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.
npx agentmods add instructions/toss/es-toolkit/claude-mdgit clone --depth 1 https://github.com/toss/es-toolkitWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00648 | $0.00648 |
| Opus 5 | $0.00324 | $0.00324 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
es-toolkit CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Instructions for AI assistants working on es-toolkit.
Language
This is a global project with users speaking various languages. When producing non-code output (explanations, reviews, reports), respond in the user's preferred language.
Quick Reference
corepack enable && yarn install # Setup
yarn vitest run # Tests
yarn vitest run src/array/chunk # Test specific function
yarn lint # ESLint
tsc --noEmit # Typecheck
Structure
src/{category}/{fn}.ts # Implementation (array, bigint, function, math, object, predicate, promise, set, string, util, error, map)
src/{category}/{fn}.spec.ts # Tests (vitest)
src/compat/{category}/{fn}.ts # Lodash-compatible variant
tests/types/compat.spec-d.ts # Type tests against @types/lodash (yarn workspace type-tests test)
docs/reference/{category}/{fn}.md # English
docs/ko/reference/{category}/{fn}.md # Korean
docs/ja/reference/{category}/{fn}.md # Japanese
docs/zh_hans/reference/{category}/{fn}.md # Chinese
Design Principles
- Performance: Must match or beat lodash.
- Simplicity: Simplest interface for the 85% use case. No complex options.
- Don't implement: Functions replaceable by modern JS (
Array.isArray,Number.isNaN,Math.min), or TC39 Stage 3+ proposals. - es-toolkit vs compat:
es-toolkitis the strict, opinionated API.es-toolkit/compatmatches lodash behavior exactly for migration. Compat is feature-complete — no new functions are being added. Only behavior inconsistency fixes against lodash are accepted. - What we accept: New functions need an accepted discussion first, performance work needs benchmark results, and refactoring-only changes are not accepted. See
.github/CONTRIBUTING.md.
Coding Conventions
forloops overreduce(local mutation is fine)- Built-in JS over custom helpers (
Array.isArray(), notisArray()) - Type params:
Telements,Kkeys,Eerrors readonly T[]for array params that aren't mutated- Detailed JSDoc with
@template,@param,@returns,@throws,@example
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.
- 3d ago First seen · 54 lines · 648 tokens per session scan A 4573eab9360e
es-toolkit CLAUDE.md is an instructions file published in the GitHub repository toss/es-toolkit (11,320 stars, last pushed 2d ago), licensed MIT. It adds 648 tokens to every session, about $0.0032 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.