opencode-sync

opencode-sync is a skill for Claude Code from YoungLeadersDotTech/young-leaders-tech-marketplace. It costs 42 tokens per session (3,789 once invoked), scanned A, original, MIT.

A synchronisation tool for keeping coding-agent configuration usable in both Claude Code and OpenCode. OpenCode is another coding assistant that can read some shared project instructions.

In plain words
What is it for?
Generating OpenCode agents, commands, and MCP settings, importing marketplaces or repositories, validating both runtimes, and detecting mismatches.
Why use it?
It reduces differences between the two runtimes by generating supported files from one canonical source. It also checks rules and reports configuration drift, meaning the copies no longer match.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the opencode-sync plugin — 1 skill shipped together

Good fit Generating OpenCode agents, commands, and MCP settings, importing marketplaces or repositories, validating both runtimes, and detecting mismatches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/youngleadersdottech/young-leaders-tech-marketplace/opencode-sync
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.

Any agent
npx skills add YoungLeadersDotTech/young-leaders-tech-marketplace --skill opencode-sync
Clone the repo
git clone --depth 1 https://github.com/YoungLeadersDotTech/young-leaders-tech-marketplace

Made for: Claude Code.

Or install opencode-sync, the plugin that ships this one along with the rest of its 1 skill.

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 opencode-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/youngleadersdottech/young-leaders-tech-marketplace/opencode-sync/github.svg)](https://agentmods.dev/skills/youngleadersdottech/young-leaders-tech-marketplace/opencode-sync)
Your own site
<a href="https://agentmods.dev/skills/youngleadersdottech/young-leaders-tech-marketplace/opencode-sync"><img src="https://agentmods.dev/badge/skills/youngleadersdottech/young-leaders-tech-marketplace/opencode-sync/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for opencode-sync

Your own site · 80×15
<a href="https://agentmods.dev/skills/youngleadersdottech/young-leaders-tech-marketplace/opencode-sync"><img src="https://agentmods.dev/badge/skills/youngleadersdottech/young-leaders-tech-marketplace/opencode-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,789 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00042 $0.03789
Opus 5 $0.00021 $0.01895
Sonnet 5 $0.00008 $0.00758
Haiku 4.5 $0.00004 $0.00379

Measured 11d ago against content hash 0f36ffdf8b45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

opencode-sync 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 11d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/check_drift.py, scripts/ingest_source.py, scripts/sync_agents.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/opencode-sync/skills/opencode-sync/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

opencode-sync

Keeps one canonical source of truth (skills, agents, commands, MCP config, rules files) usable on BOTH Claude Code and OpenCode. Skills and rules are single-source by design (OpenCode reads .claude/skills/ and AGENTS.md natively); agents, commands, and MCP config are generated from the canonical Claude-side files by the bundled scripts. Plugin skills are exposed to OpenCode via skills.paths (see Mode E). The canonical copy always lives on the open side of the fence - if Claude Code access is capped, everything here still runs.

MANDATORY FIRST ACTION - Task Chain Bootstrap

On Claude Code, run these TaskCreate calls before anything else:

t0 = TaskCreate("Phase 0: Pre-Flight checks")
t1 = TaskCreate("Phase 1: Mode selection (Ingest / Sync / Validate / Drift / Setup)")
t2 = TaskCreate("Phase 2: Execute selected mode")
t3 = TaskCreate("Phase 3: Report, ledger, commit")

TaskUpdate(t1, addBlockedBy=[t0])
TaskUpdate(t2, addBlockedBy=[t1])
TaskUpdate(t3, addBlockedBy=[t2])

Mark t0 in_progress immediately, mark each phase completed at its boundary.

OpenCode or Cowork runtime: TaskCreate does not exist there. Mirror the same four phases as a todowrite checklist (OpenCode) or a visible markdown checklist (Cowork) instead. Full translation recipe: references/tool-translation.md. Do not skip phase tracking just because Task* is unavailable.

When to Use

  • Onboarding a marketplace, plugin, or repo so OpenCode can find and run its skills/agents/tools (Mode E)
  • Adding OpenCode support to a repo or plugin that currently targets Claude Code only
  • Converting Claude Code subagents into OpenCode agent files (frontmatter translation)
  • Checking whether skills are portable across both runtimes before shipping
  • Running a drift check after editing canonical sources, or wiring that check into CI

Skip when

  • Creating a brand new skill or agent from scratch - use the skills-toolkit creation workflows, then run this skill's Validate mode on the result
  • Syncing the local skill registry or marketplace versions - use aios-sync-skills and the 4/5-file version rule directly
  • Validating a single Claude-only skill with no OpenCode target - use skill-validation-workflow
  • Pushing pages or tickets to external systems - this skill only touches local runtime config and artifact files

Read the full file on GitHub · 194 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. 11d ago First seen · 194 lines · 42 tokens per session scan A 0f36ffdf8b45

Subscribe to this mod's changes

opencode-sync is a skill published in the GitHub repository YoungLeadersDotTech/young-leaders-tech-marketplace (10 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 3,789 once invoked, about $0.0002 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.