sync-reconcile

sync-reconcile is a command for coding agents from Leoyang183/sync-agents-settings. It costs 18 tokens per session (449 once invoked), scanned A, original, MIT.

A command that checks MCP configurations for problems, compares them with other agents, and syncs only missing servers. MCP configurations describe connections between coding agents and external tools.

In plain words
What is it for?
Use /sync-reconcile for selected agents or servers, with options such as a preview, backups, OAuth handling, and machine-readable reports.
Why use it?
It combines validation, difference checking, and selective syncing in one workflow, reducing the chance of unsafe or unnecessary configuration changes.

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-reconcile
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-reconcile

README.md
[![agentmods](https://agentmods.dev/badge/commands/leoyang183/sync-agents-settings/sync-reconcile.svg)](https://agentmods.dev/commands/leoyang183/sync-agents-settings/sync-reconcile)
Your own site
<a href="https://agentmods.dev/commands/leoyang183/sync-agents-settings/sync-reconcile"><img src="https://agentmods.dev/badge/commands/leoyang183/sync-agents-settings/sync-reconcile.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 449 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 $0.00449
Opus 5 $0.00009 $0.00225
Sonnet 5 $0.00004 $0.00090
Haiku 4.5 $0.00002 $0.00045

Measured 5d ago against content hash 0d81f9ccc7d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-reconcile 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-reconcile.md · 48 lines

What it actually says

Run a safe one-shot reconcile pipeline:

  1. validate schema/capability
  2. detect drift
  3. sync only missing servers

Arguments

The user may pass target names: /sync-reconcile gemini codex If no targets are specified, reconcile all targets.

Optional flags:

  • --server <names...> or -s <names...> — reconcile only specified MCP servers by name
  • --dry-run — preview only, no writes
  • --no-backup — skip backup before write
  • --skip-oauth — ignore OAuth-only servers
  • --codex-home <path> — custom Codex config directory
  • --kimi-home <path> — custom Kimi config directory
  • --vibe-home <path> — custom Vibe config directory
  • --qwen-home <path> — custom Qwen Code config directory
  • --amp-home <path> — custom Amp config directory
  • --cline-home <path> — custom Cline CLI config directory
  • --windsurf-home <path> — custom Windsurf config directory
  • --report json — emit machine-readable JSON only (for CI)

Execution Flow

  1. Build command: npx sync-agents-settings reconcile --target <targets> Include user-provided flags.
  2. Run with --dry-run first if user didn't explicitly request real write.
  3. Present output:
    • validation errors/warnings
    • drift summary
    • servers added/skipped per target
  4. If dry-run was used and output is acceptable, ask user whether to run without --dry-run.
  5. In automation/CI, prefer --report json and parse the output programmatically.

Error Handling

  • Exit code 2: validation error or target parse error (must fix before sync).
  • Exit code 0: reconcile finished (or no drift).
  • If npx fails: suggest npm install -g sync-agents-settings as fallback.
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 · 48 lines · 18 tokens per session scan A 0d81f9ccc7d6

Subscribe to this mod's changes

sync-reconcile 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 449 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.