sync-workflow

A rule for keeping AI assistant configuration synchronized across five coding tools. It defines the canonical source files and explains which Claude Code and Cursor files are generated copies or links.

In plain words
What is it for?
Use it before editing project rules, slash commands, or skills, especially when changes must reach Claude Code, Cursor, Codex CLI, GitHub Copilot, or Gemini.
Why use it?
It prevents conflicting hand edits and makes clear where rules, commands, and skills should be changed so every supported tool stays aligned.

Cursor rule for Cursor

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/secondlifes/code-intel/sync-workflow
Clone the repo
git clone --depth 1 https://github.com/SecondLifes/code-intel

Made for: Cursor.

Per session 1,369 This file is loaded in full into every session.
When invoked 1,369 The same file — it is already loaded in full.
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 $0.01369 $0.01369
Opus 5 $0.00685 $0.00685
Sonnet 5 $0.00274 $0.00274
Haiku 4.5 $0.00137 $0.00137

Measured yesterday against content hash d80c682a2536, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-workflow 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.

.cursor/rules/sync-workflow.mdc · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Config Source of Truth & Sync Workflow

This repo supports five AI coding tools (Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini/Antigravity CLI). To avoid maintaining near-duplicate copies by hand, most content has a single canonical source under .agents/.

Where content actually lives

Content Canonical source Generated / native copies
Rules (per-topic, glob-scoped) .agents/rules/*.md .claude/rules/*.md and .cursor/rules/*.mdcgenerated, do not hand-edit. Note the extension: Cursor recognizes only .mdc under .cursor/rules and silently ignores .md there (cursor.com/docs/rules).
Slash commands .agents/commands/*.md .claude/commands/*.mdgenerated, do not hand-edit
Skills .agents/skills/*/SKILL.md content is never copied, but Claude Code needs an entry point: a generated junction/symlink per skill at .claude/skills/<skill-name>.agents/skills/<skill-name>. Claude Code additionally gets a generated thin wrapper at .claude/commands/<skill-name>.md so the skill is also invocable as an explicit /<skill-name> command — see below.
Root universal summary AGENTS.md none — hand-authored, references .agents/rules for detail
Gemini/Antigravity summary .gemini/rules/project-rules.md none — hand-authored, same role as AGENTS.md but Gemini-specific
Copilot pre-prompt .github/copilot-instructions.md none — hand-authored, references AGENTS.md
Kiro steering docs .kiro/steering/*.md none — different concept (living project context, not per-topic rules), intentionally out of this sync scheme

Mandatory workflow

Whenever you add, edit or delete a file under .agents/rules/ or .agents/commands/, OR add/remove a skill folder under .agents/skills/, immediately run the generator before finishing your turn:

pwsh tools/generate-ai-configs.ps1

This copies the current source into .claude/rules (as .md) and .cursor/rules (as .mdc), copies commands into .claude/commands, generates one .claude/commands/<skill-name>.md wrapper per folder under .agents/skills/, links each of those skill folders into .claude/skills/, and removes any generated file, wrapper or link whose source was deleted. If a skill's folder name collides with a hand-authored file under .agents/commands/, the script skips generating a wrapper for it and prints a warning — hand-authored commands always win. Never hand-edit files inside .claude/rules/, .cursor/rules/ or .claude/commands/ directly — they will be silently overwritten on the next run and any change made only there will be lost.

Read the full file on GitHub · 90 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. yesterday First seen · 90 lines · 1,369 tokens per session scan A d80c682a2536

Subscribe to this mod's changes

sync-workflow is a cursor rule published in the GitHub repository SecondLifes/code-intel (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 1,369 tokens to every session, about $0.0068 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.