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/research-session-workflow/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/research-session-workflow)<a href="https://agentmods.dev/skills/cpuguy96/stepcovnet/research-session-workflow"><img src="https://agentmods.dev/badge/skills/cpuguy96/stepcovnet/research-session-workflow.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.01288 |
| Opus 5 | $0.00022 | $0.00644 |
| Sonnet 5 | $0.00009 | $0.00258 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
research-session-workflow 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 7d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research session workflow
Session start
- docs/research/README.md — load one linked doc, not the full log
- EXPERIMENT_LOG.md § Current phase / Recommended next step
- One
EXP-…row from the same log index if needed - Skim DISCUSSION_NOTES.md for open questions (newest first)
North star: PIPELINE_ARCHITECTURE.md.
During work
Tag changes by pipeline stage: pre | model | post | metric | train.
Plan docs with JSON/schemas: design-doc-fields.mdc and DATASET_PREP_PIPELINE.md §6.3.
Log experiment (EXP-YYYYMMDD-NN)
Same turn, no ask: After any measurable run or offline eval (eval_ar_onset_offline.py, eval_dense_onset.py, threshold sweep, training finish), prepend or update EXPERIMENT_LOG.md in the same session — do not offer to log or wait for user confirmation.
Complete the series: When a thread has multiple runs (run1, run2, v3, v4, offline --ar_decode logs under logs/), append every run’s key numbers to the same EXP-… entry in the session you discover them — not only the latest run and not vague “local v4” hand-waves.
Before suggesting a re-run: grep EXPERIMENT_LOG.md and logs/ for the checkpoint/config — if decode already exists on disk, read it and update the log instead of proposing the job again.
Before suggesting a new experiment / loss / architecture probe: gather evidence first (existing ckpt metrics, ablation, cheap analysis). Do not recommend a train because Current phase named a lever — that line is a candidate until measurements support it. See whats-next § Evidence before recommending a run.
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.
- 7d ago First seen · 75 lines · 44 tokens per session scan A 9dc6ce12f863
research-session-workflow is a skill published in the GitHub repository cpuguy96/StepCOVNet (22 stars, last pushed 12d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,288 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 2026-08-30.
Other skills, from other repositories
flow-nexus-neural
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus.
developing-with-streamlit
Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st.…
physicsnemo-shard-tensor
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…
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…
lepton-cli
Operate NVIDIA DGX Cloud Lepton through the globally installed lep CLI. Use when the user asks to inspect or manage Lepton workspaces, endpoints/deployments, dev pods, batch jobs, fine-tuning jobs, Ray clusters, Slurm clusters, Dynamo endpoints, storage, secrets, nodes, ingress, templates, logs, authentication, or…
perforatedai
Expert in PerforatedAI library for adding artificial dendrites to PyTorch neural networks. Triggers: 'Perforate my model' (start interactive setup), 'debug my perforated model' (debug/optimize existing integration), 'load my perforated model for inference' (deploy trained models). Also use when: debugging dendrite…