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 agentmods add rules/cpuguy96/stepcovnet/research-logginggit 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/rules/cpuguy96/stepcovnet/research-logging)<a href="https://agentmods.dev/rules/cpuguy96/stepcovnet/research-logging"><img src="https://agentmods.dev/badge/rules/cpuguy96/stepcovnet/research-logging.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 | $0.00000 | $0.00396 |
| Opus 5 | $0.00000 | $0.00198 |
| Sonnet 5 | $0.00000 | $0.00079 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
research-logging 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 3d 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.
What it actually says
Research logging
When work under docs/research/ produces runs, design decisions, or durable insights — persist in the same session, not only in chat.
| Artifact | When | ID |
|---|---|---|
EXPERIMENT_LOG.md |
Measurable / reproducible run | EXP-YYYYMMDD-NN |
DISCUSSION_NOTES.md |
Design Q&A, tradeoffs, failure analysis | NOTE-YYYYMMDD-NN |
PAPER_LEDGER.md + paper.bib |
Paper, codebase, pack, or metric used as prior art / baseline / method / data | citation key |
PAPER_OUTLINE.md |
Optional — promote paper-worthy results only | — |
Prior art is cited (ledger key + BibTeX). Recreating a published pipeline is a baseline, not a substitute for a citation. Do not describe that as stealing.
Timestamp on every entry: YYYY-MM-DD HH:MM:SS from system clock at write time.
Agent: Log in the same turn — never ask the user to approve logging. Log all runs in a thread (including offline --ar_decode from logs/). Check the log and logs/ before suggesting a re-run.
Training seeds: reproducibility.apply_training_seed(seed) before model construction and dataset creation.
Full workflow: research-session-workflow skill. Log runs in EXPERIMENT_LOG.md; citations in PAPER_LEDGER.md + paper.bib; PAPER_OUTLINE.md only when drafting the paper.
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.
- 3d ago First seen · 27 lines · 0 tokens per session scan A 1e40170e8793
research-logging is a cursor rule published in the GitHub repository cpuguy96/StepCOVNet (21 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 396 tokens. 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 cursor rules, from other repositories
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.
workflows
This folder contains all GitHub Actions workflows for the Streamlit repository. Workflows automate CI/CD, testing, releases, and maintenance tasks.
python_tests
We use the unit tests to cover internal behavior that can work without the web / backend counterpart. We aim for 95%+ unit test coverage of our Python code in lib/streamlit.
skills
This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, etc.) when working with skills in this repository.