cross-tool-config

A reference for carrying coding instructions between Cursor, Claude Code, GitHub Copilot, Windsurf, Gemini CLI, and Codex. It explains which configuration files each tool reads and how their project rules differ.

In plain words
What is it for?
Use it when moving project guidance between AI coding tools, choosing the correct configuration file, or checking whether rules apply to the whole project or selected paths.
Why use it?
Each coding tool uses its own instruction files, so copying one file between tools may not work as expected. This reference helps identify what can be shared and what must be adapted.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/nedcodes-ok/cursorrules-collection/cross-tool-config
Clone the repo
git clone --depth 1 https://github.com/nedcodes-ok/cursorrules-collection
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 958 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00958
Opus 5 $0.00012 $0.00479
Sonnet 5 $0.00005 $0.00192
Haiku 4.5 $0.00002 $0.00096

Measured 2d ago against content hash 6e9b81cbf002, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cross-tool-config 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 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

rules-mdc/ai-tools/cross-tool-config.mdc · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Tool AI Configuration

Every AI coding tool has its own instruction format. None of them read each other's files. Here's the landscape and what actually transfers.

Config File Reference

Tool File(s) Location Glob/Scope Support
Cursor .cursorrules, .cursor/rules/*.mdc Project root Yes (globs, alwaysApply in .mdc frontmatter)
Claude Code CLAUDE.md ~/.claude/, project root, subdirs No (all content loaded every session)
OpenAI Codex AGENTS.md, AGENTS.override.md ~/.codex/, project root → cwd No (concatenated root-to-leaf)
GitHub Copilot .github/copilot-instructions.md, .github/instructions/*.instructions.md, also reads AGENTS.md/CLAUDE.md/GEMINI.md .github/ dir Yes (applyTo globs in path-specific files)
Windsurf .windsurfrules, .windsurf/rules/*.md, .windsurf/workflows/*.md Project root No (plain markdown, 12K char limit per file)
Gemini CLI GEMINI.md ~/.gemini/, project root, subdirs (scans down too) No (pure markdown)

What Transfers Between Tools

  • Build/test/lint commands — every tool needs to know how to verify its changes. Write these once, copy to each config
  • Coding conventions — naming, formatting, patterns. These are language/project decisions, not tool decisions
  • Architecture context — project structure, key directories, tech stack. Same information, different files
  • "Don't touch" rules — files, directories, or patterns the AI should leave alone

What Doesn't Transfer

  • Frontmatter/metadata — Cursor's alwaysApply, globs, description don't exist in CLAUDE.md or AGENTS.md. Copilot has applyTo but the format is different
  • File locations.cursor/rules/ vs .github/instructions/ vs .windsurf/rules/ are all different paths
  • Behavioral tuning — each model responds differently to the same instruction. "Be concise" means different things to Claude, GPT, and Gemini
  • Workflows — Windsurf's step-by-step workflows have no equivalent in other tools. Cursor has no workflow concept. Claude Code uses slash commands differently

Read the full file on GitHub · 52 lines

Changes

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.

  1. 2d ago First seen · 52 lines · 24 tokens per session scan A 6e9b81cbf002

Subscribe to this mod's changes

cross-tool-config is a cursor rule published in the GitHub repository nedcodes-ok/cursorrules-collection (37 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 958 once invoked, about $0.0001 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 2026-08-30.