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/cursor_rules)<a href="https://agentmods.dev/rules/neuromechanist/research-skills/cursor_rules"><img src="https://agentmods.dev/badge/rules/neuromechanist/research-skills/cursor_rules.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 | $0.00878 | $0.00878 |
| Opus 5 | $0.00439 | $0.00439 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
cursor_rules 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Mindset: Think Like a Senior Developer
You are a skilled developer with excellent knowledge. Keep the big picture in mind. Before coding: Understand the problem deeply, review context, consider implications. During work: Maintain perspective, think about edge cases, document learnings.
Documentation-Driven Development
Core Docs (in .context/): plan.md (tasks), research.md (solutions), ideas.md (concepts), scratch_history.md (failures)
Integration: These work together - check .context/ideas.md for vision, .context/research.md for solutions, .context/plan.md for tasks, .context/scratch_history.md for pitfalls
Task Management
Simple: plan.md with [ ]→[⚠️]→[🔬]→[x]
Complex: TaskMaster CLI/MCP tools for dependencies
Development Flow (Think Through Each Step)
- Understand: Review requirements thoroughly, check .context/ideas.md for context
- Research: Explore solutions, update research.md with findings
- Branch:
git checkout -b feature/short-name - Plan: Identify changes and implications
- Code: Follow patterns, think about maintainability
- Test: Real tests only (no mocks) - see
testing.mdc - Document: Log failures in .context/scratch_history.md immediately
- Commit:
feat: concise message(<50 chars, atomic) - PR: Descriptive title, reference context in body
Pre-commit (Python)
cp templates/config/pre-commit .git/hooks/pre-commit
chmod +x .git/hooks/pre-commit
# Auto runs: ruff check --fix --unsafe-fixes + format
Code Quality Standards
Write code for humans to read:
- Python: ruff, pytest, mypy type hints
- General: Clear names, focused functions, docstrings for APIs
- Tests: Real data only, no mocks ever
- Commits: Atomic, focused, no emojis (<50 chars)
Think about:
- Will this be maintainable?
- Have I considered edge cases?
- Is the intent clear?
AI Guidelines (You're a Thoughtful Developer)
Before starting:
- Review ALL .context docs (ideas→research→plan)
- Understand the bigger picture and goals
- Consider architectural implications
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 · 96 lines · 878 tokens per session scan A 48b2e93b94c7
cursor_rules is a cursor rule published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 5d ago), licensed BSD-3-Clause. It adds 878 tokens to every session, about $0.0044 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
secret-scanner
Scans codebase for leaked API keys, credentials, certificates, and .env misconfigurations. / TR: Kod tabanında unutulmuş API key, şifre, sertifika gibi hassas verilerin taranması ve .env yönetimi.
git-pr-reviewer
Pull Request (PR) creation and code review standards with constructive feedback and merge strategies. / TR: Pull Request (PR) oluşturma ve kod inceleme (code review) süreçleri için standartlar ve yapıcı geri bildirim.
safe-push
Pre-push hygiene check for GitHub repositories. Scans for PII, secrets, and sensitive data before pushing. Audits commit messages, enforces repo-specific blocklists, and rate-limits pushes to avoid GitHub abuse detection. Use before any git push, especially to public repos.
git-conventions
Apply when committing, branching, or opening a pull request. Conventional commit format, branch naming, PR scope.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.