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 commands/nextflow-io/agent-skills/evalgit clone --depth 1 https://github.com/nextflow-io/agent-skillsWhat 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 | $0.00007 | $0.00369 |
| Opus 5 | $0.00003 | $0.00185 |
| Sonnet 5 | $0.00001 | $0.00074 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
eval 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 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.
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.
What it actually says
Evaluate the migrate-nextflow-code skill by attempting a real migration on a real Nextflow pipeline.
Arguments:
$1— which migration to evaluate: one ofstrict-syntax,topic-channels,static-typing,workflow-outputs(required)$2— GitHub URL of the pipeline to migrate (required)$3— branch to check out (optional; default branch if omitted)
If $1 is not one of the four migrations above, stop and say so — do not guess.
Do this in order:
-
Read the skill. Read
skills/migrate-nextflow-code/SKILL.md, then the reference file for the$1migration. Follow that procedure — do not improvise your own migration steps. -
Clone into
evals/. Clone the repository asevals/<name>(add--branch $3if a branch was given). Ifevals/<name>already exists, stop and ask whether to reuse it or re-clone — do not silently overwrite. Change into the directory. -
Run the
$1migration. Perform the$1migration onevals/<name>. -
Report the outcome. When done (or blocked), summarize as an eval result:
- how far the migration got;
- anything the skill's instructions didn't cover or got wrong, and any point where a tool's output was stale, missing, or misleading.
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 · 27 lines · 7 tokens per session scan A 6347ac490f39
eval is a command published in the GitHub repository nextflow-io/agent-skills (21 stars, last pushed 27d ago), licensed Apache-2.0. It adds 7 tokens to every session and 369 once invoked, about $0.0000 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.
Other commands, from other repositories
OPSX: Fast Forward
Create a change and generate all artifacts needed for implementation in one go.
medical-necessity
Generate medical necessity letters citing chiropractic clinical guidelines for insurance authorization and appeals.
wh:asta-lit
Use when the user wants to find literature with Asta Paper Finder and ingest the results into the Wheeler knowledge graph.
gpd:derive-equation
Perform a rigorous physics derivation with systematic verification at each step.
run-panguweather
Guide the user through running PanguWeather end-to-end on an AMD cluster.
unity-test
Writes missing tests and runs them via MCP. Identifies untested code, creates EditMode/PlayMode tests, executes via runtests, reports results.