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/nitinjain999/platform-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/nitinjain999/platform-skills/marketplace)<a href="https://agentmods.dev/plugins/nitinjain999/platform-skills/marketplace"><img src="https://agentmods.dev/badge/plugins/nitinjain999/platform-skills/marketplace/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/nitinjain999/platform-skills/marketplace"><img src="https://agentmods.dev/badge/plugins/nitinjain999/platform-skills/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
platform-skills marketplace 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 14d 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.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "platform-skills",
"description": "Platform engineering plugins for Claude Code: platform-skills, slash-command workflows for Kubernetes, GitOps, Terraform, CI/CD, cloud, security and observability with blast radius, validation and rollback in every answer; and platform-guardrails, enforcing hooks for session capture and an AI-governance policy gate.",
"owner": {
"name": "Nitin Jain",
"email": "[email protected]"
},
"plugins": [
{
"name": "platform-skills",
"version": "1.45.10",
"description": "Production-grade platform engineering handbook for Claude, Codex, and Cursor. 51 slash-command workflows: Kubernetes (baseline, RBAC, workload, debug), GitHub Actions (design, security, review, debug), Azure (Workload Identity, AKS, tagging, RBAC), OpenShift (SCC, Routes, GitOps, upgrades), Secrets (ESO, Sealed Secrets, rotation, audit), Helm, Terraform, Flux CD, Argo CD, Gateway API (ingress-nginx migration), AWS, Kyverno, OPA, KEDA, Karpenter, cluster upgrades (EKS version rollback), Flagger progressive delivery, Velero backup and restore drills, FinOps (Infracost, cost tags, OpenCost), supply chain security, Kubescape posture and operator (NSA, MITRE, CIS, SOC2), Falco, chaos engineering, DORA metrics, Datadog, Dynatrace, Linkerd, AWS MCP, Renovate, Checkov, Trivy, Zizmor workflow auditing, Kingfisher secret scanning and revocation, token optimization, and multi-agent scaffolding. Every answer includes blast radius, validation steps, and rollback plan.",
"author": {
"name": "Nitin Jain"
},
"license": "Apache-2.0",
"category": "development",
"keywords": [
"kubernetes",
"helm",
"helm-chart",
"helmchart",
"chart-lint",
"docker",
"containers",
"deployment",
"gitops",
"fluxcd",
"argocd",
"terraform",
"infrastructure-as-code",
"github-actions",
"ci-cd",
"aws",
The plugins it lists here
This marketplace lists 2 plugins kept in the same repository. Each has its own page, its own measurements and its own install command.
What ships with it
2 files beside marketplace.json 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.
- 14d ago Changed 9aba1b24df77
- 19d ago Changed 85219a4f30a0
- 20d ago Changed · +3 lines 328e5e9b8ab9
- 21d ago Changed · +1 lines c2d9deda5e8e
- 27d ago Changed · +17 lines f02c30b3eb3f
- 1mo ago Changed f698a40a6cdb
- 1mo ago Changed 5dc96b7b40c5
- 1mo ago Changed 50c2128778b7
- 2mo ago First seen · 203 lines scan A 27246a5b2a7e
platform-skills marketplace is a plugin published in the GitHub repository nitinjain999/platform-skills (71 stars, last pushed 2d ago), licensed Apache-2.0. 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.
platform-skills marketplace compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| platform-skills marketplacenitinjain999/platform-skills | Plugin | 71 | 2d ago | Apache-2.0 | A | — | Claude Code |
| frontend-designharnessprotocol/harness-kit | Plugin | 10 | 2d ago | Apache-2.0 | A | — | Claude Code |
| alex-confidentialqueelius/claude-anvil | Plugin | 2 | 5d ago | MIT | A | — | Claude Code |
| advisorsbackchainai/backchain-plugins | Plugin | 4 | 3mo ago | Apache-2.0 | A | — | Claude Code |
| ckw-designconnerkward/ckw-design-skill | Plugin | 9 | 4mo ago | MIT | A | — | Claude Code |
| deterministic-designconnerkward/deterministic-design-skill | Plugin | 4 | 4mo ago | MIT | A | — | Claude Code |
| cckshinhyukahn/cck | Plugin | 12 | 7mo ago | MIT | A | — | Claude Code |