Token-efficient second opinion slash command /advice. Extracts decision point + artifact (≤150 lines), then fans out in parallel: (1) Opus subagent reviewer with fallback chain codex→agy→cursor, (2) /research on the decision topic, (3) /secondo multi-model opinion. Use instead of advisor() which ships the full conversation uncached.

2026-06-2427

ponytail

jleechanorg/claude-commands

Lazy senior-dev mode — the seven-rung ladder that decides whether to write code at all, whether to reuse code that already exists, and whether to prefer stdlib/platform/installed deps over a new dependency. Use before writing any code, every PR diff, every fix, every feature. Source attribution included.

2026-06-2427

runtime-activation-claim

jleechanorg/claude-commands

Use when making any "X is enabled" / "feature X works" / "cache works" claim in a running session — requires runtime probe output from the standard harness startup path, NOT a launchd/cron test that explicitly sets the activation env var.

2026-06-2427

self-hosted-runner-preflight

jleechanorg/claude-commands

Pre-flight checklist for self-hosted runner failures. Use when investigating low disk, missing runner, or stuck Green Gate on the jleechanorg/worldarchitect.ai fleet. Always verifies host-level container state, not just GitHub API.

2026-06-2427

test-tui-claude-feature-via-cmux

jleechanorg/claude-commands

When asked to verify whether a Claude Code feature works (especially slash commands, dialogs, pickers, status indicators), spawn a real interactive TUI session in cmux — never use `claude --print "/feature"` as a test, because --print is non-interactive and will always return "isn't available in this environment" regardless of whether the feature actually works.

2026-06-2427

ao-agent-shorthands

jleechanorg/claude-commands

Read ~/.hermes/agent-orchestrator.yaml BEFORE declaring an --agent <X> value unsupported. Lists plugin shorthands (wafer, minimax, agy).

2026-06-2127

name	disk-magician-claude
description	Run disk usage diagnostics, growth history logs, and automated cache/temp cleanup on development machines.
metadata	{"type":"skill","runtime":"claude"}

Disk Magician — Claude Skill

This skill teaches Claude how to use disk_magician to audit disk space, identify growth regressions, and perform cleanups.

Skill Integration & Commands

Snapshot Validation (Phase 0): Check the coverage and timeouts of the snapshot file located in your backup repository:
```
./disk_magician.sh audit --dry-run
```
Check the output to make sure coverage is >= 70% and there are no warnings.
Scan / Discover (Phase 1): Scan for directories > 5 GB not currently in the monitored configuration:
```
./disk_magician.sh discover
```
Audit Candidates (Phase 2): View cleanup candidates and regressions:
```
./disk_magician.sh audit
```
Safe Cleanup (Phase 3): Execute safe cache and temp cleanups (which deletes stale temporary PR clones, dev caches, and orphaned worktrees):
```
./disk_magician.sh clean
```
Destructive Cleanup (Phase 4): Interactively clear Docker VM disk images, Colima VMs, and old agent session folders:
```
./disk_magician.sh clean-all
```

Safety Constraints & Guardrails

Mtime Caution: Worktrees and agent sessions with modification time < 14 days require explicit WORKTREE APPROVED confirmation from the user before deletion.
Never-delete list: Do not delete ~/.codex/sessions, ~/.codex/sessions_archive/, ~/.codex/state*.sqlite, ~/.codex/log, or ~/.claude/projects directly. Always run cleanups through disk_magician.sh to ensure safety filters are respected.