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 pandysp/claude-plugins --skill classify-with-jevgit clone --depth 1 https://github.com/pandysp/claude-pluginsWrote 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/pandysp/claude-plugins/classify-with-jev)<a href="https://agentmods.dev/skills/pandysp/claude-plugins/classify-with-jev"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/classify-with-jev/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/pandysp/claude-plugins/classify-with-jev"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/classify-with-jev.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 | $0.00173 | $0.00651 |
| Opus 5.5 | $0.00069 | $0.00260 |
| Sonnet 5.5 | $0.00035 | $0.00130 |
| Haiku 4.5 | $0.00017 | $0.00065 |
Grade A, and why
classify-with-jev 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 23d 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Classify with Jev
A classifier model answers questions that have a fixed set of answers (one of a few labels, yes or no, or a score) about data you pass as a JSON object, for example {"message": "…"}. Each answer comes with a probability or a confidence value that shows how sure the classifier is. In Pi it runs from a codemode script through models.classify().
Before writing the script, read the "Models" and "Classify" sections of codemode.md completely. The codemode tool description gives the file's path.
Classifier calls are fast and cheap. When you have many items, classify all of them rather than a sample.
A classifier does not reason. It is least reliable on questions that need thought, such as whether a claim follows from the evidence or whether two texts say the same thing.
Get a first feeling before thinking hard
This section is for using a classifier as a first impression. In labelling jobs, its answers are what you deliver, and the advice under "Read the answers" still applies.
- You write the options; the classifier picks one. Turn an open question into fixed-answer ones by listing the possible causes, options or verdicts as labels. When the thing has more than one side, such as its cause and its urgency, ask one question for each.
- Its answer tells you where to look, not what to conclude. Act on it without checking only when a wrong answer costs little, for example when it only decides what you read first.
- Look closest at unsure answers and surprises. An answer split between labels, or one that disagrees with your own reading, is where a closer look pays off. Read the item yourself before you overrule a surprise.
Read the answers
- Use probabilities and confidence values to rank answers against each other. They are not the chance that an answer is right. A classifier can pick a label with high confidence and still be wrong.
- Reword the question to test a result. Asking the identical question again tells you little. Change the wording of the question or the labels, and compare the answers.
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.
- 23d ago Changed · +28 lines · +52 tokens per session 56ab3f7fa067
- 25d ago First seen · 11 lines · 121 tokens per session scan A a06583e8e106
classify-with-jev is a skill published in the GitHub repository pandysp/claude-plugins (6 stars, last pushed 7d ago), licensed MIT. It adds 173 tokens to every session and 651 once invoked, about $0.0007 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 2026-10-03.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…