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.
/plugin marketplace add rube-de/cc-skillsnpx agentmods add plugins/rube-de/cc-skills/cdtgit clone --depth 1 https://github.com/rube-de/cc-skillsWrote 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/rube-de/cc-skills/cdt)<a href="https://agentmods.dev/plugins/rube-de/cc-skills/cdt"><img src="https://agentmods.dev/badge/plugins/rube-de/cc-skills/cdt.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
cdt 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 today.
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.
What it actually says
{
"name": "cdt",
"description": "Multi-agent development workflow with five modes: plan, dev, full, auto, and bugfix. Uses Agent Teams for collaborative roles (Architect, PM, Developer, Tester, Reviewer) and a Researcher subagent for documentation lookups via Context7.",
"version": "2.14.0",
"source": "./plugins/cdt",
"category": "development",
"author": {
"name": "rube-de",
"url": "https://github.com/rube-de"
},
"keywords": [
"agent-teams",
"multi-agent",
"planning",
"development",
"code-review",
"testing"
]
}What it installs
The manifest is a name and a version. 1 skill, 5 commands, 1 agent, 4 hooks travel with it, and installing the plugin installs all of them — 445 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill cdt A 96 tokens
- Command bugfix A 55 tokens
- Command dev-task A 43 tokens
- Command plan-task A 31 tokens
- Command auto-task C 42 tokens
- Command full-task C 39 tokens
- Agent researcher A 139 tokens
- Hook UserPromptSubmit A not measured
- Hook PreToolUse A not measured
- Hook Stop A not measured
- Hook SessionStart A not measured
What ships with it
1 file beside marketplace.json#cdt in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed 16df96f2ebbd
- yesterday First seen · 19 lines scan A f1a2f9b5f08d
cdt is a plugin published in the GitHub repository rube-de/cc-skills (10 stars, last pushed yesterday), 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 2026-09-03.
Other plugins, from other repositories
agent-harness
Multi-agent harness for Claude Code: Planner→Generator→Evaluator sprints executed as background dynamic workflows (Agent-tool fallback), fable/opus/sonnet/haiku model routing with per-role reasoning effort, harness-engineering framework for design/diagnosis, and Anthropic 2026-04-04 P-G-E pattern.
gaia-marketplace
Security-first multi-agent orchestration for Claude Code. Distributes the Gaia plugin: specialized agents across the development lifecycle with codebase-aware context injection and risk-classified command gating.
hato
Carrier-pigeon messaging between Claude Code sessions — send messages and files, and get woken up by other sessions across your machines.
productionos
AI engineering OS for Claude Code and Codex — 80 agents, 41 commands, 18 hooks.
orodruin-labs marketplace
Plugin marketplace listing 1 plugin: nazgul.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.