Zod
jasonjgardner/blockbench-mcp-plugin
Zod schema validation best practices for type safety, parsing, and error handling.
A skill your agent uses when adding a new domain to Nuclear's plugin system, or implementing a host.
$ npx skills add nukeop/nuclear --skill host-pattern -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nukeop/nuclear host-pattern --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nukeop/nuclear.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/host-pattern .claude/skills/host-pattern && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "host-pattern" agent skill from https://github.com/nukeop/nuclear/tree/master/.agents/skills/host-pattern into .claude/skills/host-pattern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-pattern", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nukeop/nuclear/tree/master/.agents/skills/host-patternType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nukeop/nuclear --skill host-pattern -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nukeop/nuclear host-pattern --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nukeop/nuclear.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/host-pattern .agents/skills/host-pattern && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "host-pattern" agent skill from https://github.com/nukeop/nuclear/tree/master/.agents/skills/host-pattern into .agents/skills/host-pattern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-pattern", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nukeop/nuclear --skill host-pattern -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nukeop/nuclear host-pattern --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nukeop/nuclear.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/host-pattern .cursor/skills/host-pattern && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "host-pattern" agent skill from https://github.com/nukeop/nuclear/tree/master/.agents/skills/host-pattern into .cursor/skills/host-pattern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-pattern", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nukeop/nuclear.git --path .agents/skills/host-pattern--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nukeop/nuclear --skill host-pattern -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nukeop/nuclear host-pattern --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nukeop/nuclear.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/host-pattern .gemini/skills/host-pattern && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "host-pattern" agent skill from https://github.com/nukeop/nuclear/tree/master/.agents/skills/host-pattern into .gemini/skills/host-pattern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-pattern", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nukeop/nuclear host-patternInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nukeop/nuclear --skill host-pattern -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nukeop/nuclear.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/host-pattern .github/skills/host-pattern && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "host-pattern" agent skill from https://github.com/nukeop/nuclear/tree/master/.agents/skills/host-pattern into .github/skills/host-pattern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-pattern", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nukeop/nuclear --skill host-pattern -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nukeop/nuclear host-pattern --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nukeop/nuclear.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/host-pattern .opencode/skills/host-pattern && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "host-pattern" agent skill from https://github.com/nukeop/nuclear/tree/master/.agents/skills/host-pattern into .opencode/skills/host-pattern/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "host-pattern", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
host-patternA skill your agent uses when adding a new domain to Nuclear's plugin system, or implementing a host.
Host Pattern is an agent skill from nukeop/nuclear. Use when adding a new domain to Nuclear's plugin system, or implementing a host. Covers the host pattern (how player functionality is exposed to plugins), the host interface and API class structure, how hosts are implemented in the player, error handling conventions, and what files to create and modify. Trigger phrases include "add a domain", "new domain", "host implementation", "host pattern", "createPluginAPI".
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with Model Context Protocol. The repository describes itself as: Streaming music player that finds free music for you. The licence is AGPL-3.0.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 27904e9. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Host Pattern loads about 1.3k tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 264 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from nukeop/nuclear at commit 27904e9, republished under its AGPL-3.0 licence (© nukeop). 264 words, ~1,327 tokens.
.claude/skills/host-pattern/SKILL.md (or your agent's skills folder).Every feature area follows the same three-layer structure:
Plugins call methods on an API class (e.g. api.Queue.addToQueue()), which holds a reference to the host and delegates to it. Plugins never touch a host directly.
packages/plugin-sdk/)| Action | File | What |
|---|---|---|
| Create | src/types/yourDomain.ts | YourDomainHost interface + related types |
| Create | src/api/yourDomain.ts | YourDomainAPI class |
| Modify | src/api/index.ts | Add yourDomainHost option + YourDomain field to NuclearAPI |
| Modify | src/index.ts | Export types and API class |
packages/player/)| Action | File | What |
|---|---|---|
| Create | src/services/yourDomainHost.ts | Host implementation + singleton export |
| Modify | src/services/plugins/createPluginAPI.ts | Pass singleton to NuclearPluginAPI |
| Modify | src/services/logger.ts | Add domain to LOG_SCOPES (needed for reportError) |
If the domain needs shared model types: create packages/model/src/yourDomain.ts and re-export from packages/model/src/index.ts.
Every API class follows this structure.
// packages/plugin-sdk/src/api/yourDomain.ts
export class YourDomainAPI {
#host?: YourDomainHost;
constructor(host?: YourDomainHost) {
this.#host = host;
}
#withHost<T>(fn: (host: YourDomainHost) => T): T {
const host = this.#host;
if (!host) {
throw new Error('YourDomain host not available');
}
return fn(host);
}
yourMethod(arg: SomeType) {
return this.#withHost((host) => host.yourMethod(arg));
}
}Reference: packages/plugin-sdk/src/api/queue.ts, packages/plugin-sdk/src/api/dashboard.ts
// packages/plugin-sdk/src/api/index.ts
import type { YourDomainHost } from '../types/yourDomain';
import { YourDomainAPI } from './yourDomain';
// Add to class:
readonly YourDomain: YourDomainAPI;
// Add to constructor opts type:
yourDomainHost?: YourDomainHost;
// Add to constructor body:
this.YourDomain = new YourDomainAPI(opts?.yourDomainHost);// packages/player/src/services/plugins/createPluginAPI.ts
import { yourDomainHost } from '../../services/yourDomainHost';
// Add to NuclearPluginAPI constructor call:
yourDomainHost,Hosts bridge the SDK contract to whatever backs the domain. Most commonly a Zustand store:
// packages/player/src/services/yourDomainHost.ts
import type { YourDomainHost } from '@nuclearplayer/plugin-sdk';
import { useYourDomainStore } from '../stores/yourDomainStore';
export const createYourDomainHost = (): YourDomainHost => ({
yourMethod: (arg) => useYourDomainStore.getState().doThing(arg),
getState: () => useYourDomainStore.getState().value,
});
export const yourDomainHost = createYourDomainHost();A host can also have access to the provider registry (metadata, streaming, dashboard), resolving which registered provider to call. Two patterns:
Single provider (user picks one in Sources):
const getProvider = (providerId?: string) =>
providersHost.get<YourProvider>(
providerId ?? providersHost.getActive('yourkind'), 'yourkind',
);
export const createYourDomainHost = (): YourDomainHost => ({
async fetch(query, providerId?) {
const provider = getProvider(providerId);
if (!provider) throw new Error('No provider available');
return provider.fetch(query);
},
});Fan-out (aggregate across all providers - dashboard):
export const createYourDomainHost = (): YourDomainHost => ({
async fetchAll() {
const providers = providersHost.list('yourkind') as YourProvider[];
const results = await Promise.allSettled(providers.map(async (provider) => {
const items = await provider.fetch();
return { providerId: provider.id, providerName: provider.name, items };
}));
return results.filter(isFulfilled).map((r) => r.value);
},
});Reference: packages/player/src/services/metadataHost.ts (single), packages/player/src/services/dashboardHost.ts (fan-out)
reportError, return partial results.MissingCapabilityError: always a plugin bug. Single-provider domains throw it; fan-out domains log it and skip the offending provider.© nukeop, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/host-pattern of nukeop/nuclear.
Open the folder on GitHubat commit 27904e9
Host Pattern next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Host Pattern this skillnukeop/nuclear | 19k | — | ~1.3k | Automated safety check: Pass | AGPL-3.0 | |
| Zodjasonjgardner/blockbench-mcp-plugin | 488 | 3 repos | ~1.4k | Automated safety check: Pass | GPL-3.0 | |
| Logging Observabilitygetsentry/toolkit | 917 | — | ~2.6k | Automated safety check: Pass | Custom licence | |
| fp-go Logging PatternsIBM/fp-go | 2k | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | |
| Agent Tool Builderomer-metin/skills-for-antigravity | 162 | — | ~705 | Automated safety check: Pass | Apache-2.0 | |
| AWS Lambda Durable Functionsawslabs/agent-plugins | 912 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 |
jasonjgardner/blockbench-mcp-plugin
Zod schema validation best practices for type safety, parsing, and error handling.
getsentry/toolkit
Review code for correct logging and error handling patterns.
IBM/fp-go
Adds logging to fp-go functional pipelines with Tap operators, entry and exit logs and error context, so that logging never changes the value or error flowing through.
omer-metin/skills-for-antigravity
Tools are how AI agents interact with the world. An agent skill from omer-metin/skills-for-antigravity.
awslabs/agent-plugins
Build resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions.
davila7/claude-code-templates
Tools are how AI agents interact with the world. An agent skill from davila7/claude-code-templates.
nukeop/nuclear
A skill your agent uses when making a demo, tutorial, or feature video of Nuclear.
nukeop/nuclear
A skill your agent uses when creating new UI components in packages/ui.
nukeop/nuclear
A skill your agent uses when writing or editing documentation in packages/docs.
nukeop/nuclear
A skill your agent uses when writing, scaffolding, or modifying Nuclear plugins.
Works with
A skill your agent uses when adding a new domain to Nuclear's plugin system, or implementing a host. Host Pattern is an agent skill from nukeop/nuclear. Use when adding a new domain to Nuclear's plugin system, or implementing a host.
Host Pattern fits situations like: adding a new domain to Nuclears plugin system; implementing a host; phrases include add a domain; host implementation.
Run `npx skills add nukeop/nuclear --skill host-pattern -a claude-code`. Or copy the skill folder (.agents/skills/host-pattern in nukeop/nuclear) into .claude/skills/host-pattern in your project. Claude Code loads it when a task matches its description.
Run `npx skills add nukeop/nuclear --skill host-pattern -a codex`. Or copy the skill folder (.agents/skills/host-pattern in nukeop/nuclear) into .agents/skills/host-pattern in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nukeop/nuclear --skill host-pattern -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/host-pattern, .gemini/skills/host-pattern, .github/skills/host-pattern and .opencode/skills/host-pattern in your project.
SKILL.md names no scripts, command-line tools or credentials: Host Pattern is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Host Pattern is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Host Pattern: Zod (jasonjgardner/blockbench-mcp-plugin, 488 stars), Logging Observability (getsentry/toolkit, 917 stars), fp-go Logging Patterns (IBM/fp-go, 2k stars) and Agent Tool Builder (omer-metin/skills-for-antigravity, 162 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
nukeop (a GitHub user) maintains it in nukeop/nuclear, which has 18,611 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 6, 2026.
Source: nukeop/nuclear on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.