What is agent-install AGENTS.md?

General development rules for a TypeScript pnpm monorepo, meaning one repository containing multiple applications or packages. They define commands, file naming, type usage and code-style conventions.

Use them when adding or modifying packages, choosing file and variable names, and running project commands through the required tooling.

They keep contributions consistent and explain how to install dependencies and run scripts in this repository.

agent-install AGENTS.md — Instructions file by millionco

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 instructions/millionco/agent-install/agents-md

Clone the repo

git clone --depth 1 https://github.com/millionco/agent-install

Made for: Codex, OpenCode.

Per session 1,170 This file is loaded in full into every session.

When invoked 1,170 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.01170	$0.01170
Opus 5	$0.00585	$0.00585
Sonnet 5	$0.00234	$0.00234
Haiku 4.5	$0.00117	$0.00117

Measured 2d ago against content hash c473ba8b5500, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-install AGENTS.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 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.

AGENTS.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

General Rules

MUST: Use @antfu/ni. Use ni to install, nr SCRIPT_NAME to run. nun to uninstall.
MUST: Use TypeScript interfaces over types.
MUST: Keep all types in the global scope.
MUST: Use arrow functions over function declarations.
MUST: Default to NO comments. Only add a comment when the "why" is truly non-obvious — browser quirks, platform bugs, performance tradeoffs, fragile internal patching, or counter-intuitive design decisions. Never add comments that restate what the code does or what a well-named function/variable already conveys.
MUST: Use kebab-case for files.
MUST: Use descriptive names for variables (avoid shorthands, or 1-2 character names).
MUST: Do not type cast (as) unless absolutely necessary.
MUST: Remove unused code and don't repeat yourself.
MUST: Put all magic numbers in constants.ts using SCREAMING_SNAKE_CASE with unit suffixes (_MS, _PX).
MUST: Put small, focused utility functions in utils/ with one utility per file.
MUST: Use Boolean() over !!.

Development instructions

This is a pnpm monorepo with apps/ and packages/. No external services required.

Package layout

One package: packages/agent-install — agent-install on npm. It ships both the Node API (via subpath exports) and the CLI (via bin) from a single build.

src/
  index.ts            -> re-exports ./skill/index.ts (default = skill surface)
  skill.ts            -> ./skill/index.ts
  mcp.ts              -> ./mcp/index.ts
  agents-md.ts        -> ./agents-md/index.ts
  skill/              -> library: SKILL.md install, discovery, git/URL fetch
  mcp/                -> library: MCP server install across JSON/JSONC/YAML/TOML
  agents-md/          -> library: AGENTS.md section editor + CLAUDE.md symlink
  utils/              -> shared utilities
  cli/
    cli.ts            -> CLI entry (built to dist/cli.js; invoked via bin/agent-install.mjs shim)
    commands/
      skill/, mcp/, doc/
    utils/            -> CLI-only helpers (logger, formatters)
bin/
  agent-install.mjs   -> #!/usr/bin/env node shim that imports dist/cli.js

Read the full file on GitHub · 86 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.

2d ago First seen · 86 lines · 1,170 tokens per session scan A c473ba8b5500

Subscribe to this mod's changes

agent-install AGENTS.md is an instructions file published in the GitHub repository millionco/agent-install (53 stars, last pushed 2mo ago), licensed MIT. It adds 1,170 tokens to every session, about $0.0059 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.

Languages Testing agent mcps skills

agent-install AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

General Rules

Development instructions

Package layout

What this file has done since we first saw it

Other instructions, from other repositories

webflow-skills CLAUDE.md

rolecraft AGENTS.md

MathModelAgent CLAUDE.md

lime AGENTS.md

clean-code-skills clean-code.instructions.md

wtcraft CLAUDE.md