dale — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 lubluniky · Codex Skill · ★ 51

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is dale safe to install? View the security audit →

About dale

Dale A focused toolbox for Codex: think through a direction, map a repository, delegate independent work, verify the result, and resume work when needed. Install and update Run for the interactive skill picker. For an existing installation: Restart Codex after updating. The updater supports plugin-cache and standalone skill installations and preserves the previous plugin version for rollback. Headless options and the installer implementation are documented in tui/README.md. Updating skills does not require replacing your global . Execution in 0.5 Dale uses the calling agent and subagents by default. Delegate when a work unit can progress independently and saves time or supplies meaningful independent evidence. Small or tightly coupled work stays local. The coordinator works on a complementary part, integrates accepted artifacts, and verifies the final target. A graph is a set of outcomes, dependencies, and evidence obligations. It does not require a sidebar task for every node. Workers inherit the chosen model an

codexgraphorchestrationorchestration-frameworkorchestration-systemsskillskills

Quick Facts

Stars51
Forks3
LanguageHTML
CategoryCodex Skill
LicenseMPL-2.0
Quality Score63.4526606155428/100
Open Issues1
Last Updated2026-09-06
Created2026-07-23
Platformscodex
Est. Tokens~17k

Compatible Skills

These tools work well together with dale for enhanced workflows:

  • third-brain-v7-skills — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)
  • AgentSkillOS — semantic(0.21)+complementary+same_lang+similar_pop (52%)
  • swarms — semantic(0.33)+complementary+similar_pop+shared_platform (51%)

dale alternative? Top 6 similar tools

Looking for a dale alternative? If you're comparing dale with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • symfony-ux-skills by smnandre · ⭐ 166

    Symfony UX skills for Claude, Gemini, Codex, ... Live Component, Twig Component, Turbo, Stimulus

  • maestro by ReinaMacCredy · ⭐ 232

    Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f

  • aiwg by jmagly · ⭐ 213

    Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and mu

  • skillkit by maxvaega · ⭐ 146

    Implementing Skills functionality for your agents

  • my-ai-tools by jellydn · ⭐ 121

    Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, Open

  • sub-agents-mcp by shinpr · ⭐ 98

    Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular HTML Agent Tools

Frequently Asked Questions

What is dale?

dale is Graph orchestration for codex skills. It is categorized as a Codex Skill with 51 GitHub stars.

What programming language is dale written in?

dale is primarily written in HTML. It covers topics such as codex, graph, orchestration.

How do I install or use dale?

You can find installation instructions and usage details in the dale GitHub repository at github.com/lubluniky/dale. The project has 51 stars and 3 forks, indicating an active community.

What license does dale use?

dale is released under the MPL-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to dale?

The top alternatives to dale on Agent Skills Hub include symfony-ux-skills, maestro, aiwg. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools