setup

Installs the gsecure test-build layer into a project non-destructively and gathers project context.

1|1|Updated Jun 24, 2026
One-click install
npx skills add https://github.com/growmax/growmax-skills --skill setup-growmax
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: setup
Source: https://github.com/growmax/growmax-skills/tree/main/gsecure/skills/setup
Command: npx skills add https://github.com/growmax/growmax-skills --skill setup-growmax

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Setting up a testing layer in an existing project often means overwriting conventions, guessing at tooling, or leaving docs disconnected from reality. This Skill installs the gsecure test-build layer into a project without destroying anything, adopting whatever test tooling, structure, and gates already exist and asking the developer only for what is genuinely missing. ## Core Features & Use Cases - Non-destructive installation: Copies agents, skills, references, and standards with merge/no-clobber semantics, appending to AGENTS.md under a marker instead of replacing it. - Evidence-based recon: Reads manifests, configs, and repo structure to detect the stack, existing test tooling, test structure, knowledge base, issue tracker, and static gates — every claim cited with a file path or command output. - Stack neutrality: Never suggests or pre-selects test runners, frameworks, or assertion libraries; missing tooling is decided by the developer and recorded verbatim. - Use Case: A team wants to add a structured unit-testing workflow to an existing repo. Run this once from the repo root; it merges in the test-build layer, confirms the real gate set, fills the coverage plan and test-mechanics docs from verified findings, and proves the setup with one smoke test. ## Quick Start Ask the AI to run the gsecure setup skill from the root of your project repository to install the test-build layer and configure it for your project.

Frequently Asked Questions about setup

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I install the gsecure test-build layer into an existing project?▼

Run the setup skill once from the target project's repo root in the main session. It copies the agents, skills, references, and standards directories with merge semantics, appends to AGENTS.md under a marker, and never overwrites existing files.

Does gsecure setup overwrite my existing test configuration?▼

No. The skill is non-destructive: existing files are skipped, merged, or appended to, never overwritten. If it detects a prior gsecure install or a directory collision, it stops and asks the human before proceeding.

Will the setup skill recommend a test framework for my project?▼

No. The skill is strictly stack-neutral and never suggests test runners, frameworks, or assertion libraries. Existing tooling is adopted exactly as found; missing tooling is decided by the developer and recorded verbatim.

What happens if my project has no test tooling at all?▼

The skill asks the developer one consolidated question covering tooling, structure, gates, and coverage scope, offering no candidate lists. The answers are recorded verbatim in the coverage plan, and docs note that tooling is still awaited.

Which agent harnesses does gsecure setup support?▼

It installs shim trees for Claude Code (.claude/) and OpenCode (.opencode/) using no-clobber copies, while Hermes auto-loads AGENTS.md and needs no shims. Existing shims are left untouched during the merge.

Why does setup require running in the main session instead of a subagent?▼

The skill asks the human consolidated questions about missing tooling, structure, and gates, and those answers bind the generated docs. A subagent cannot conduct that interactive exchange, so it must run in the main session.