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 instructions/hamzaamjad/cursor-rules/gemini-mdgit clone --depth 1 https://github.com/hamzaamjad/cursor-rulesWhat 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 | $0.00674 | $0.00674 |
| Opus 5 | $0.00337 | $0.00337 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade B, and why
cursor-rules GEMINI.md scanned grade B with 1 finding 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- May run bash/python snippets directly (no sudo without explicit permission) This is a copy
97% identical to cursor-rules CLAUDE.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Assistant Rules for The Mirror Project
Core Philosophy
You are assisting with The Mirror Project - a local-first, privacy-respecting AI workspace that unifies LLMs, personal health & context streams, and autonomous agents. Always prioritize:
- Information density and engineering precision
- Privacy and local-first architecture
- Practical, working solutions over theoretical discussions
Communication Style
- Be information-dense and engineering-precise; avoid fluff
- Default to "you can do this" coaching tone
- Ask clarifying questions ONLY when ambiguity blocks action
- Prefer primary sources and official documentation; always cite links
Code Standards
- Language: Python 3.11+ with type hints
- Framework: FastAPI with Pydantic v2 for APIs
- Style: Well-commented, runnable code with minimal external dependencies
- Testing: Maintain 80%+ coverage with descriptive test names
- Security: Never commit secrets, validate all inputs, use secure defaults
Output Formats
- Code: Properly formatted with comments, ready to run
- Tasks: Numbered checklists or YAML/JSON specs ready for agents
- Documentation: Markdown with clear heading hierarchy and links
- Diagrams: Mermaid for architecture, tables for comparisons
Technology Stack
Core
- Python 3.11, FastAPI, Pydantic v2, Poetry/venv
- PostgreSQL + TimescaleDB, Redis, Docker
- GitHub Actions for CI/CD
ML/LLM
- HuggingFace (transformers, accelerate)
- Diffusion-based LLaDA-8B
- Vector stores (Chroma), RAG implementations
Infrastructure
- Kubernetes-lite (k3d), Prometheus + Grafana
- Pulumi (TypeScript) for IaC
- Git-secrets pre-commit hooks
Project-Specific Context
- Building local-first health data integration (WHOOP, Oura, Tomorrow.io)
- Implementing FastAPI/OpenAI-style endpoints
- Creating Grafana dashboards for visualization
- Ensuring GitHub Actions CI/CD with act-local parity
Development Workflow
- Rapid prototyping with edge-case thinking
- Test coverage for all new features
- Clear documentation in README/AGENTS.md
- Containerized, production-ready deployments
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.
- 2d ago First seen · 74 lines · 674 tokens per session scan B bb3322057128
cursor-rules GEMINI.md is an instructions file published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 674 tokens to every session, about $0.0034 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). It is 97% identical to cursor-rules CLAUDE.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.