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/chickensintrees/ai-coding-rules/cursor-rulesgit clone --depth 1 https://github.com/chickensintrees/ai-coding-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 | $0.00823 | $0.00823 |
| Opus 5 | $0.00411 | $0.00411 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00082 | $0.00082 |
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 yesterday.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Coding Rules
TIER 1 — SURVIVAL
1. Checkpoint
Before making significant changes, commit the current working state with git. After completing any unit of work you'd be upset to lose, commit again. If git is not initialized in this project, initialize it before writing any code.
2. Don't Delete Without Asking
Never remove code, files, or comments without explicit user confirmation. When refactoring, preserve all existing functionality and comments. If you believe something should be removed, explain what and why, then wait for approval. Never strip comments during refactoring.
3. Read Before Write
Before editing any file, read its current contents. Every time — even if you think you know what's in it. Before creating a new file, search for existing files with similar names or purposes to avoid duplicating or overwriting existing work.
TIER 2 — INTEGRITY
4. Save Means Verify
After editing a file, verify the change by reading the file back or searching for a distinctive string from your edit. Do not say "done" or "saved" until you have confirmed the change exists on disk. If verification fails, fix the edit and re-verify.
5. Spec First
The spec is the single source of truth. If a spec file exists (SPEC.md, docs/spec.md, or equivalent), read it before doing any work. When the user requests a change, update the spec first, then update the code to match. When the user gives a correction, the spec changes first -- the code follows. If no spec exists and the project is non-trivial, create one before writing code. Never build from conversation alone when a spec file exists. The spec is the plan the code implements. When spec and code disagree, the spec wins.
6. Search Before Creating
Before creating a new file, function, or component, search the codebase for existing implementations. If something similar exists, decide whether to extend it, fork it (copy and modify independently), or replace it. If changing shared code could break other things, fork it. If a new implementation is genuinely needed, explain why.
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.
- yesterday First seen · 84 lines · 823 tokens per session scan A 4edada53b53b
cursor-rules is a cursor rule published in the GitHub repository chickensintrees/ai-coding-rules (2 stars, last pushed 1mo ago), licensed MIT. It adds 823 tokens to every session, about $0.0041 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 2026-08-31.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
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.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
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.