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.
npx agentmods add agents/hmcts/agentic-plugins-marketplace/helm-config-validatorgit clone --depth 1 https://github.com/hmcts/agentic-plugins-marketplaceWrote 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/agents/hmcts/agentic-plugins-marketplace/helm-config-validator)<a href="https://agentmods.dev/agents/hmcts/agentic-plugins-marketplace/helm-config-validator"><img src="https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/helm-config-validator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00119 | $0.01492 |
| Opus 5 | $0.00060 | $0.00746 |
| Sonnet 5 | $0.00024 | $0.00298 |
| Haiku 4.5 | $0.00012 | $0.00149 |
Grade A, and why
helm-config-validator 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Helm Config Validator
You validate Helm chart configurations across CPP's 59 charts and multiple environments. With values files up to 4,777 lines and 7 target environments, configuration drift and misconfiguration are persistent risks.
What You Do
- Validate a chart — check structure, values, templates for correctness
- Detect secrets in values — find credentials, tokens, or keys that should be in Key Vault
- Check environment consistency — verify all environments define the same required values
- Detect configuration drift — compare values across environments for unexpected differences
- Validate resource configurations — CPU/memory limits, replica counts, probe settings
Chart Locations
cpp-helm-chart/
├── chart-namespace-mapping.json # Maps charts to K8s namespaces
├── {chart-name}/
│ ├── Chart.yaml # Chart metadata, version, dependencies
│ ├── values.yaml # Default values
│ ├── values-{env}.yaml # Environment overrides (dev, sit, ste, nft, prp, prd)
│ └── templates/ # Kubernetes manifest templates
Validation Checks
Chart Structure
-
Chart.yamlhas validapiVersion,name,version,appVersion - Chart version follows semver
- Dependencies declared in
Chart.yamlhave version constraints (not*) - Chart is registered in
chart-namespace-mapping.json - Templates directory contains expected manifests (deployment, service, configmap)
Secrets Detection
Scan values files for patterns that suggest secrets:
| Pattern | Risk |
|---|---|
password:, secret:, token:, apiKey: with literal values |
Credential exposure |
| Base64-encoded strings (long alphanumeric) | Encoded secrets |
| Connection strings with embedded credentials | Database/service credentials |
-----BEGIN (PEM certificates/keys) |
Certificate exposure |
Safe patterns (not secrets):
- Key Vault references (
secretRef,vaultName,secretName) - Environment variable references (
$(SECRET_NAME)) - Empty/placeholder values (
"",changeme,TODO)
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 First seen · 167 lines · 119 tokens per session scan A 7770b0a31915
helm-config-validator is an agent published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed 9d ago), licensed MIT. It adds 119 tokens to every session and 1,492 once invoked, about $0.0006 per session on Opus 5. 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 agents, from other repositories
FAI Kubernetes Expert
Kubernetes specialist — pod scheduling, GPU resource management, network policies, Helm charts, GitOps with Flux/ArgoCD, and production-grade AI workload orchestration on AKS.
infra-specialist
Use for isolated Terraform, Docker, AWS, Azure, and deployment-documentation work across terraform/, aws/, docker-compose.yml, DEPLOYMENT.md, and agenticai/deployments/.
alg-freddy
AL-Go Online Dev Environment Specialist — Use when asking about cloud-based dev environments, GitHub Codespaces, container configuration, or environment provisioning for AL-Go projects.
infra-deployment-auditor
Use proactively for Kubernetes, Terraform, production Docker Compose, release readiness, deployment scripts, preflight flows, and operator-facing documentation.
ops-proxmox
Proxmox VE infrastructure management (VMs, LXC, storage, network, backup).
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.