Skill Claude CodeCodex
Use when feature work needs isolation or before executing a plan: sets up an isolated workspace via native tools or a git worktree.
Autonomous AI orchestration with persistent memory, self-coordinating agent orgs, and a codebase knowledge graph and more.
This repository also configures its own agents. See what monomind tells them →
Skill Claude CodeCodex
Use when feature work needs isolation or before executing a plan: sets up an isolated workspace via native tools or a git worktree.
Skill Claude CodeCodex
Use when a request may need a Mastermind workflow such as planning, review, debugging, research, execution, organization work, or memory.
Skill Claude CodeCodex
Save and search cross-session knowledge in monomind's local memory. Use for "remember this", "store in memory", "search memory", "recall past decisions", "solved this before?".
Skill Claude CodeCodex
Generate images via Gemini's browser session using the monoagentcli tool, always scoped to the "monoes" profile — no API key, no billing, browser-automated.
Skill Claude Code needs its repo
Design, redesign, critique, audit or polish a frontend UI: landing pages, dashboards, components, forms; make it bolder or quieter; type, color, motion, a11y, design systems. Not for non-UI.
Skill Claude CodeCodex
Full technical writing workbench — writes, reviews, fixes, scaffolds, and audits project docs per Google Developer Documentation Style Guide + industry best practices. Autodiscovers doc tasks. Enforces tone, formatting, accessibility, inclusive language, readability, terminology consistency, Diátaxis doc typing, and…
Skill Claude CodeCodex
Whole-repo over-engineering audit: a ranked list of what to delete, simplify or replace with stdlib/native code. One-shot report, no fixes. Not for security audits.
Skill Claude CodeCodex
Collect every monolean: comment into a debt ledger so deliberate shortcuts and deferrals get tracked. Use for "monolean debt" or "what did we defer". Changes nothing.
Skill Claude CodeCodex
Quick-reference card for all monolean modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /monolean-help, "monolean help", "what monolean commands", "how do I use monolean".
Skill Claude Code
Forces the simplest solution that works: YAGNI, stdlib before dependencies. Levels lite/full/ultra. Use for "lean mode", "yagni", "do less", "minimal solution", or over-engineering.
Skill Claude CodeCodex
HTML-native GSAP animation system: timeline-driven, API-controllable browser animations with WebSocket/REST playback, effects and sequencing; no video rendering.
Skill Claude CodeCodex
Pair programming with Claude as driver, navigator, reviewer or mentor, for TDD, debugging, refactoring and learning, run in the conversation (there is no pair CLI).
Skill Claude CodeCodex
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Monomind swarms.
Skill Claude CodeCodex needs its repo
Create Claude Code skills with proper YAML frontmatter, progressive disclosure and directory layout; generate skill templates or explain the skill spec.
Skill Claude CodeCodex
Find the single best specialized agent for a task — the [PICK] line or the shared pick index (mcpmonomindpick / monomind pick), with a two-stage domain→agent fallback over the installed agents.
Skill Claude CodeCodex
Remove AI writing patterns from prose: predictable phrases, structural clichés, false agency, passive voice. Use when drafting, editing or reviewing text.
Skill Claude CodeCodex
Truth scoring and code quality verification with automatic rollback below a 0.95 confidence threshold, for checking agent output.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: