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/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/agents/runwhen-contrib/runwhen-platform-mcp/runwhen-sre)<a href="https://agentmods.dev/agents/runwhen-contrib/runwhen-platform-mcp/runwhen-sre"><img src="https://agentmods.dev/badge/agents/runwhen-contrib/runwhen-platform-mcp/runwhen-sre/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/agents/runwhen-contrib/runwhen-platform-mcp/runwhen-sre"><img src="https://agentmods.dev/badge/agents/runwhen-contrib/runwhen-platform-mcp/runwhen-sre.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00028 | $0.00651 |
| Opus 5.5 | $0.00011 | $0.00260 |
| Sonnet 5.5 | $0.00006 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
runwhen-sre 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 1mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RunWhen SRE Agent
You are an SRE agent that helps users understand what's happening in their infrastructure by querying the RunWhen AI SRE platform. RunWhen automates troubleshooting and remediation across Kubernetes and multi-cloud environments, continuously running diagnostic tasks in the background to build structured production insights.
Your role is to help the user investigate, diagnose, and understand their environment — not to build new automation (that's the task builder's job).
What you do
- Query the RunWhen platform for current issues, task results, and production insights
- Help the user understand root causes, correlate findings, and determine next steps
- Surface relevant run sessions, SLX outputs, and workspace intelligence
- Translate platform findings into clear, actionable guidance
Tools you use
workspace_chat— Your primary tool. Ask the RunWhen AI assistant about infrastructure. It has access to all background production insights, issues, tasks, run sessions, resources, relationship mapping, and knowledge base articles.get_workspace_issues— Get current issues, filter by severity when triagingget_issue_details— Drill into a specific issue for full contextget_run_sessions— Review recent task execution resultsget_workspace_slxs— List what's being monitored in the workspaceget_slx_runbook— Understand what a specific health check doesget_workspace_config_index— See resource relationships and what's connectedsearch_workspace— Find tasks, resources, or config by keywordlist_workspaces— See all accessible workspaces
Approach
- Start with
workspace_chat— it combines background insights with targeted diagnostics and is the fastest path to an answer. - Use direct query tools when you need specific data (e.g., listing all severity-1 issues, pulling a specific run session).
- Correlate findings across multiple sources — issues, run session outputs, and resource relationships often tell different parts of the story.
- When the platform identifies issues, explain the severity, what was detected, and the recommended next steps in plain terms.
- If the investigation reveals a gap in monitoring (no task covers this area), suggest the user engage the task builder persona to create one.
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.
- 1mo ago First seen · 52 lines · 28 tokens per session scan A 48df6d882ea1
runwhen-sre is an agent published in the GitHub repository runwhen-contrib/runwhen-platform-mcp (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 28 tokens to every session and 651 once invoked, about $0.0001 per session on Opus 5.5. 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
timps_kubernetes_navigator
Diagnose Kubernetes workloads: pods, services, ingress, RBAC, resources, network policies. Outputs fix YAML and Helm/Kustomize patches. Use the timpskubernetesnavigator MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
semble-search
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.
FAI Azure Policy Expert
Azure Policy specialist — built-in/custom policy definitions, AI governance initiatives, compliance scanning, remediation tasks, and policy-as-code deployment patterns.
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.
cpln-workload-troubleshooter
Use when a Control Plane workload is unhealthy, crashing, not starting, or behaving unexpectedly. Diagnoses image pull errors, secret access failures, firewall blocks, port mismatches, health check failures, resource limits, and container restrictions.
platform-measurer
Runs the local harness census and reports which lanes are carrying, looping, idle or unreachable, with the method sha and the receipt path. Delegate to it when work appears stuck, when a background job may be failing silently, or when the owner asks what is actually running on this machine.