opencode-plugin-compatibility

A compatibility checklist for connecting plugins between OpenCode and OpenClaw, two different AI tool ecosystems.

In plain words
What is it for?
It helps decide whether to use an existing equivalent, check package compatibility, or connect the two ecosystems through a separate HTTP service.
Why use it?
It prevents integrations from using incompatible plugin systems, software development kits, or in-process registries.

Cursor rule

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 rules/tashangkd/tashan-cursor-skills/opencode-plugin-compatibility
Clone the repo
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skills
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 761 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 $0.00074 $0.00761
Opus 5 $0.00037 $0.00380
Sonnet 5 $0.00015 $0.00152
Haiku 4.5 $0.00007 $0.00076

Measured 3d ago against content hash 705e6fd65b08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opencode-plugin-compatibility 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 3d 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.

rules/opencode-plugin-compatibility.mdc · 62 lines

What it actually says

opencode/openclaw 插件兼容性前置检查(opencode-plugin-compatibility)

触发条件:任何涉及 opencode、openclaw、openwork-server、tashan-workbench 集成第三方框架/插件的任务


核心问题

opencode(different-ai 生态)与 openclaw(开源社区生态)的插件体系完全不兼容

维度 opencode / openwork-server openclaw
Plugin SDK opencode 原生(无独立SDK) openclaw/plugin-sdk
工具注册方式 MCP(Model Context Protocol) definePluginEntry()
内存扩展 opencode.json plugin 字段 openclaw extension 目录
子智能体 opencode session API openclaw subagent SDK

强制检查(触发后立即执行)

在提出任何集成方案前,必须回答:

□ 我要集成的模块使用的是哪个生态的 SDK?

  • 来自 openclaw/plugin-sdk不可直接用于 openwork-server,需重新设计或通过 HTTP 桥接
  • 来自 opencode 原生(MCP/opencode.json)→ 可用于 openwork-server
  • 来自第三方 npm 包 → 检查依赖是否与 Bun 兼容

□ 目标集成的插件是否已有 opencode 生态的等效实现

  • 先搜索:opencode.json plugin 列表 + openwork hub skills
  • 有等效实现 → 直接用,不重新集成外部插件

□ 如果两套生态都需要同时使用,设计 HTTP 桥接层:

  • openwork-server → HTTP API → openclaw 独立服务
  • 不得共享同一进程内的 plugin registry

典型案例(已踩坑)

场景 错误做法 正确做法
接入 openclaw memory-core 直接注册到 openwork-server plugin 自建 BM25(workspace-search.ts)或通过 HTTP 调用独立 openclaw 服务
接入 openclaw subagents 直接注册 openclaw subagent SDK 在 openwork-server 实现 MCP 工具(tashan-mcp/brain_ask 模式)

违反后果

  • 可能浪费整个 Phase 的设计工作
  • 架构草稿需要完全推倒重写
  • 关卡B 不会发现此类问题(兼容性不在安全审查范围内)

变更记录

2026-03-21 — 初始创建

根因:tashan-workbench Phase B 设计时,架构师提出使用 openclaw memory-core,调研/设计后才发现与 openwork-server 生态不兼容,需要完全重设计,浪费大量工时。

验证状态:🔵 待验证(下次集成第三方框架时触发验证)

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. 3d ago First seen · 62 lines · 74 tokens per session scan A 705e6fd65b08

Subscribe to this mod's changes

opencode-plugin-compatibility is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (19 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 761 once invoked, about $0.0004 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 2026-08-30.