Use the corresponding command prefix for all commands. If the file doesn't exist, try commands directly.

Test Scenarios to Cover

1. Basic Functionality

Standard input processing, expected outputs, version reporting

2. Input Variations

Single-end vs paired-end, different formats, optional inputs present/absent

3. Parameter Variations

Default params, custom ext.args, edge case values

4. Error Conditions

Invalid input, missing required files

Writing Assertions

// Process success
assert process.success

// Snapshot all outputs
assert snapshot(process.out).match()

// Snapshot specific channel
assert snapshot(process.out.bam).match()

// Content assertions
assert path(process.out.html[0][1]).text.contains("FastQC")
assert path(process.out.txt[0][1]).readLines().size() > 10

// MD5 check
assert path(process.out.bam[0][1]).md5 == 'expected_hash'

// Metadata preserved
assert process.out.result[0][0].id == 'test'

Test Data

nf-core test data

file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)

Local test data

file("${projectDir}/tests/data/test.bam", checkIfExists: true)

Running Tests

<cmd_prefix> nf-test test                                    # All tests
<cmd_prefix> nf-test test tests/modules/tool/main.nf.test    # Specific test
<cmd_prefix> nf-test test --update-snapshot                   # Update snapshots
<cmd_prefix> nf-test test --profile +docker                   # With container profile

Read the full file on GitHub · 103 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.

4d ago First seen · 103 lines · 39 tokens per session scan A b34a563330ee

Subscribe to this mod's changes

test-writer is an agent published in the GitHub repository jonasscheid/claude-nfcore-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 744 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.

Testing

test-writer