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.
git clone --depth 1 https://github.com/neuromechanist/research-skillsWrote 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/neuromechanist/research-skills/documentation)<a href="https://agentmods.dev/rules/neuromechanist/research-skills/documentation"><img src="https://agentmods.dev/badge/rules/neuromechanist/research-skills/documentation.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 | $0.00004 | $0.00571 |
| Opus 5 | $0.00002 | $0.00285 |
| Sonnet 5 | $0.00001 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
documentation 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Standards (MkDocs)
Core Philosophy: Write for Your Future Self
Good docs answer questions before they're asked. Think: What would confuse me in 6 months? Goal: New developers productive in <1 hour.
Setup
Install: uv add --group docs mkdocs mkdocs-material mkdocstrings[python]
Config: mkdocs.yml in project root
Minimal mkdocs.yml
site_name: {{PROJECT_NAME}}
site_url: https://example.com
repo_url: https://github.com/user/repo
theme:
name: material
features: [navigation.tabs, search.suggest]
nav:
- Home: index.md
- API: api/
- Guides: guides/
plugins:
- search
- mkdocstrings:
handlers:
python:
options:
show_root_heading: yes
members_order: source
markdown_extensions:
- pymdownx.highlight
- pymdownx.superfences
- admonition
- toc
Structure
docs/
index.md # Home page
guides/
getting_started.md
advanced.md
api/ # Auto-generated from docstrings
module_a.md # Contains ::: my_project.module_a
API Documentation
# Module A
::: my_project.module_a
handler: python
options:
show_source: no
Commands
- Develop:
mkdocs serve(live preview at localhost:8000) - Build:
mkdocs build(generates site/) - Deploy:
mkdocs gh-deploy(to GitHub Pages)
Writing Tips (Think Like a Teacher)
- Start with why: Context before details
- Show, don't tell: Examples > explanations
- Use admonitions:
!!! warning "Common mistake" - Code blocks: Include full context, not fragments
- Progressive disclosure: Simple first, then advanced
Ask yourself:
- Would a new developer understand this?
- Did I explain the "why" not just the "how"?
- Are there examples for each concept?
CI/CD Integration
See ci-cd.mdc for auto-deployment workflow
Documentation Mindset
You're not just documenting - you're teaching. Every README should get someone running in minutes. Every guide should prevent a support question. Think: "What would I want to know?"
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 · 95 lines · 4 tokens per session scan A 533dcce42900
documentation is a cursor rule published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 5d ago), licensed BSD-3-Clause. It adds 4 tokens to every session and 571 once invoked, about $0.0000 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 2026-09-04.
Other cursor rules, from other repositories
pro-report-builder
Create polished HTML technical reports and multi-page documents for consulting deliverables. Includes a customizable design system with dark cover page, warm cream content pages (8.5x11 portrait), professional typography, and a curated component library (KPI cards, data tables with severity coloring, callout boxes…
pptx
Tools for creating and editing PowerPoint (.pptx) presentations. / TR: PowerPoint (.pptx) sunumları oluşturmak ve düzenlemek için yetenek.
data-viz-deck
Transform audit data, performance reports, and structured analyses into polished visual deliverables. Generates presentation decks (PPTX), interactive HTML dashboards, or styled markdown reports with charts. Includes a customizable design system with forest green accent and warm cream backgrounds. Use when the user…
Tools for creating, reading, and converting PDF documents. / TR: PDF belgeleri oluşturmak, okumak ve dönüştürmek için yetenek.
docx
Tools for creating, reading, and editing Word (.docx) documents. / TR: Word (.docx) belgeleri oluşturmak, okumak ve düzenlemek için yetenek.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.