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.
git clone --depth 1 https://github.com/nextflow-io/agent-skillsWrote 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.
[](https://agentmods.dev/commands/nextflow-io/agent-skills/eval)<a href="https://agentmods.dev/commands/nextflow-io/agent-skills/eval"><img src="https://agentmods.dev/badge/commands/nextflow-io/agent-skills/eval/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/nextflow-io/agent-skills/eval"><img src="https://agentmods.dev/badge/commands/nextflow-io/agent-skills/eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00007 | $0.00281 |
| Opus 5.5 | $0.00003 | $0.00112 |
| Sonnet 5.5 | $0.00001 | $0.00056 |
| Haiku 4.5 | $0.00001 | $0.00028 |
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 16d 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
Clone a Nextflow pipeline. Have a subagent migrate it using the /migrate-nextflow-code skill and report back on its experience with the skill.
Arguments:
$1— GitHub URL of the pipeline to migrate (required)$2— branch to check out (optional)$3— description of the migration to perform (required)
Procedure:
-
Clone the pipeline repository into the
evalsdirectory asevals/<name>-<NNN>, whereNNNis zero-padded increment to distinguish between repeated runs on the same pipeline. If a branch is not given, use thedevbranch if the project has one, otherwise the default branch. -
Prompt a subagent with the repo, the skill, and the migration to perform.
-
Have the agent report on its experience using the skill: how the migration went, what external resources it used, what worked or didn't work, etc. The agent should write a detailed
REPORT.mdto the repository, with inline code snippets as needed to explain issues. Offer to ask the agent follow-up questions if you have the tools to do so.
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.
- 16d ago Changed · -6 lines 08a70b8f2576
- 2mo 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 (25 stars, last pushed yesterday), licensed Apache-2.0. It adds 7 tokens to every session and 281 once invoked, about $0.0000 per session on Opus 5.5. 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
fix-tests
Focus on all unit + command tests (pytest --exclude tests/integration). Make sure they pass and fix errors. If you run into anything very odd: stop, and let me know. Mutate test code first and let me know if you think you should update application code.
pn-audit-design-tokens
Surgical design-token audit — CSS custom property coverage, token naming, dark-mode correctness, and hardcoded value elimination. Standalone or chained by pn-frontend-audit.
run_tests
Use the text the user typed after the command name as the request for this command.
implement_tests
Use the text the user typed after the command name as the request for this command.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
pn-audit-api
Surgical API design review — REST conventions, status codes, response shapes, validation, and schema leaks. Use standalone or as part of pn-backend-audit. Outputs a scored fix roadmap.