adlc-agent-engineering
v2.4.0Agent engineering for teams building AI agents and LLM features: architecture patterns, tool design, eval suites, prompts as versioned code, and runtime guardrails.
By Shmulik Davar — BrAIght WaveLicense: MIT1 GitHub starsUpdated 1 hour ago
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 5 skill or MCP entries
- Source updated
- Oct 1, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install adlc-agent-engineering for Codex and Claude Code
codex plugin marketplace add shmulikdav/adlc-skills
codex plugin marketplace upgrade adlc-skills
codex plugin add adlc-agent-engineering@adlc-skillsPaste and run these commands in a terminal with Codex. They add and refresh the adlc-skills catalog, then install this plugin.
Compatibility: the page URL and API slug “adlc-agent-engineering” remain stable.
- Codex:
adlc-agent-engineering@agent-plugin-marketplace→adlc-agent-engineering@adlc-skills
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/shmulikdav/adlc-skillsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is adlc-agent-engineering/.
Plugin files
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json├── skills/agent-architecture/SKILL.md├── skills/agent-runtime-guardrails/SKILL.md├── skills/eval-suite-design/SKILL.md├── skills/prompt-versioning/SKILL.md└── skills/tool-design/SKILL.md
Included Skills5
Use when designing a new AI agent or LLM feature, when someone asks whether something should be an agent, or when an existing agent is too unreliable, slow, or expensive.
Use when shipping an agent to users or connecting it to real systems, after a red-team or prompt-injection finding, or when mapping an agent's controls to the OWASP Agentic Top 10.
Use when building evals for an agent or LLM feature, before changing models or prompts, when moving an agent from demo to production, or when asked how to know the agent got better or worse.
Use when prompts or model settings live in dashboards or chats without history, when a prompt or model change broke production behavior, or when setting up a change process for LLM features.
Use when building function-calling tools or an MCP server for agents, when an agent misuses, ignores, or loops on a tool, or when reviewing an agent's tool set.
Plugin manifests2
{
"name": "adlc-agent-engineering",
"version": "2.4.0",
"description": "Agent engineering for teams building AI agents and LLM features: architecture patterns, tool design, eval suites, prompts as versioned code, and runtime guardrails.",
"author": {
"name": "Shmulik Davar — BrAIght Wave",
"email": "[email protected]",
"url": "https://www.braightwave.com"
},
"homepage": "https://braightwave.com/adlc",
"repository": "https://github.com/shmulikdav/adlc-skills",
"license": "MIT",
"keywords": [
"adlc",
"agent-development-lifecycle",
"evals",
"tool-design",
"guardrails",
"llm-apps"
],
"skills": [
"./skills/",
"./workflows/"
],
"interface": {
"displayName": "ADLC Agent Engineering",
"shortDescription": "Building agents as products",
"longDescription": "Agent engineering for teams building AI agents and LLM features: architecture patterns, tool design, eval suites, prompts as versioned code, and runtime guardrails.",
"developerName": "BrAIght Wave",
"category": "Coding",
"capabilities": [
"Interactive",
"Write"
],
"websiteURL": "https://braightwave.com/adlc",
"defaultPrompt": [
"Run $build-evals",
"Run $design-agent",
"Run $red-team-agent"
]
}
}{
"name": "adlc-agent-engineering",
"displayName": "ADLC Agent Engineering",
"version": "2.4.0",
"description": "Agent engineering for teams building AI agents and LLM features: architecture patterns, tool design, eval suites, prompts as versioned code, and runtime guardrails.",
"author": {
"name": "Shmulik Davar — BrAIght Wave",
"email": "[email protected]",
"url": "https://www.braightwave.com"
},
"homepage": "https://github.com/shmulikdav/adlc-skills",
"repository": "https://github.com/shmulikdav/adlc-skills",
"license": "MIT",
"keywords": [
"adlc",
"agent-development-lifecycle",
"evals",
"tool-design",
"guardrails",
"llm-apps"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[adlc-agent-engineering on Agent Plugins Marketplace](https://pluginsmp.com/plugins/adlc-agent-engineering)