Is the Mythos Scaffold skill free?

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

What is the Mythos Scaffold SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Mythos Scaffold?

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 Mythos Scaffold 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.

Mythos Scaffold

Agentic-discipline scaffold: decomposition, verification, stuck-detection, plus research and migration domain modes.

by kasparovabi · kasparovabi/claude-mythos-scaffold

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 9d5e014

⚠ The source repository is archived — it won't receive fixes.

Applied to a small Flask-endpoint-plus-tests task, the scaffold's verification.md caught a real gap a baseline plan didn't have: reading test output for skipped/warning noise instead of trusting exit code 0, plus an explicit stuck-after-3-turns and never-rm-rf-without-asking gate.

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 7/10
Docs & honesty 4/5

What Mythos Scaffold does

A tiered library of process protocols (tool selection, decomposition, Plan-and-Execute/Reflexion/Self-Refine loop, headless-first verification, Ralph-loop failure recovery) plus two domain bundles for long-horizon research synthesis and codebase migration. Trigger on multi-step, long-horizon, or drift-prone work; explicitly skips itself on trivial one-liners and on Mythos-class models.

How to install Mythos Scaffold

git clone https://github.com/kasparovabi/claude-mythos-scaffold
mkdir -p ~/.claude/skills
cp -r claude-mythos-scaffold ~/.claude/skills/mythos-scaffold
cp claude-mythos-scaffold/commands/mythos-mode.md ~/.claude/commands/

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

Commands — how to trigger Mythos Scaffold

/mythos-scaffold Agentic-discipline scaffold: decomposition, verification, stuck-detection, plus research and migration domain modes.

It also activates on plain-language prompts like these:

Plan out adding a REST endpoint and tests without losing track
I need a disciplined approach for this long, multi-step migration
Help me avoid drifting off track during this research synthesis task

Frequently asked questions

Is the Mythos Scaffold skill free?: Yes. The skill itself is free from kasparovabi/claude-mythos-scaffold. SkillProof publishes the install command and an independent test verdict at no cost.
Does Mythos Scaffold work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Applied to a small Flask-endpoint-plus-tests task, the scaffold's verification.md caught a real gap a baseline plan didn't have: reading test output for skipped/warning noise instead of trusting exit code 0, plus an explicit stuck-after-3-turns and never-rm-rf-without-asking gate.
What is the Mythos Scaffold SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Mythos Scaffold?: 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 Mythos Scaffold 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.