sync-tool

sync-tool is a command for Claude Code from WYZDevin/ChronoGeoLab. It costs 0 tokens per session (1,694 once invoked), scanned A, original, MIT.

A code-synchronization command for keeping geospatial analysis tools aligned between a frontend app and a backend service.

In plain words
What is it for?
Use it to check where a tool exists, add a frontend stub when only the backend has it, create a backend implementation when only the frontend has it, or confirm that both sides are already synchronized.
Why use it?
It removes the need to manually compare registrations and implementation files, reducing the risk that a tool appears in one side but not the other.

Command for Claude Code

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/wyzdevin/chronogeolab/sync-tool
Clone the repo
git clone --depth 1 https://github.com/WYZDevin/ChronoGeoLab

Made for: Claude Code.

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-tool

README.md
[![agentmods](https://agentmods.dev/badge/commands/wyzdevin/chronogeolab/sync-tool.svg)](https://agentmods.dev/commands/wyzdevin/chronogeolab/sync-tool)
Your own site
<a href="https://agentmods.dev/commands/wyzdevin/chronogeolab/sync-tool"><img src="https://agentmods.dev/badge/commands/wyzdevin/chronogeolab/sync-tool.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,694 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 $0.00000 $0.01694
Opus 5 $0.00000 $0.00847
Sonnet 5 $0.00000 $0.00339
Haiku 4.5 $0.00000 $0.00169

Measured 4d ago against content hash daff98f06d33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync-tool 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 4d 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.

.claude/commands/sync-tool.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Tool Between Frontend and Backend

You are synchronizing a geospatial analysis tool between the frontend (app/front-end/) and backend (app/back-end/) codebases. The user will provide a tool name or ID, and optionally the direction.

Determine Direction

First, figure out where the tool currently exists:

  1. Check app/back-end/app/tool_registry.py for backend registration
  2. Check app/front-end/src/tools/index.ts for frontend registration
  3. Check app/back-end/app/tools/ for the backend implementation file
  4. Check app/front-end/src/tools/ for the frontend implementation file

Based on what exists:

  • Tool exists only in backend → Register it in the frontend (stub only — no analyze() implementation unless the user explicitly asks)
  • Tool exists only in frontend → Create a full backend implementation and register it
  • Tool exists in both → Report that it's already synced, check if the tool IDs match across both sides

Direction A: Backend → Frontend (Registration Only)

When a tool exists in the backend but NOT in the frontend, create a frontend stub. This makes the tool visible in the UI and runnable via the backend, without implementing browser-side logic.

Steps

  1. Read the backend tool to extract: id, name, description, version, execution_policy, and what options/attributes it accepts in execute().

  2. Create frontend tool file at app/front-end/src/tools/<tool-name>-tool.ts:

import { SimpleTool, ToolOptionSchema } from '@/interfaces/simple-tool';
import { FeatureCollection } from '@/interfaces/data-interfaces';
import { AttributeMapping } from '@/interfaces/attribute-mapping';

export class <ToolClass> implements SimpleTool {
  id = '<tool-id>';                    // Must match backend tool.id exactly
  name = '<Tool Name>';
  description = '<description>';
  icon = '<emoji>';
  category = '<visualization|analysis|processing>' as const;
  version = '<version>';
  capabilities = {
    executionPolicy: 'backend_only' as const,  // Backend-only since no frontend implementation
  };

  // Only declare attributeMapping if the backend tool uses attributes
  attributeMapping?: AttributeMapping = { /* match backend attributes */ };

  getOptionSchema(): ToolOptionSchema[] {
    // Mirror the options the backend tool accepts
    return [ /* ... */ ];
  }

  async analyze(
    data: FeatureCollection,
    options: Record<string, unknown>,
    attributes?: AttributeMapping
  ): Promise<FeatureCollection[]> {
    // This tool runs on the backend only
    throw new Error('<Tool Name> requires the backend server. Enable backend mode to use this tool.');
  }
}

Read the full file on GitHub · 168 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. 4d ago First seen · 168 lines · 0 tokens per session scan A daff98f06d33

Subscribe to this mod's changes

sync-tool is a command published in the GitHub repository WYZDevin/ChronoGeoLab (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,694 tokens. 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.