A set of rules for a script that synchronizes AI-agent instructions and settings across several coding tools.

Use it when modifying the synchronization script, especially when merging settings for Claude Code, Codex, Copilot, Cursor, and Gemini.

It prevents repeated runs from changing the same data unnecessarily and protects configuration that the script does not own.

sync-script — Cursor rule by wyattowalsh

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/wyattowalsh/agents/sync-script

Clone the repo

git clone --depth 1 https://github.com/wyattowalsh/agents

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 801 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00801
Opus 5	$0.00000	$0.00400
Sonnet 5	$0.00000	$0.00160
Haiku 4.5	$0.00000	$0.00080

Measured yesterday against content hash 1b314813f170, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

sync-script 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `~/.claude/settings.json` — Claude Code settings (merge hooks, permissions).

.cursor/rules/sync-script.mdc · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Script Rules

scripts/sync_agent_stack.py syncs AI agent assets (instructions, MCP configs, hooks, rules) to multiple platforms. Changes must preserve idempotency and never overwrite user data.

Core Principles

Idempotency: Running the script multiple times with the same inputs must produce the same outputs. Use content comparisons before writing.
Safe Merging: Preserve user-owned config keys, tables, and entries that the script does not manage.
Never overwrite user data: Only mutate sections explicitly marked as managed (e.g., blocks between BEGIN MANAGED BY sync_agent_stack.py and END MANAGED BY sync_agent_stack.py).

Platform Paths

Key destination paths the script writes to:

~/.claude/settings.json — Claude Code settings (merge hooks, permissions).
~/.claude/CLAUDE.md — Claude Code entrypoint (symlink to instructions/claude-code-global.md).
~/.codex/config.toml — Codex config (merge top-level keys, preserve unmanaged tables).
~/.codex/AGENTS.md — Codex entrypoint (symlink to instructions/codex-global.md).
~/.copilot/copilot-instructions.md — Copilot entrypoint.
~/.cursor/mcp.json — Cursor MCP servers.
~/.gemini/settings.json / ~/.gemini/GEMINI.md — Gemini CLI.
~/.config/opencode/opencode.json — OpenCode config.
.github/copilot-instructions.md — Repo-level Copilot instructions.
.github/instructions/ — Copilot rule instructions (generated from .claude/rules/).
.github/hooks/policy.json — Copilot hooks.
mcp.json / .vscode/mcp.json — Repo MCP configs.

MCP Registry

config/mcp-registry.json is the single source of truth for MCP server definitions.
seed_registry_from_current_state() bootstraps the registry from existing platform configs if the registry does not exist.
enabled_registry_servers() filters to servers where enabled is not False.
Env values in registry use placeholders (${ENV_VAR}); actual values are resolved at render time via resolve_env_value().

Read the full file on GitHub · 59 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.

yesterday First seen · 59 lines · 0 tokens per session scan B 1b314813f170

Subscribe to this mod's changes

sync-script is a cursor rule published in the GitHub repository wyattowalsh/agents (5 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 801 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

sync-script

Getting it into your agent

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

Sync Script Rules

Core Principles

Platform Paths

MCP Registry

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

typescript

coolify-ai-docs

python_lib

specs