principles
v0.1.0by lyddonb · author: Beau Lyddon
principles is an Agent Plugin published by lyddonb. It packages 1 skill. We fetched the plugin.json from GitHub on 2026-10-21 and checked it against the official Agent Plugins 1.0.0 schema.
Twenty-four named engineering principles (prove it works, fix root causes, subtract before you add, build the lever, and more) that steer how agents design, build and verify, plus a benchmark checklist. One skill with one file per principle.
- Skills
- 1
- MCP servers
- 0
- Stars
- 0
- License
- MIT
- Repo created
- 2026-10-10
- Last pushed
- 2026-10-12
- Publisher type
- User
- Version
- 0.1.0
Links
Skills · 1
- principles
- Named engineering principles (prove it works, fix root causes, subtract before you add, build the lever, and 20 more) that steer how an agent designs, builds and verifies. Use when a task or the user names a principle, when beau-mode tells you to apply one, or when deciding how much to build, where…
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
principles · engineering · verification · design · rigor
Related by publisher and keywords
Beau's rigorous agent workflow. beau-mode routes each task to a playbook and the principles; skills for understanding (how, why, teach, recall), proof (verify-work, create- and maintain-verification-skill, swarm), design and planning (architect, arena, technical-writing), review and trails (interrogate, show-me-your-work), and improvement (reflect, correct, unslop) do the steps. Adapted from Lauren Tan's pstack to work in any agent.
Skills for engineering leaders, for design/RFC reviews and structured interview kits.
Everyday engineering skills that work in any agent, for commit messages and cross-tool session handoffs.
Up-to-date library and API documentation lookup via the Context7 MCP server, with a no-MCP fallback.
Engineering workflows for DeepSeek Harness: guided feature development with codebase exploration, architecture and review agents, legacy-system modernization driven by workflow scripts, interactive HTML playgrounds, frontend design direction, and a security-reviewer agent.
Engineering skills for issue backlog burn-down with runbook-driven validation and workspace setup, product mapping, build-failure diagnosis, complexity, consistency and conformance analysis, test design, scenario analysis, technical debt reviews, and controlled technical writing.
[](https://agentpluginsdirectory.com/plugins/principles)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.