Add Model Provider
openclaw/openclaw
Add and live-prove a model provider with non-interactive config one-liners, without exposing credentials.
Declare, inject and scope Ts.ED v8 providers and wire lifecycle hooks - @Injectable, @Module, @Controller, @Inject, the functional API (inject, injectMany, lazyInject, constant, refValue…
$ npx skills add tsedio/tsed --skill tsed-di -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tsedio/tsed tsed-di --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/tsedio/tsed.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/tsed/skills/tsed-di .claude/skills/tsed-di && 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 "tsed-di" agent skill from https://github.com/tsedio/tsed/tree/production/plugins/tsed/skills/tsed-di into .claude/skills/tsed-di/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsed-di", 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/tsedio/tsed/tree/production/plugins/tsed/skills/tsed-diType 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 tsedio/tsed --skill tsed-di -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tsedio/tsed tsed-di --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsedio/tsed.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/tsed/skills/tsed-di .agents/skills/tsed-di && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tsed-di" agent skill from https://github.com/tsedio/tsed/tree/production/plugins/tsed/skills/tsed-di into .agents/skills/tsed-di/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsed-di", 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 tsedio/tsed --skill tsed-di -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tsedio/tsed tsed-di --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsedio/tsed.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/tsed/skills/tsed-di .cursor/skills/tsed-di && 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 "tsed-di" agent skill from https://github.com/tsedio/tsed/tree/production/plugins/tsed/skills/tsed-di into .cursor/skills/tsed-di/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsed-di", 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/tsedio/tsed.git --path plugins/tsed/skills/tsed-di--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 tsedio/tsed --skill tsed-di -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tsedio/tsed tsed-di --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsedio/tsed.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/tsed/skills/tsed-di .gemini/skills/tsed-di && 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 "tsed-di" agent skill from https://github.com/tsedio/tsed/tree/production/plugins/tsed/skills/tsed-di into .gemini/skills/tsed-di/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsed-di", 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 tsedio/tsed tsed-diInstalls 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 tsedio/tsed --skill tsed-di -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tsedio/tsed.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/tsed/skills/tsed-di .github/skills/tsed-di && 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 "tsed-di" agent skill from https://github.com/tsedio/tsed/tree/production/plugins/tsed/skills/tsed-di into .github/skills/tsed-di/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsed-di", 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 tsedio/tsed --skill tsed-di -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tsedio/tsed tsed-di --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsedio/tsed.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/tsed/skills/tsed-di .opencode/skills/tsed-di && 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 "tsed-di" agent skill from https://github.com/tsedio/tsed/tree/production/plugins/tsed/skills/tsed-di into .opencode/skills/tsed-di/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsed-di", 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.
tsed-diDeclare, inject and scope Ts.ED v8 providers and wire lifecycle hooks - @Injectable, @Module, @Controller, @Inject, the functional API (inject, injectMany, lazyInject, constant, refValue…
Tsed Di is an agent skill from tsedio/tsed. Declare, inject and scope Ts.ED v8 providers and wire lifecycle hooks - @Injectable, @Module, @Controller, @Inject, the functional API (inject, injectMany, lazyInject, constant, refValue, injectable().factory/asyncFactory/class/value, injector, context, logger), ProviderScope, custom tokens, @tsed/hooks ($on, $emit, $asyncEmit, $alter) and request context. Use when writing services or modules with @tsed/di, fixing InjectionError, "Given token is undefined" or undefined injected properties, choosing a scope…
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/di-api.md`).
The repository describes itself as: :triangularruler: Ts.ED is a Node.js and TypeScript framework on top of Express to write your application with TypeScript (or ES6). It provides a lot of decorators and guideline… The licence is MIT.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit cf95a4e. 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.
Hosts in commands or code, which the agent is likely to contact:
tsed.devFrom 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.
Tsed Di loads about 2.1k tokens when it runs, and up to ~5.1k if it reads all its reference files. Until then it costs about 154 tokens; SKILL.md has 692 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 tsedio/tsed at commit cf95a4e, republished under its MIT licence (© tsedio). 692 words, ~2,099 tokens.
.claude/skills/tsed-di/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Register every class the framework must build, resolve dependencies through the injector, and never construct DI-managed classes with new.
Read the DI API reference for signatures, the hook order and the deprecated-API table. Depth: https://tsed.dev/docs/providers.md, https://tsed.dev/docs/custom-providers.md, https://tsed.dev/docs/hooks.md.
All symbols below come from @tsed/di. Decorators and the functional API are interchangeable; follow the style already used in the project.
import {Injectable, Inject, inject, injectable} from "@tsed/di";
import {UsersRepository} from "./UsersRepository.js";
@Injectable()
export class UsersService {
@Inject()
protected repository: UsersRepository; // decorator style
// or: private readonly repository = inject(UsersRepository); // functional style
}
// Functional registration, without the class decorator:
// export class UsersService { ... }
// injectable(UsersService);inject() works in class field initializers, constructors, factories and hooks of registered providers.inject() at module top level: it builds the provider before configuration, imports overrides and test mocks are loaded.@Injectable() and injectable(Class) on the same class.@Controller("/path"), or controller(Class).path("/path"). Routing belongs to tsed-controllers.@Injectable().@Module({imports: [...]}).@Interceptor() and @Intercept() are exported by @tsed/di.import {constant, injectable} from "@tsed/di";
export const DbConnection = injectable(Symbol.for("DbConnection"))
.asyncFactory(async () => {
const options = constant<DbOptions>("database");
return connect(options);
})
.hooks({$onDestroy: (connection) => connection.close()})
.token();
export type DbConnection = typeof DbConnection;.value(v), .factory(fn), .asyncFactory(fn), .class(Klass); chain .scope(), .deps(), .imports(), .hooks(), .type(), .alias(), and end with .token().inject(DbConnection) or @Inject(DbConnection) db: DbConnection.@Inject(TOKEN). A bare @Inject() only works when the TypeScript type is a class.export const RetryPolicy = Symbol("RetryPolicy") plus export interface RetryPolicy {...}, then injectable(RetryPolicy).class(TokenBucket).injectable(Foo).type(Bar) or @Injectable({type: Bar}), then injectMany<Bar>(Bar) or @Inject(Bar) bars: Bar[].@OverrideProvider(Original) on the replacement class, or imports: [{token, useClass}] in configuration.import {Injectable, ProviderScope, Scope} from "@tsed/di";
@Injectable()
@Scope(ProviderScope.REQUEST)
export class RequestCart {}
// functional: injectable(RequestCart).scope(ProviderScope.REQUEST);SINGLETON (default): one instance, built at startup.REQUEST: one instance per request. The controller and every provider on the injection chain must also be REQUEST; a singleton parent keeps the first instance forever.INSTANCE: a new instance on every injection. inject(Token, {rebuild: true}) forces a fresh one ad hoc.REQUEST scope when you only need per-request data.import {lazyInject} from "@tsed/di";
const service = await lazyInject(() => import("./ReportService.js")); // module must `export default` the classDecorator form: @LazyInject("ReportService", () => import("./ReportService.js")) reports: Promise<ReportService>. Only $onInit runs for lazy providers. Do not lazy-load controllers, middlewares, or providers that rely on other hooks.
import {Injectable, OnDestroy, OnInit} from "@tsed/di";
import {$asyncEmit, $on} from "@tsed/hooks";
@Injectable()
export class QueueService implements OnInit, OnDestroy {
async $onInit() {}
async $onDestroy() {}
$onReady() {}
}
$on("$onReady", () => {}); // subscribe without a class
await $asyncEmit("$orderCreated", [order]); // emit a custom hook; listeners are `$orderCreated(order)` methods$ on a provider is registered as a hook listener.$beforeInit → $onInit → $afterInit → $beforeRoutesInit → $onRoutesInit → $afterRoutesInit → $beforeListen → $afterListen → $onReady; per request $onRequest / $onResponse; shutdown $onDestroy.OnInit and OnDestroy types come from @tsed/di; BeforeInit, AfterInit, BeforeRoutesInit, OnRoutesInit, AfterRoutesInit, BeforeListen, AfterListen, OnReady come from @tsed/platform-http.$alter("$name", value, [args]) / $asyncAlter for hooks that transform a value. $emit is synchronous and does not await listeners.import {context} from "@tsed/di";
import type {PlatformContext} from "@tsed/platform-http";
const $ctx = context<PlatformContext>();
$ctx.logger.info({event: "LOOKUP", id: $ctx.request.params.id});@Context() $ctx: PlatformContext from @tsed/platform-params.context() or @InjectContext() $ctx?: PlatformContext from @tsed/di. Do not store $ctx on a singleton.$ctx.set(key, value) / $ctx.get(key). Outside a request, context() returns a detached DIContext, not the request.InjectionError or "Given token is undefined. Could mean a circular dependency problem": two files import each other. Extract the shared logic into a third provider, or resolve late with inject(Token) inside the method; never fix it with new.@Inject() typed as an interface resolves to Object and throws InvalidPropertyTokenError. Pass the token.undefined in the constructor under some compilers: set useDefineForClassFields: false and enable experimentalDecorators + emitDecoratorMetadata.$onInit; consumers receive the resolved value, not a promise. Do not await inject(TOKEN) in singletons.$onDestroy; other $ hooks are not called on them.imports.@tsed/common; use @tsed/di, @tsed/hooks, @tsed/platform-http, @tsed/platform-params.@Injectable/@Module/@Controller or injectable()/controller()).$onInit or a factory are closed in $onDestroy.registerProvider, injector.emit/alter/alterAsync, or @tsed/common import remains (see the reference table; use tsed-migration for v7 code).constant() / refValue() (tsed-configuration) and providers are tested through PlatformTest (tsed-testing).© tsedio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (references) in plugins/tsed/skills/tsed-di of tsedio/tsed.
Open the folder on GitHubat commit cf95a4e
Tsed Di 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 |
|---|---|---|---|---|---|---|
| Tsed Di this skilltsedio/tsed | 3.1k | — | ~2.1k | Automated safety check: Pass | MIT | |
| Add Model Provideropenclaw/openclaw | 392k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Prompt Injection Defensesickn33/agentic-awesome-skills | 47k | 2 repos | ~4.2k | Automated safety check: Warn | MIT | |
| OmniRoute Provider Managementdiegosouzapw/OmniRoute | 74k | — | ~2.4k | Automated safety check: Pass | MIT | |
| OmniRoute Providers CLIdiegosouzapw/OmniRoute | 74k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Detecting AI Model Prompt Injection Attacksmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.9k | Automated safety check: Warn | Apache-2.0 |
openclaw/openclaw
Add and live-prove a model provider with non-interactive config one-liners, without exposing credentials.
sickn33/agentic-awesome-skills
Defend AI systems against prompt injection and indirect prompt attacks using input controls, tool permissions, output validation, and isolation boundaries.
diegosouzapw/OmniRoute
Manages AI provider connections, API keys, OAuth flows and connection tests through OmniRoute's REST API across its 327-provider catalog.
diegosouzapw/OmniRoute
Command reference for managing provider connections in the omniroute gateway: browse the catalog, test and validate connections, rotate API keys and read per-provider metrics.
mukul975/Anthropic-Cybersecurity-Skills
Detects prompt injection using regex signature matching, heuristic scoring for structural anomalies, and DeBERTa-based transformer classification, flagging direct injections (system-prompt…
mukul975/Anthropic-Cybersecurity-Skills
Detect and defend against indirect prompt injection hidden in web pages, documents, and images consumed by an agent, via content extraction (HTML/PDF/OCR), normalization, and scanning with LLM…
tsedio/tsed
Create a production-ready Ts.ED platform adapter for a new HTTP framework or runtime, such as Hono, Elysia, Bun.serve, or a Node framework.
tsedio/tsed
Scaffolds Ts.ED v8 projects and generates files with the Ts.ED CLI v7, through its MCP server (tools set-workspace, init-project, list-templates, get-template, generate-file) or the tsed binary…
tsedio/tsed
Configure and bootstrap a Ts.ED v8 server - the @Configuration decorator or configuration() on the Server class, PlatformExpress/PlatformKoa/PlatformFastify.bootstrap, server options (mount…
tsedio/tsed
Locates authoritative Ts.ED v8 documentation and API reference instead of guessing framework APIs.
tsedio/tsed
Configure and use logging in a Ts.ED v8 application with @tsed/logger v8.
tsedio/tsed
Expose Model Context Protocol (MCP) tools, resources and prompts from a Ts.ED v8 application with @tsed/platform-mcp, over the application's HTTP endpoint or as a standalone stdio / Streamable HTTP…
Declare, inject and scope Ts.ED v8 providers and wire lifecycle hooks - @Injectable, @Module, @Controller, @Inject, the functional API (inject, injectMany, lazyInject, constant, refValue…. Tsed Di is an agent skill from tsedio/tsed.factory/asyncFactory/class/value, injector, context, logger), ProviderScope, custom tokens, @tsed/hooks ($on, $emit, $asyncEmit, $alter) and request context.
Tsed Di fits situations like: writing services; modules with @tsed/di; fixing InjectionError; given token is undefined.
Run `npx skills add tsedio/tsed --skill tsed-di -a claude-code`. Or copy the skill folder (plugins/tsed/skills/tsed-di in tsedio/tsed) into .claude/skills/tsed-di in your project. Claude Code loads it when a task matches its description.
Run `npx skills add tsedio/tsed --skill tsed-di -a codex`. Or copy the skill folder (plugins/tsed/skills/tsed-di in tsedio/tsed) into .agents/skills/tsed-di 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 tsedio/tsed --skill tsed-di -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tsed-di, .gemini/skills/tsed-di, .github/skills/tsed-di and .opencode/skills/tsed-di in your project.
SKILL.md names no scripts, command-line tools or credentials: Tsed Di is instructions for the agent only.
SKILL.md names 1 domain. In commands or code: tsed.dev; the agent is likely to contact it when it follows the instructions. 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.
Tsed Di is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Tsed Di: Add Model Provider (openclaw/openclaw, 392k stars), Prompt Injection Defense (sickn33/agentic-awesome-skills, 47k stars), OmniRoute Provider Management (diegosouzapw/OmniRoute, 74k stars) and OmniRoute Providers CLI (diegosouzapw/OmniRoute, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
tsedio (a GitHub organization) maintains it in tsedio/tsed, which has 3,088 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 8, 2026.
Source: tsedio/tsed on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.