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 hieuphung97 · Claude Skill · ★ 52
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is dely safe to install? View the security audit →
dely An automation-first delivery protocol for coding agents, packaged for Claude Code, Codex CLI, Grok Build, Antigravity CLI, Kiro CLI, Cursor Agent CLI, and GitHub Copilot CLI: it takes a request that may still be vague, brings it to an approved design contract, then automates sequential implementation, independent review, and pull-request preparation. Quickstart Four steps, and nothing more: Install in the harness. Open a session in the project. Invoke (optional). Ask for a change normally. You need one of Claude Code, Codex CLI, Grok Build, Antigravity CLI, Cursor Agent CLI, or GitHub Copilot CLI, each with plugin support, or Kiro CLI with the installer; Orca as the required, constant execution plane that launches and supervises the per-phase worker TUIs; and Git plus a GitHub remote for the project you run Dely against. preflights Orca and stops when the CLI is missing, the runtime cannot start, or a required capability is absent. Preflight Orca before installing a harness plugin: Per-harness install commands live under Install. Project pins
| Stars | 52 |
| Forks | 13 |
| Language | Shell |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 65.5058750725472/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-08 |
| Created | 2026-08-21 |
| Platforms | claude-code, cli, codex |
| Est. Tokens | ~15k |
These tools work well together with dely for enhanced workflows:
Looking for a dely alternative? If you're comparing dely 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.
Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Universal CLI for Agent Skills. Access 40,000+ skills from SkillsMP and sync them to Cursor, Claude Code, GitH
103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf,
Self-hosted terminal browser multiplexer for persistent shells and coding agents on Windows, macOS, and Linux.
Self-hosted browser workspace for remote AI coding agents—Codex, Claude Code, Gemini CLI, Grok Build, OpenCode
Explore other popular claude skill tools:
dely is Multi-harness control protocol that turns requests into approved design contracts, orchestrating isolated worker sessions for sequential implementation and independent code reviews under Orca supervis. It is categorized as a Claude Skill with 52 GitHub stars.
dely is primarily written in Shell. It covers topics such as agent-orchestration, agent-skills, ai-agents.
You can find installation instructions and usage details in the dely GitHub repository at github.com/hieuphung97/dely. The project has 52 stars and 13 forks, indicating an active community.
dely is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to dely on Agent Skills Hub include sample-well-architected-skills-and-steering, agent-skills, agent-skills-cli. 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: