Is the Frontier Plan OpenCode Executor skill free?

Yes. The skill itself is free from alexdcd/Mafia-Claude-Skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Frontier Plan OpenCode Executor SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.

How do I install Frontier Plan OpenCode Executor?

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 Frontier Plan OpenCode Executor 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.

Frontier Plan OpenCode Executor

Reality-checks a frontier-model plan step-by-step so cheaper coding models don't thrash.

by alexdcd · alexdcd/Mafia-Claude-Skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 9759bb3

Fed it a 3-step plan that assumed an uninstalled `is-odd` package: blind baseline execution crashed with MODULE_NOT_FOUND, while the skill's repo reality-check caught the missing dependency and adapted to the repo's existing isEven() helper instead — test passed clean.

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 9/10
Docs & honesty 4/5

What Frontier Plan OpenCode Executor does

Turns a frontier-model-written implementation plan into a disciplined execution loop for cheaper coding models: validate each step against the real repo, implement one step at a time, run tiered verification, inspect the diff, and stop cleanly on repeated failure instead of blind-patching. Triggers on receiving a multi-step plan with specific file paths from Opus/GPT-5/etc., or being told to 'execute this plan step by step'. Its own README documents installation into OpenCode's skills directory rather than Claude's, but the SKILL.md is plain markdown that ported cleanly to a Claude Code test.

How to install Frontier Plan OpenCode Executor

git clone https://github.com/alexdcd/Mafia-Claude-Skills
cd Mafia-Claude-Skills
mkdir -p ~/.claude/skills
cp -r skills/frontier-plan-opencode-executor ~/.claude/skills/frontier-plan-opencode-executor

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

Commands — how to trigger Frontier Plan OpenCode Executor

/frontier-plan-opencode-executor Reality-checks a frontier-model plan step-by-step so cheaper coding models don't thrash.

It also activates on plain-language prompts like these:

Here's a detailed plan from GPT-5, please implement it step by step
Execute this plan step by step, validating each step against the repo
I have a frontier-model plan with file paths, run it against our code

Frequently asked questions

Is the Frontier Plan OpenCode Executor skill free?: Yes. The skill itself is free from alexdcd/Mafia-Claude-Skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Frontier Plan OpenCode Executor work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Fed it a 3-step plan that assumed an uninstalled `is-odd` package: blind baseline execution crashed with MODULE_NOT_FOUND, while the skill's repo reality-check caught the missing dependency and adapted to the repo's existing isEven() helper instead — test passed clean.
What is the Frontier Plan OpenCode Executor SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.
How do I install Frontier Plan OpenCode Executor?: 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 Frontier Plan OpenCode Executor 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.