Skip to main content

​
Overview

The @standardagents/skill package ships editable coding skills for Standard Agents work. Each skill is authored in plain .md files so teams can review, copy, and customize the guidance without changing a generated artifact. The first bundled skill is agentbuilder, which helps coding agents decide when to use:
  • defineModel
  • definePrompt
  • defineTool
  • defineAgent
  • defineHook
  • defineThreadEndpoint
  • dual_ai subagents

​
Installation

npx @standardagents/cli skill
This opens an interactive picker so you can choose the install target. Supported targets:
  • Codex: installs a skill folder into $CODEX_HOME/skills or ~/.codex/skills
  • Claude Code: installs a user subagent into ~/.claude/agents/agentbuilder.md
Use --force to overwrite an existing installed copy: 
npx @standardagents/cli skill --force
Use --dir to choose a different install root: 
npx @standardagents/cli skill --agent codex --dir ~/.codex/skills
npx @standardagents/cli skill --agent claude

​
Package Install

npm
npm install @standardagents/skill
pnpm
pnpm add @standardagents/skill
yarn
yarn add @standardagents/skill

​
Package Layout

node_modules/@standardagents/skill/
├── dist/
└── skills/
    └── agentbuilder/
        └── SKILL.md

​
Helper API

Use the package API when you want to inspect or install the bundled skill from Node: 
import {
  copySkill,
  listSkills,
  readSkillFile,
  resolveSkillDir,
} from "@standardagents/skill"

console.log(listSkills())
console.log(resolveSkillDir("agentbuilder"))

const markdown = await readSkillFile("agentbuilder")
await copySkill("agentbuilder", ".codex/skills", { overwrite: true })

​
Manual Editing

The skill content is intentionally stored as raw markdown. A common workflow is: 
cp -R node_modules/@standardagents/skill/skills/agentbuilder .codex/skills/agentbuilder
Then edit:
  • .codex/skills/agentbuilder/SKILL.md

​
What The agentbuilder Skill Covers

  • Choosing the right AgentBuilder primitive for a change
  • Keeping prompt logic, tool logic, and orchestration concerns separate
  • Knowing when subagents are warranted
  • Mapping changes to the correct workspace files
  • Applying the docs-and-tests checklist before landing behavior changes