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 swingerman · Claude Skill · ★ 134
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is disciplined-agentic-engineering safe to install? View the security audit →
Disciplined Agentic Engineering — methodology marketplace for Claude Code ℹ️ Repo renamed: this marketplace was previously . Existing URLs continue to work via GitHub's automatic redirect — no action needed unless you want to update local remotes (). A Claude Code marketplace hosting the Disciplined Agentic Engineering (DAE) methodology kit — skills, agents, hooks, and commands that keep software engineers in charge of architecture, behavior decisions, and verification while AI agents do the typing. What is Disciplined Agentic Engineering? DAE is a methodology for engineering-led AI development. AI agents do the coding; software engineers stay in charge of architecture, performance, and feature validation. Discipline lives in the contracts at every layer (charter → ACs → specs → plans → verification) and in the loop-aware skills that enforce them. It's positioned in direct opposition to the failure mode of loose-boundary, weak-check agentic engineering — AI tools that produce code with no charter, no behavior contract, and no verification gates. DAE makes the boundaries explicit and the chec
| Stars | 134 |
| Forks | 9 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 72.9423735407052/100 |
| Last Updated | 2026-08-10 |
| Created | 2026-02-16 |
| Platforms | claude-code, python |
| Est. Tokens | ~17k |
These tools work well together with disciplined-agentic-engineering for enhanced workflows:
Looking for a disciplined-agentic-engineering alternative? If you're comparing disciplined-agentic-engineering 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.
AI agents that guide you from idea to working code, with you in control at every step.
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
Tu equipo de desarrolladores en un plugin. 10 agentes, 11 skills planas, 18 comandos /alfred-dev:*. Memoria pe
Use Claude Code like a Director, not a Programmer. MIT toolkit with Auto-Loop, guided setup, 27 commands, 14 a
Primes your project for peak Claude Code performance
Structured project lifecycle plugin for Claude Code — from idea to production with discipline, parallel agents
Explore other popular claude skill tools:
disciplined-agentic-engineering is Acceptance Test Driven Development for Claude Code — inspired by Uncle Bob's approach from empire-2025. It is categorized as a Claude Skill with 134 GitHub stars.
disciplined-agentic-engineering is primarily written in Python. It covers topics such as acceptance-testing, ai-development, atdd.
You can find installation instructions and usage details in the disciplined-agentic-engineering GitHub repository at github.com/swingerman/disciplined-agentic-engineering. The project has 134 stars and 9 forks, indicating an active community.
disciplined-agentic-engineering is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to disciplined-agentic-engineering on Agent Skills Hub include nWave, orchestkit, alfred-dev. 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: