Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/davekilleen/DexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/davekilleen/dex/compound-engineering)<a href="https://agentmods.dev/plugins/davekilleen/dex/compound-engineering"><img src="https://agentmods.dev/badge/plugins/davekilleen/dex/compound-engineering/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/davekilleen/dex/compound-engineering"><img src="https://agentmods.dev/badge/plugins/davekilleen/dex/compound-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
compound-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- compound-engineering — 97% identical, 4 lines differ
- compound-engineering — 84% identical, 4 lines differ
What it actually says
{
"name": "compound-engineering",
"version": "2.28.0",
"description": "AI-powered development tools. 28 agents, 24 commands, 15 skills, 1 MCP server for code review, research, design, and workflow automation.",
"author": {
"name": "Kieran Klaassen",
"email": "[email protected]",
"url": "https://github.com/kieranklaassen"
},
"homepage": "https://every.to/source-code/my-ai-had-already-fixed-the-code-before-i-saw-it",
"repository": "https://github.com/EveryInc/compound-engineering-plugin",
"license": "MIT",
"keywords": [
"ai-powered",
"compound-engineering",
"workflow-automation",
"code-review",
"rails",
"ruby",
"python",
"typescript",
"knowledge-management",
"image-generation",
"agent-browser",
"browser-automation"
],
"mcpServers": {
"context7": {
"type": "http",
"url": "https://mcp.context7.com/mcp"
}
}
}
What it installs
The manifest is a name and a version. 17 skills, 19 commands travel with it, and installing the plugin installs all of them — 1,226 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill agent-native-architecture A 47 tokens
- Skill dspy-ruby A 81 tokens
- Skill compound-docs A 17 tokens
- Skill git-worktree A 39 tokens
- Skill creating-agent-skills A 44 tokens
- Skill dhh-rails-style A 115 tokens
- Skill file-todos A 49 tokens
- Skill gemini-imagegen A 81 tokens
- Skill agent-browser A 77 tokens
- Skill andrew-kane-gem-writer A 88 tokens
- Skill brainstorming A 76 tokens
- Skill every-style-editor A 44 tokens
- Skill rclone D 94 tokens
- Skill skill-creator A 45 tokens
- Skill frontend-design A 48 tokens
- Skill {{SKILL_NAME}} A 0 tokens
- Skill {{SKILL_NAME}} A 0 tokens
- Command agent-native-audit A 14 tokens
- Command test-browser A 14 tokens
- Command triage A 13 tokens
- Command xcode-test A 18 tokens
- Command release-docs A 14 tokens
- Command changelog A 14 tokens
- Command generate_command A 14 tokens
- Command deploy-docs A 13 tokens
- Command reproduce-bug A 20 tokens
- Command resolve_pr_parallel A 11 tokens
- Command resolve_parallel A 10 tokens
- Command resolve_todo_parallel A 13 tokens
- Command lfg A 7 tokens
- Command plan_review A 12 tokens
- Command report-bug B 13 tokens
- Command deepen-plan C 25 tokens
- Command feature-video C 17 tokens
- Command heal-skill A 20 tokens
- Command create-agent-skill A 19 tokens
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 34 lines scan A 3fc650aa791b
compound-engineering is a plugin published in the GitHub repository davekilleen/Dex (495 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
before-you-build
Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts.
data-validation-suite
Schema validation, data quality monitoring, streaming validation pipelines, and input validation for backend APIs.
dependency-management
Dependency auditing, version management, and security vulnerability scanning.
deployment-strategies
Deployment patterns, rollback automation, and infrastructure templates.
multi-cursor
Official Cursor SDK coding harness.
aio-monitoring-observability
Monitoring and observability strategy, implementation, and troubleshooting. Metrics design (Golden Signals, RED/USE), distributed tracing (OpenTelemetry), alerting, SLOs, dashboards, log aggregation, and tool selection. Includes 7 automation scripts and production-ready templates.