Is the Build Agent skill free?

Yes. The skill itself is free from LukeRenton/explore-claude-code. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Build Agent SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Build Agent?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Build Agent with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Build Agent

Scaffolds Claude Code subagent files with ordered frontmatter and a self-critique pass

by LukeRenton · LukeRenton/explore-claude-code

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · e5664ac

Fetched SKILL.md (HTTP 200) at .claude/skills/build-agent/SKILL.md; frontmatter parses with name+description, no scripts/deps, no security smells. Wrote 5 trigger phrasings and judged all 5 correctly (3 agent-creation/delegation asks fire; "build a REST API" and "write an SEO skill" correctly do not). Built baseline vs skill-following agent files: baseline had 3 frontmatter fields and a bland trigger-free description; the skill version had the 6 spec-ordered fields, color:purple, DO_NOT_TOUCH/MAY_EDIT zones, and explicit "Use when" delegation triggers. Noted the skill's body warns about brackets in argument-hint but not colons in description, which broke my first draft's YAML.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Build Agent does

Generates well-structured Claude Code subagent markdown files: enforces ordered frontmatter (name, description, model, color, tools, permissions, memory, hooks), adaptive Q&A to fill gaps, overlap checks against existing agents, and a self-critique pass. Triggers when the user asks to create a new agent, delegate a specialised role, or discuss team composition.

How to install Build Agent

git clone --depth 1 https://github.com/LukeRenton/explore-claude-code.git /tmp/build-agent-src
mkdir -p ~/.claude/skills
cp -R /tmp/build-agent-src/.claude/skills/build-agent ~/.claude/skills/build-agent
# SKILL.md lands at ~/.claude/skills/build-agent/SKILL.md
# Self-contained meta-skill: no scripts, deps, API keys, or external tools.
# It writes agent files into a project's .claude/agents/ ; optionally reads
# .claude/agents/core-orchestrator.md to register core-team agents.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Build Agent

/build-agent Scaffolds Claude Code subagent files with ordered frontmatter and a self-critique pass

It also activates on plain-language prompts like these:

Create a new agent for reviewing pull requests
Build a specialized agent for database migrations
Set up an agent with enforced coding standards

Frequently asked questions

Is the Build Agent skill free?: Yes. The skill itself is free from LukeRenton/explore-claude-code. SkillProof publishes the install command and an independent test verdict at no cost.
Does Build Agent work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Fetched SKILL.md (HTTP 200) at .claude/skills/build-agent/SKILL.md; frontmatter parses with name+description, no scripts/deps, no security smells. Wrote 5 trigger phrasings and judged all 5 correctly (3 agent-creation/delegation asks fire; "build a REST API" and "write an SEO skill" correctly do not). Built baseline vs skill-following agent files: baseline had 3 frontmatter fields and a bland trigger-free description; the skill version had the 6 spec-ordered fields, color:purple, DO_NOT_TOUCH/MAY_EDIT zones, and explicit "Use when" delegation triggers. Noted the skill's body warns about brackets in argument-hint but not colons in description, which broke my first draft's YAML.
What is the Build Agent SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Build Agent?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Build Agent with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.