Stats
Actions
Tags
From loom
Use at the start of every session and before any implementation — Loom's three gates (plan-on-disk, verify-before-done, autonomous-by-default) and how to work in Drew's workspace.
How this skill is triggered — by the user, by Claude, or both
Slash command
/loom:using-loomThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Loom's constitution — the three gates and the no-approval override of superpowers — is the canonical **`AGENTS.md`** at the plugin root, injected into every session by Loom's SessionStart hook. It is Drew's tier-1 user instruction; follow it.
Loom's constitution — the three gates and the no-approval override of superpowers — is the canonical AGENTS.md at the plugin root, injected into every session by Loom's SessionStart hook. It is Drew's tier-1 user instruction; follow it.
In Claude Code specifically:
brainstorming, writing-plans, executing-plans, subagent-driven-development, systematic-debugging, verification-before-completion, requesting/receiving-code-review, finishing-a-development-branch — are your toolkit./loom:loom-autopilot.(The full gate text lives in AGENTS.md so it stays identical across Claude Code, Codex, Cursor, Gemini, and opencode.)
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub mountain-dr3w/loom --plugin loom