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 skills/runwhen-contrib/runwhen-platform-mcp/find-and-deploy-codebundlenpx skills add runwhen-contrib/runwhen-platform-mcp --skill find-and-deploy-codebundlegit clone --depth 1 https://github.com/runwhen-contrib/runwhen-platform-mcpWrote 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/skills/runwhen-contrib/runwhen-platform-mcp/find-and-deploy-codebundle)<a href="https://agentmods.dev/skills/runwhen-contrib/runwhen-platform-mcp/find-and-deploy-codebundle"><img src="https://agentmods.dev/badge/skills/runwhen-contrib/runwhen-platform-mcp/find-and-deploy-codebundle.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 | $0.00095 | $0.01537 |
| Opus 5 | $0.00048 | $0.00768 |
| Sonnet 5 | $0.00019 | $0.00307 |
| Haiku 4.5 | $0.00010 | $0.00154 |
Grade A, and why
find-and-deploy-codebundle 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 3d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find and Deploy a CodeBundle from the Registry
Search the RunWhen CodeBundle Registry for production-ready automation before writing a custom script. The registry contains hundreds of pre-built, tested codebundles for Kubernetes, cloud providers, databases, and more.
When to use this skill
- The user asks to "add monitoring for X" or "create a health check for Y"
- The user describes a task that sounds like common operational automation
- Before starting a custom
build-runwhen-taskworkflow — always check the registry first
Key concept: two different deployment paths
| Path | Tool | When to use |
|---|---|---|
| Registry codebundle | deploy_registry_codebundle |
Pre-built automation from the registry. Points to the codebundle's own git repo + robot file. No inline script. |
| Custom script | commit_slx |
Hand-written bash/python script. Uses the Tool Builder codebundle with an inline base64-encoded script. |
These are not interchangeable — the YAML structure is fundamentally
different. Registry codebundles use the codebundle's own runbook.robot /
sli.robot files from its codecollection git repo.
Workflow
1. Search the registry
search_registry(search="kubernetes pod health", platform="Kubernetes")
Search tips:
- Use natural language: "postgres connection pool", "gcp bucket permissions"
- Filter by
platformwhen you know it: "Kubernetes", "GCP", "AWS" - Filter by
tagsfor specifics: "GKE,KUBERNETES" or "EKS" - Review
tasksandslisin results to confirm the codebundle covers what the user needs
2. Get full codebundle details
If a result looks promising, fetch the full details:
get_registry_codebundle(
collection_slug="rw-cli-codecollection",
codebundle_slug="k8s-namespace-healthcheck"
)
Key fields to examine:
- tasks / slis: what the codebundle actually does
- user_variables: the config vars you need to provide (NAMESPACE, CONTEXT, etc.)
- support_tags: which platforms and services it covers
- access_level: "read-only" vs "read-write"
- runbook_path / sli_path: confirms whether runbook and/or SLI exist
- codecollection.git_url: the repo URL needed for deployment
- runbook_source_url: link to source code on GitHub
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.
- 3d ago First seen · 151 lines · 95 tokens per session scan A 30359d4e070e
find-and-deploy-codebundle is a skill published in the GitHub repository runwhen-contrib/runwhen-platform-mcp (1 stars, last pushed 20d ago), licensed Apache-2.0. It adds 95 tokens to every session and 1,537 once invoked, about $0.0005 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 skills, from other repositories
cluster-events
Analyze cluster-wide Kubernetes events to identify issues and patterns. Aggregates Warning events, detects high-frequency patterns, and correlates related events.
quota-debug
Diagnose Kubernetes native ResourceQuota and LimitRange admission rejections (exceeded quota, forbidden by LimitRange, FailedCreate). Checks namespace quotas, current usage, LimitRange constraints, and ReplicaSet events to identify why pods cannot be created. Not applicable to Volcano Queue — use…
volcano-diagnose-pod
Diagnose Volcano-managed Pod scheduling issues. Checks Pod status, PodGroup, events, and Queue to identify scheduling failures.
volcano-job-diagnose
Diagnose Volcano Job status and issues. Check Job phases, task statuses, PodGroup associations, and overall job health.
volcano-node-resources
Query cluster node resources for Volcano scheduling. Check allocatable CPU, memory, GPU, and current usage.
volcano-queue-diagnose
Diagnose Volcano Queue status and resource allocation. Check queue weights, deserved resources, allocated resources, and identify queue-related scheduling bottlenecks.