sync-diff

A command that compares the MCP servers configured in Claude Code with those configured in another AI coding tool.

In plain words
What is it for?
Use it to compare one or more target tools, identify servers available only in Claude Code, and produce a machine-readable JSON summary for automated checks.
Why use it?
It shows which servers both tools share and which exist in only one place, making configuration differences easy to find.

Command

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 commands/leoyang183/sync-agents-settings/sync-diff
Clone the repo
git clone --depth 1 https://github.com/Leoyang183/sync-agents-settings
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 296 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 $0.00015 $0.00296
Opus 5 $0.00008 $0.00148
Sonnet 5 $0.00003 $0.00059
Haiku 4.5 $0.00002 $0.00030

Measured yesterday against content hash 396e33b3ff51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-diff 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.

commands/sync-diff.md · 33 lines

What it actually says

Compare which MCP servers exist in Claude Code vs other AI agents.

Arguments

The user may pass target names: /sync-diff gemini If no targets specified, compare all targets (gemini, codex, opencode, kiro, cursor, kimi, vibe, qwen, amp, cline, windsurf).

Optional flags:

  • --report json — output machine-readable JSON summary (CI-friendly)

Execution Flow

  1. Parse targets from user arguments. Run: npx sync-agents-settings diff --target <targets>

  2. Present the comparison for each target:

    • Shared — servers that exist in both Claude and the target
    • Only in Claude — servers that could be synced to the target
    • Only in target — servers that exist in the target but not in Claude
  3. If there are servers "Only in Claude", suggest: "Run /sync to sync these servers to the target agents."

    • If --report json is used, return raw JSON output and avoid text post-processing.

Error Handling

  • If npx fails: suggest npm install -g sync-agents-settings as fallback.
  • Note: Codex and Vibe diff show a note instead of actual comparison (TOML format limitation).
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 · 33 lines · 15 tokens per session scan A 396e33b3ff51

Subscribe to this mod's changes

sync-diff is a command published in the GitHub repository Leoyang183/sync-agents-settings (8 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 296 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 2026-08-31.