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 skills add Azealoo/miniAgent --skill generate_perturbation_hypothesisgit clone --depth 1 https://github.com/Azealoo/miniAgentWrote 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/skills/azealoo/miniagent/generate_perturbation_hypothesis)<a href="https://agentmods.dev/skills/azealoo/miniagent/generate_perturbation_hypothesis"><img src="https://agentmods.dev/badge/skills/azealoo/miniagent/generate_perturbation_hypothesis/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/skills/azealoo/miniagent/generate_perturbation_hypothesis"><img src="https://agentmods.dev/badge/skills/azealoo/miniagent/generate_perturbation_hypothesis.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 | $0.00034 | $0.01169 |
| Opus 5 | $0.00017 | $0.00584 |
| Sonnet 5 | $0.00007 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
generate_perturbation_hypothesis 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 8d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 8d ago First seen · 100 lines · 34 tokens per session scan A 9e6e4b21eae9
generate_perturbation_hypothesis is a skill published in the GitHub repository Azealoo/miniAgent (2 stars, last pushed 2mo ago), with no licence file. It adds 34 tokens to every session and 1,169 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.
Other skills, from other repositories
sc-perturb
Load when classifying perturbed vs non-perturbed cells in a Perturb-seq / CRISPR-screen scRNA AnnData via the pertpy Mixscape workflow. Skip when guide labels are not yet attached to the expression object (use sc-perturb-prep); in-silico KO predictions on unperturbed data (use sc-in-silico-perturbation).
sc-perturb-prep
Load when attaching cell-barcode → sgRNA assignments from a mapping TSV/CSV onto a Perturb-seq expression AnnData, producing standardised perturbation / sgRNA / target-gene obs columns. Skip when the AnnData already has perturbation labels (use sc-perturb); raw guide-calling from FASTQ (use upstream demuxlet /…
figure
Generates complete, runnable visualization code for research figures. Produces matplotlib/seaborn Python scripts for quantitative data and Mermaid diagrams for conceptual relationships, workflows, and taxonomies. Use when the user asks for charts, graphs, visualizations, figures, or diagrams. Produces code only — does…
peer-review
Simulates a full academic journal peer review with EIC decision and 3 independent reviewers (Methodology Expert, Domain Specialist, Devil's Advocate). Scores 1–10, provides major/minor comments, and issues a final verdict: Accept, Minor Revision, Major Revision, or Reject. Use when the user asks for a peer review…
validation
Designs detailed experimental protocols to validate research hypotheses. Each protocol includes independent variable, dependent variable, controls, sample size with power analysis, timeline, and expected outcome. Use when the user asks to design experiments, plan a study, propose validation methods, or test a specific…
hypothesis
Generates falsifiable, testable research hypotheses from notes, documents, and research content. Use when the user asks to brainstorm hypotheses, generate research questions, identify testable predictions, or discover patterns across their notes. Do NOT use for general Q&A — only when structured hypothesis output is…