sync-doctor

sync-doctor is a command for coding agents from Leoyang183/sync-agents-settings. It costs 18 tokens per session (624 once invoked), scanned A, original, MIT.

A command that checks whether MCP server settings match between Claude Code and other AI coding tools, and whether those settings contain parsing errors.

In plain words
What is it for?
Use it to check selected tools such as Gemini or Codex, inspect a JSON report in automated checks, exclude OAuth-only servers, or reconcile missing servers.
Why use it?
It helps find missing or broken server settings before they cause an agent to lose access to a tool. It can also repair differences, or preview the repair first.

Command

Part of the sync-agents-settings plugin — 1 skill, 8 commands shipped together

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-doctor
Clone the repo
git clone --depth 1 https://github.com/Leoyang183/sync-agents-settings

Or install sync-agents-settings, the plugin that ships this one along with the rest of its 1 skill, 8 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for sync-doctor

README.md
[![agentmods](https://agentmods.dev/badge/commands/leoyang183/sync-agents-settings/sync-doctor.svg)](https://agentmods.dev/commands/leoyang183/sync-agents-settings/sync-doctor)
Your own site
<a href="https://agentmods.dev/commands/leoyang183/sync-agents-settings/sync-doctor"><img src="https://agentmods.dev/badge/commands/leoyang183/sync-agents-settings/sync-doctor.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 624 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 $0.00018 $0.00624
Opus 5 $0.00009 $0.00312
Sonnet 5 $0.00004 $0.00125
Haiku 4.5 $0.00002 $0.00062

Measured 5d ago against content hash 0d4ae08ba762, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-doctor 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 5d 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.

commands/sync-doctor.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Check whether target MCP configs are in sync with Claude Code, without writing any files.

Arguments

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

Optional flags:

  • --skip-oauth — ignore OAuth-only servers from Claude source
  • --codex-home <path> — check project-level Codex config (e.g. ./.codex)
  • --kimi-home <path> — check project-level Kimi config (e.g. ./.kimi)
  • --vibe-home <path> — check project-level Vibe config (e.g. ./.vibe)
  • --qwen-home <path> — check project-level Qwen Code config
  • --amp-home <path> — check project-level Amp config
  • --cline-home <path> — check project-level Cline CLI config
  • --windsurf-home <path> — check project-level Windsurf config
  • --fix — if drift exists, auto-run reconcile to add missing servers
  • --dry-run — with --fix, preview only
  • --no-backup — with --fix, skip backup before writing
  • --report json — emit machine-readable JSON report

Execution Flow

  1. Parse targets and flags from user arguments.
  2. Run: npx sync-agents-settings doctor --target <targets> Add --skip-oauth / --codex-home / --kimi-home / --vibe-home / --qwen-home / --amp-home / --cline-home / --windsurf-home when specified.
  3. Present results per target:
    • No drift when fully in sync
    • Missing in <target> when Claude has servers not present in target
    • Extra in <target> when target has servers absent in Claude
    • Unavailable if target directory is missing
    • Parse error when target config is malformed
  4. If drift exists, suggest running /sync to reconcile.
    • Or run /sync-doctor --fix to reconcile automatically.

Error Handling

  • Exit code 1 means drift detected.
  • Exit code 2 means config parse error detected.
  • With --fix, failure reasons are specific: parse-related (target config parse error) or validation-related (validation errors detected) before exiting 2.
  • If npx fails: suggest npm install -g sync-agents-settings as fallback.
  • --report json cannot be used with --fix on doctor (use reconcile --report json instead).

Read the full file on GitHub · 49 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. 5d ago First seen · 49 lines · 18 tokens per session scan A 0d4ae08ba762

Subscribe to this mod's changes

sync-doctor is a command published in the GitHub repository Leoyang183/sync-agents-settings (8 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 624 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.