No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Optim-Agent · Claude Skill · ★ 444
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is optim-plans safe to install? View the security audit →
optim-plans Your planning loop and execution loop for agentic coding. It may be your best planner ever. turns "build me something" into a reviewed Markdown plan, records the decisions that shaped it, and keeps execution behind explicit approval. It gives Claude and Codex the two loops agentic coding act
| Stars | 444 |
| Forks | 1 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 71.8284653410642/100 |
| Last Updated | 2026-08-09 |
| Created | 2026-07-23 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~18k |
Looking for a optim-plans alternative? If you're comparing optim-plans with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and wor
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured
A VSCode extension that lets you find and install Agent Skills and MCP Apps to use with GitHub Copilot, Claude
An opinionated, AI-native development workflow for Java Enterprise — reusable Skills, Agents, Commands, and MC
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf,
Explore other popular claude skill tools:
optim-plans is Human-in-the-loop planning plugin for Claude and Codex: turn ideas into reviewed Markdown plans, record decisions, enforce explicit execution gates, and provide tested controller primitives for safer . It is categorized as a Claude Skill with 444 GitHub stars.
optim-plans is primarily written in Python. It covers topics such as agent-skills, brainstorming, claude-skills.
You can find installation instructions and usage details in the optim-plans GitHub repository at github.com/Optim-Agent/optim-plans. The project has 444 stars and 1 forks, indicating an active community.
optim-plans is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to optim-plans on Agent Skills Hub include babysitter, smart-ralph, copilot-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: