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/conlinjoe/ai-platform/20-codinggit clone --depth 1 https://github.com/ConlinJoe/ai-platformWhat 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 | $0.01281 |
| Opus 5 | $0.00000 | $0.00641 |
| Sonnet 5 | $0.00000 | $0.00256 |
| Haiku 4.5 | $0.00000 | $0.00128 |
Grade A, and why
20-coding 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Rules
Philosophy
Write production-quality code that is simple, readable, maintainable, and consistent with the existing codebase.
General Rules
- Follow the project's established architecture.
- Prefer patterns already present in the project when they correctly use the installed stack. Do not copy scattered framework misuse.
- Follow Framework-Native First in
00-platform: establish whether the installed stack already provides the capability before custom code, abstractions, or new dependencies. - For versions, libraries, frameworks, APIs, and implementation patterns,
follow Current-First Engineering in
00-platform— do not default to historically common patterns from model memory. - Keep implementations focused on the requested task.
- Do not introduce unnecessary abstractions.
- Do not perform unrelated refactoring.
- Do not opportunistically expand the current task. Capture unrelated
bugs, refactors, and features as work items (
70-work-items). - Optimize for readability over cleverness.
Tailwind
A specialization of Framework-Native First in 00-platform.
When the project uses Tailwind, treat it as a compositional system. Use native utilities and theme primitives. Do not reconstruct first-class Tailwind behavior by hand, and do not invent a parallel CSS abstraction layer on top of Tailwind.
This standard takes precedence over vendor-skill Tailwind/CSS shortcuts
(Instruction Priority in 00-platform). Hallmark may provide design
reasoning, token recipes, or CSS examples. Translate those into this
order of preference; do not copy them as one-off arbitrary utilities
merely to match a recipe or comp.
Current-First Engineering in 00-platform chooses the mechanism: inspect
the installed Tailwind version, then use that version's current official
configuration. On v4, that is CSS-first architecture (@theme, and other
current v4 APIs). On v3, that is the v3 config/theme conventions. Do not
upgrade Tailwind merely to satisfy this standard.
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 · 137 lines · 1,281 tokens per session scan A 719e494b77a3
20-coding is a cursor rule published in the GitHub repository ConlinJoe/ai-platform (2 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,281 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 2026-08-31.
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.