**Current problem**: 669-line agent with embedded knowledge - Too token-heavy - Not conversational - Hard to maintain **Proposed solution**: Break into slash commands ``` .claude/commands/mokai/ ├── mokai-primer.md # Loads all MOKAI context ├── mokai-strategy.md # Strategic planning mode ├── mokai-compliance.md # Tenders/IPP mode ├── mokai-finance.md # Financial operations mode ├── mokai-operations.md # Daily ops mode ├── mokai-status.md ...
Scanned 9/2/2026
Install to Claude Code
npx -y skills add majiayu000/claude-skill-registry --skill mokai --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Mokai?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-mokai)More formats (shields.io, HTML) on the badges page.
---
Done: false
today: false
follow up: false
this week: true
back burner: false
ASAP: false
type: Task
status:
relation:
description:
effort:
ai-assigned: true
ai-ignore: false
ai-ask: false
priority:
agent:
slash-command:
urgent: false
---
**Current problem**: 669-line agent with embedded knowledge
- Too token-heavy
- Not conversational
- Hard to maintain
**Proposed solution**: Break into slash commands
```
.claude/commands/mokai/
├── mokai-primer.md # Loads all MOKAI context
├── mokai-strategy.md # Strategic planning mode
├── mokai-compliance.md # Tenders/IPP mode
├── mokai-finance.md # Financial operations mode
├── mokai-operations.md # Daily ops mode
├── mokai-status.md # Daily status (existing)
├── mokai-weekly.md # Weekly review (existing)
└── mokai-insights.md # Deep analysis (existing)
```
**Benefits**:
- Lightweight (50-100 lines each vs 669)
- Conversational (context loads once, persists)
- Flexible (mix modes as needed)
- Maintainable (update one without touching others)
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...