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.
curl -O https://raw.githubusercontent.com/cpuguy96/StepCOVNet/master/.cursor/skills/autoresearch/SKILL.mdgit clone --depth 1 https://github.com/cpuguy96/StepCOVNetWrote 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/cpuguy96/stepcovnet/autoresearch)<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.
<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>- NVIDIA SkillSpector warn
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
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 | $0.00078 | $0.02637 |
| Opus 5 | $0.00039 | $0.01319 |
| Sonnet 5 | $0.00016 | $0.00527 |
| Haiku 4.5 | $0.00008 | $0.00264 |
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.
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.
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.
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.
- 10d ago First seen · 173 lines · 78 tokens per session scan A d11f066578b5
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.
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…
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.
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…
science-vibecoding
Structured AI-assisted scientific code generation. 6 safety guards, 8 principles, 11 prompt templates. Grounded in Nature (2026).
flow-nexus-neural
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus.
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.