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 terrylica/cc-skillsnpx agentmods add plugins/terrylica/cc-skills/devops-toolsgit clone --depth 1 https://github.com/terrylica/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/terrylica/cc-skills/devops-tools)<a href="https://agentmods.dev/plugins/terrylica/cc-skills/devops-tools"><img src="https://agentmods.dev/badge/plugins/terrylica/cc-skills/devops-tools.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
devops-tools 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 yesterday.
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": "devops-tools",
"description": "DevOps automation: ClickHouse, Doppler, MLflow, Cloudflare Workers, pueue orchestration, notifications, session recovery, MiniMax consensus analysis",
"version": "30.1.0",
"source": "./plugins/devops-tools",
"category": "devops",
"author": {
"name": "Terry Li",
"url": "https://github.com/terrylica"
},
"keywords": [
"doppler",
"credentials",
"secrets",
"mlflow",
"session-recovery",
"session-blind-spots",
"consensus-analysis",
"minimax",
"pushover",
"watchexec",
"notifications",
"loguru",
"platformdirs",
"structured-logging",
"jsonl",
"project-directory-migration",
"proxy",
"oauth",
"claude-code-proxy",
"anthropic-base-url",
"model-routing"
],
"strict": false
}What it installs
The manifest is a name and a version. 24 skills travel with it, and installing the plugin installs all of them — 953 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill cloudflare-workers-publish A 21 tokens
- Skill distributed-job-safety A 22 tokens
- Skill ml-failfast-validation A 36 tokens
- Skill python-logging-best-practices A 34 tokens
- Skill worktree-manager A 35 tokens
- Skill clickhouse-pydantic-config A 38 tokens
- Skill ml-data-pipeline-architecture A 38 tokens
- Skill python-memory-safe-scripts A 197 tokens
- Skill agentic-process-monitor A 28 tokens
- Skill doppler-secret-validation A 31 tokens
- Skill mlflow-python A 31 tokens
- Skill project-directory-migration A 29 tokens
- Skill session-debrief A 31 tokens
- Skill doppler-workflows A 28 tokens
- Skill macos-fda-grant-helper A 71 tokens
- Skill disk-hygiene B 34 tokens
- Skill pueue-job-orchestration B 41 tokens
- Skill session-chronicle B 27 tokens
- Skill claude-code-proxy-patterns B 23 tokens
- Skill macbook-desktop-mode B 33 tokens
- Skill clickhouse-cloud-management B 32 tokens
- Skill dual-channel-watchexec B 35 tokens
- Skill session-recovery B 28 tokens
- Skill firecrawl-research-patterns C 30 tokens
What ships with it
3 files beside marketplace.json#devops-tools 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.
- yesterday First seen · 35 lines scan A c32437d59196
devops-tools is a plugin published in the GitHub repository terrylica/cc-skills (62 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 2026-09-05.
Other plugins, from other repositories
oracle-ai
Enterprise AI architecture patterns using Oracle Cloud Infrastructure.
local-ai
From nothing to a working AI setup you own. Scans the machine for models that fit, installs and wires up the right app with consent at every download, shares it over a private URL, and rents a cloud GPU when a model is too big. Needs shell access.
databricks
Databricks skills for the CLI, Apps, Lakebase, Model Serving, Lakeflow Jobs, Spark Declarative Pipelines, Declarative Automation Bundles (DABs), and classic-to-serverless migration.
orchestra
Skills for working with Orchestra data pipelines — diagnose and fix failed runs, triage with a merge gate, author pipeline YAML, set up dbt Slim CI, configure dbt state-aware orchestration (source freshness and buildafter), run Snowflake data-quality tests, review a workspace against best practices, and merge duplicat.
cloud-infrastructure
Cloud architecture design for AWS/Azure/GCP, Kubernetes cluster configuration, Terraform infrastructure-as-code, hybrid cloud networking, and multi-cloud cost optimization.
machine-learning
ML engineering agents providing expertise in MLOps, model deployment, and inference optimization.