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/datum-cloud/claude-code-pluginsWrote 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/datum-cloud/claude-code-plugins/datum-platform)<a href="https://agentmods.dev/plugins/datum-cloud/claude-code-plugins/datum-platform"><img src="https://agentmods.dev/badge/plugins/datum-cloud/claude-code-plugins/datum-platform/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/datum-cloud/claude-code-plugins/datum-platform"><img src="https://agentmods.dev/badge/plugins/datum-cloud/claude-code-plugins/datum-platform.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
datum-platform 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 4d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What it installs
The manifest is a name and a version. 34 skills, 8 commands, 16 agents, 2 hooks travel with it, and installing the plugin installs all of them — 3,127 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill warden A 111 tokens
- Skill pr-conventions A 47 tokens
- Skill c4-diagrams A 33 tokens
- Skill clear-writing A 62 tokens
- Skill capability-activity A 43 tokens
- Skill capability-insights A 39 tokens
- Skill milo-iam A 37 tokens
- Skill release A 70 tokens
- Skill capability-quota A 37 tokens
- Skill learning-engine A 41 tokens
- Skill model-tiers A 73 tokens
- Skill pr-review-loop A 128 tokens
- Skill controller-runtime-patterns A 37 tokens
- Skill fluxcd-deployment A 40 tokens
- Skill pipeline A 35 tokens
- Skill trends A 26 tokens
- Skill user-corrections A 36 tokens
- Skill agpl-compliance A 132 tokens
- Skill capability-index A 36 tokens
- Skill commit-conventions A 34 tokens
- Skill operational-review A 53 tokens
- Skill patterns A 25 tokens
- Skill pipeline-conductor A 33 tokens
- Skill platform-knowledge A 42 tokens
- Skill deploy A 27 tokens
- Skill review A 27 tokens
- Skill runbooks A 39 tokens
- Skill capability-telemetry A 33 tokens
- Skill datum-ci A 33 tokens
- Skill go-conventions A 34 tokens
- Skill k8s-apiserver-patterns A 46 tokens
- Skill design-tokens A 36 tokens
- Skill kustomize-patterns A 31 tokens
- Skill evolve B 38 tokens
- Command corrections A 28 tokens
- Command pipeline A 35 tokens
- Command trends A 26 tokens
- Command patterns A 25 tokens
- Command deploy A 27 tokens
- Command review A 27 tokens
- Command pr-review A 44 tokens
- Command evolve B 38 tokens
- Agent sre A 71 tokens
- Agent api-dev A 70 tokens
- Agent code-reviewer A 109 tokens
- Agent frontend-dev A 55 tokens
- Agent pr-conventions-reviewer A 95 tokens
- Agent test-engineer A 58 tokens
- Agent bookkeeper A 74 tokens
- Agent plan A 52 tokens
- Agent pr-adversary A 76 tokens
- Agent tech-writer A 74 tokens
- Agent gap-verifier A 81 tokens
- Agent pr-rebaser A 76 tokens
- Agent pr-rereviewer A 78 tokens
- Agent operational-reviewer A 99 tokens
- Agent rollout-verifier A 78 tokens
- Agent pr-review-fixer B 137 tokens
- Hook PreToolUse A not measured
- Hook PostToolUse A not measured
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.
- 4d ago Changed a3daf4f4c852
- 1mo ago Changed e1c86dc88006
- 1mo ago Changed ab2cb8274da1
- 1mo ago Changed 12700a0c4862
- 1mo ago Changed 30a6052e70d4
- 1mo ago Changed 46985267f5df
- 1mo ago Changed 7ee591f9680f
- 1mo ago Changed 1fe8a68fd9c2
- 1mo ago First seen · 22 lines scan A 0ccfa41c26a9
datum-platform is a plugin published in the GitHub repository datum-cloud/claude-code-plugins (2 stars, last pushed 5d ago), with no licence file. 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 2026-08-31.
Other plugins, from other repositories
agent-sandboxing
Agent sandboxing for AI coding agents: microVM and kernel-isolated execution environments. Index skill (sandbox) routes to substrate-specific paths. Currently covers the kubernetes-sigs/agent-sandbox path on kind, GKE, and kina (Kubernetes-in-Apple-Containers), with Kata, gVisor, and Apple Container microVM substrates.
ensemble-infrastructure
Infrastructure management for AWS, Kubernetes, Docker, Helm, Fly.io.
daytona
Creates and manages isolated cloud sandboxes (secure code execution environments with dedicated runtimes) on the Daytona platform.
security-hardening
System hardening and CIS Benchmark assessment for Linux and Windows hosts, containers, Kubernetes, web servers, databases, and cloud accounts, with implementation and verification steps.
open-forge
Self-host open-source apps on your own cloud, your own VPS, your own Kubernetes cluster, a PaaS, or your own laptop. Chat-friendly interface to existing tools (aws, az, hcloud, doctl, gcloud, flyctl, kubectl, helm, podman, docker, lume, tailscale, terraform, cdk, ssh, gh) — Claude runs every command; you only answer…
agentic-workflows
Intelligent multi-agent swarms for automation - Ansible collections, Kubernetes operators, Terraform modules.