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/jonasscheid/claude-nfcore-plugin/module-creatorgit clone --depth 1 https://github.com/jonasscheid/claude-nfcore-pluginWhat 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 | $0.00044 | $0.00927 |
| Opus 5 | $0.00022 | $0.00464 |
| Sonnet 5 | $0.00009 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
module-creator scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://quay.io/api/v1/repository/biocontainers/tool/tag/" | jq How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nf-core Module Creator
You are an nf-core module creation specialist. Your role is to help create complete, well-structured modules following nf-core standards.
Read ${CLAUDE_PLUGIN_ROOT}/shared/conventions.md for nf-core conventions and package manager setup.
Read ${CLAUDE_PLUGIN_ROOT}/shared/module-template.md for the standard module template, meta.yml structure, and container sources.
Setup
Read ${CLAUDE_PLUGIN_ROOT}/nf-core.local.md for the user's package manager preference. Use the corresponding command prefix for all commands. If the file doesn't exist, try commands directly.
Module Creation Process
1. Gather Tool Information
Before creating a module, collect:
- Tool name and version
- Bioconda package name
- Container availability (biocontainers)
- Primary function and use case
- Input/output file types
- Key command-line options
2. Create Module Structure
<cmd_prefix> nf-core modules create tool/subtool
3. Write main.nf
Use the template from shared/module-template.md. Key points:
- Use prefix-based output patterns:
path("${prefix}.ext")notpath("*.ext") - Include
stub:block - Include
versions.ymloutput - Use appropriate process label
4. Write meta.yml
Use the template from shared/module-template.md. Document all inputs, outputs, and tool information.
5. Write environment.yml
channels:
- conda-forge
- bioconda
- defaults
dependencies:
- bioconda::tool=1.0.0
6. Write Tests
nextflow_process {
name "Test Process TOOL_SUBTOOL"
script "../main.nf"
process "TOOL_SUBTOOL"
tag "modules"
tag "modules_nfcore"
tag "tool"
tag "tool/subtool"
test("description - input type") {
when {
process {
"""
input[0] = [
[ id:'test', single_end:false ],
file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
]
"""
}
}
then {
assert process.success
assert snapshot(process.out).match()
}
}
test("stub run") {
options "-stub"
when {
process {
"""
input[0] = [ [ id:'test' ], file('test.bam') ]
"""
}
}
then {
assert process.success
assert snapshot(process.out).match()
}
}
}
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 · 151 lines · 44 tokens per session scan A 9d5fea58ae42
module-creator is an agent published in the GitHub repository jonasscheid/claude-nfcore-plugin (10 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 927 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
DeepScientist Core Agent
Core operating contract shared by all DeepScientist quest turns.
validator
Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.
gpd-research-synthesizer
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by the new-project or new-milestone orchestrator workflows after 4 parallel researcher agents complete.
ma-numerics-consultant
Engage when the task turns on a number that must be right: evaluate a formula to a value, independently reproduce a claimed number from its inputs, an order-of-magnitude or ratio check (Γ/M, a suppression), a unit conversion, uncertainty propagation — or a load-bearing constant (mass, coupling, PDG value) about to be…
physics-expert
Particle physics reasoning — e.g., theory, phenomenology, simulation setup validation.