StepCOVNet: Skill for Claude Code

.cursor/skills/autoresearch/SKILL.md

autoresearch is a skill for Claude Code, Cursor from cpuguy96/StepCOVNet. It costs 78 tokens per session (2,637 once invoked), scanned A, original, Apache-2.0.

A guided, repeated research loop for improving StepCOVNet, a machine-learning system for detecting onset events. It uses a time budget to test ideas, record results, and continue until the goal is met or time runs out.

In plain words
What is it for?
Use it to run a defined StepCOVNet research goal with a deadline, such as testing a named research profile or improving event-detection results.
Why use it?
It removes the need to manually coordinate repeated experiments and track their results. The agent uses evidence from earlier runs when choosing what to try next.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/.

This is cpuguy96/StepCOVNet's own configuration. It tells Claude Code and Cursor how to work on StepCOVNet itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything StepCOVNet configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cpuguy96/StepCOVNet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cpuguy96/StepCOVNet/master/.cursor/skills/autoresearch/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cpuguy96/StepCOVNet

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for autoresearch

README.md
[![agentmods](https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/autoresearch/github.svg)](https://agentmods.dev/skills/cpuguy96/stepcovnet/autoresearch)
Your own site
<a href="https://agentmods.dev/skills/cpuguy96/stepcovnet/autoresearch"><img src="https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/autoresearch/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.

agentmods 80×15 button for autoresearch

Your own site · 80×15
<a href="https://agentmods.dev/skills/cpuguy96/stepcovnet/autoresearch"><img src="https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,637 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 21
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Prompt Injection · line 25
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 29
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 154
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
  • medium Prompt Injection · line 30
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.02637
Opus 5 $0.00039 $0.01319
Sonnet 5 $0.00016 $0.00527
Haiku 4.5 $0.00008 $0.00264

Measured 10d ago against content hash d11f066578b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autoresearch 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 10d 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.

.cursor/skills/autoresearch/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoresearch (agent loop)

You run the research loop in this Cursor session. Harness scripts train, eval, and record numbers; you choose hypotheses from evidence. Do not hand reasoning to unattended knob mutators (overnight_planner, fixed queues, lattice search) when this skill is active.

North star: PIPELINE_ARCHITECTURE.md.
Logging: research-session-workflow.
GPU: wsl-gpu-stepcovnet.

One-prompt invocation

When the user sends one message with a goal and time budget, run the full loop without asking between iterations unless blocked.

Parse from the user message:

Field Required Default
Profile No Infer from goal (see Choose a profile); if ambiguous, ask once before the loop
Goal No Profile default success criterion
Budget No 3 hours
Go Implied if user says autoresearch / do not ask between runs Loop autonomously

Example (tide):

Run autoresearch.
Profile: ar-tide-overfit
Goal: scratch teacher 634/634 then free-run 634/634 on tide @ 20 ms.
Budget: 7 hours.
Go — do not ask me between runs.

Read the full file on GitHub · 173 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 10d ago First seen · 173 lines · 78 tokens per session scan A d11f066578b5

Subscribe to this mod's changes

autoresearch is a skill published in the GitHub repository cpuguy96/StepCOVNet (22 stars, last pushed 15d ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,637 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

physicsnemo-discover

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…

NVIDIA/physicsnemo · 124 tokens

ml-for-aec

Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.

Abhinavbwj/Claude-skills-for-Computational-Designers · 39 tokens

ml-architecture-diagram

Create accurate, publication-ready, editable machine-learning and deep-learning architecture diagrams from model code, configuration files, model summaries, graph exports, or written specifications. Use for neural-network figures, architecture schematics, model block diagrams, training/inference diagrams, paper…

Ztsdut/ml-architecture-diagram-skill · 95 tokens

science-vibecoding

Structured AI-assisted scientific code generation. 6 safety guards, 8 principles, 11 prompt templates. Grounded in Nature (2026).

Liu-MingH/Scientific-research-SKILL · 35 tokens

flow-nexus-neural

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus.

proffesor-for-testing/agentic-qe · 21 tokens

ml-for-aec

Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.

marcinfinitesimal533/Claude-skills-for-Computational-Designers · 39 tokens