recommend

A guide for choosing the right utility function from es-toolkit, a JavaScript and TypeScript helper library.

In plain words
What is it for?
Use it to find functions for working with arrays, objects, strings, and other common data, including alternatives when replacing Lodash code.
Why use it?
It helps avoid writing manual code or choosing a function whose name or behavior does not match the task or installed library version.

Skill for Claude CodeCodex

▶ This Tech-CEO's Claude Code Toolkit Will Blow You Away Sean Kochel · about toss/es-toolkit · on YouTube →
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 skills/toss/es-toolkit/recommend
Any agent
npx skills add toss/es-toolkit --skill recommend
Clone the repo
git clone --depth 1 https://github.com/toss/es-toolkit

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,127 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 $0.00041 $0.01127
Opus 5 $0.00020 $0.00563
Sonnet 5 $0.00008 $0.00225
Haiku 4.5 $0.00004 $0.00113

Measured 2d ago against content hash 9f4a06411664, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recommend 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 2d 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.

es-toolkit-plugin/skills/recommend/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Function Recommendation

Recommend the most suitable es-toolkit function for the user's needs, grounded in source code and official documentation.

Input

$ARGUMENTS — A description of what the user needs, or a code snippet to analyze.

Why grounding matters

es-toolkit evolves faster than any training data can track. Always verify function existence, entry point, and behavior from the version installed in the user's project. The skill may be installed as a standalone directory, so never assume the es-toolkit repository or a sibling docs directory is available.

Workflow

1. Understand the requirement

Parse $ARGUMENTS to identify:

  • What operation the user wants to perform
  • What data types are involved (array, object, string, etc.)
  • Whether they might need lodash migration help (if so, suggest /es-toolkit:migrate)

2. Find candidates in the installed package

Run from the package that depends on es-toolkit. In a monorepo this is usually a workspace package, not the repository root. If the project uses Yarn Plug'n'Play, use yarn node instead of node.

Search runtime entry points with this command, replacing merge|assign with terms relevant to the request:

node --input-type=module -e "
import { createRequire } from 'node:module';

const require = createRequire(import.meta.url);
const pattern = /merge|assign/i;
const pkg = require('es-toolkit/package.json');
const entries = Object.keys(pkg.exports)
  .filter(subpath => subpath !== './package.json' && !subpath.includes('*'))
  .map(subpath => subpath === '.' ? 'es-toolkit' : 'es-toolkit/' + subpath.slice(2));
const modules = await Promise.all(entries.map(entry => import(entry).catch(() => null)));
if (modules.every(module => module == null)) {
  console.error('es-toolkit is not resolvable from ' + process.cwd());
  process.exit(1);
}
const matches = new Map();
for (let index = 0; index < modules.length; index++) {
  const module = modules[index];
  if (module == null) continue;
  for (const name of Object.keys(module)) {
    if (!pattern.test(name)) continue;
    matches.set(name, [...(matches.get(name) ?? []), entries[index]]);
  }
}
for (const [name, entryPoints] of [...matches].sort()) {
  console.log(name.padEnd(24), entryPoints.join(', '));
}
"

Read the full file on GitHub · 112 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. 2d ago First seen · 112 lines · 41 tokens per session scan A 9f4a06411664

Subscribe to this mod's changes

recommend is a skill published in the GitHub repository toss/es-toolkit (11,320 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,127 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 2026-08-30.

Related

Other skills, from other repositories

client-setup

Create a vanilla tRPC client with createTRPCClient (), configure link chain with httpBatchLink/httpLink, dynamic headers for auth, transformer on links (not client constructor). Infer types with inferRouterInputs and inferRouterOutputs. AbortController signal support. TRPCClientError typing.

trpc/trpc · 63 tokens

custom-features

Author a TanStack Table v9 feature plugin across every FeatureMap and API installation surface: state, options, column definitions, table, column, row, cell, header, row-model functions/caches, defaults, prototypes, and table/row/column instance data lifecycles. Load for initTableInstanceData, resetTableInstanceData…

TanStack/table · 93 tokens

effect-and-errors

Composing Effect programs, domain errors, HttpError, repository error types, or error propagation at HTTP boundaries.

latitude-dev/latitude-llm · 26 tokens

migrate-better-result-3

Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.

dmmulroy/better-result · 52 tokens

fast-typescript-check

Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…

internet-development/www-sacred · 84 tokens

typescript-magician

Designs complex generic types, refactors any types to strict alternatives, creates type guards and utility types, and resolves TypeScript compiler errors. Use when the user asks about TypeScript (TS) types, generics, type inference, type guards, removing any types, strict typing, type errors, infer, extends…

mcollina/skills · 108 tokens