Is the Goodcode skill free?

Yes. The skill itself is free from SpinaBuilds/goodcode. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Goodcode SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Goodcode?

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 Goodcode 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.

Goodcode

Portable exhaustive multi-agent audit/review protocol: roles, adversarial verify, loop-until-dry.

by SpinaBuilds · SpinaBuilds/goodcode

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · be0bd23

A/B'd on a throwaway 34-line Python file with a planted SQL injection, a missing-authz delete, and an off-by-one bug: unassisted baseline found the bugs but buried the missing-authz issue as a vague aside, while following the skill's role/verify/score protocol surfaced it as a verified, severity-ranked IDOR-shaped finding and raised a genuinely new open question (is_admin field exposure) baseline never touched.

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 4/5

What Goodcode does

A host-agnostic orchestration protocol (Claude Code, Codex, Cursor, OpenCode/OpenHands) for exhaustive audits, deep reviews, multi-source research, or large migrations: recon, a cheap baseline pass, a-priori worker roles cast by routing, adversarial refute-by-default verification, loop until no new findings appear, then dedup/score/synthesize with declared coverage caps. Triggers on '/goodcode', 'be exhaustive', 'orchestrate exhaustively', or any substantial task where completeness matters more than speed; explicitly skips trivial or conversational turns.

How to install Goodcode

git clone https://github.com/SpinaBuilds/goodcode.git
mkdir -p ~/.claude/skills
cp -r goodcode ~/.claude/skills/goodcode

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

Commands — how to trigger Goodcode

/goodcode Portable exhaustive multi-agent audit/review protocol: roles, adversarial verify, loop-until-dry.

It also activates on plain-language prompts like these:

Be exhaustive: find every bug in this file, not just the obvious ones
Do a deep adversarial review of this migration before I merge it
Orchestrate a full multi-pass audit of this authentication module

Frequently asked questions

Is the Goodcode skill free?: Yes. The skill itself is free from SpinaBuilds/goodcode. SkillProof publishes the install command and an independent test verdict at no cost.
Does Goodcode work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. A/B'd on a throwaway 34-line Python file with a planted SQL injection, a missing-authz delete, and an off-by-one bug: unassisted baseline found the bugs but buried the missing-authz issue as a vague aside, while following the skill's role/verify/score protocol surfaced it as a verified, severity-ranked IDOR-shaped finding and raised a genuinely new open question (is_admin field exposure) baseline never touched.
What is the Goodcode SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Goodcode?: 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 Goodcode 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.