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/causaai/causa-backend/kruize-optimizationnpx skills add causaai/causa-backend --skill kruize-optimizationgit clone --depth 1 https://github.com/causaai/causa-backendWrote 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/causaai/causa-backend/kruize-optimization)<a href="https://agentmods.dev/skills/causaai/causa-backend/kruize-optimization"><img src="https://agentmods.dev/badge/skills/causaai/causa-backend/kruize-optimization.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 5.1 | $0.00053 | $0.00936 |
| Opus 5 | $0.00026 | $0.00468 |
| Sonnet 5 | $0.00011 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
kruize-optimization 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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kruize Optimization Skill
Interprets the Kruize context already collected by Causa. The context contains two sections from the Kruize MCP server — RESOURCE COST RECOMMENDATIONS (Kruize) and RESOURCE PERFORMANCE RECOMMENDATIONS (Kruize).
What to Expect in the Context
Two JSON sections are present in the diagnostic context:
- RESOURCE PERFORMANCE RECOMMENDATIONS (Kruize) — CPU sized to the 98th percentile of observed usage; primary source for incident response
- RESOURCE COST RECOMMENDATIONS (Kruize) — CPU sized to the 60th percentile of observed usage; lower bound for safe sizing
- Both sections share the same JSON schema with
current,recommendation_terms(short_term24h /medium_term7d /long_term15d), optionalruntime_recommendations, andnotifications
Before interpreting either section, refer to kruize-reference.md for the full schema, recommendation engines, runtime layers, and notification code reference.
Interpreting RESOURCE PERFORMANCE RECOMMENDATIONS (Kruize)
Use long_term (15 days) values — they use the most data and are most reliable. Fall back to short_term only when the incident is very recent and long_term data predates a known configuration change.
No Data Available
Kruize had no data for this container. Do not cite this section as evidence.
current memory limit below recommended
Container is under-provisioned for observed peak usage. If POD EVENTS also show OOMKilling, this gap is the direct cause of the kill. Since requests and limits are unified, both values move together when sizing is corrected.
current memory limit at or above recommended
Memory sizing is not the problem. A code-level cause is more likely — look at POD LOGS for OutOfMemoryError and Cryostat JFR sections for heap or GC evidence.
current CPU limit below recommended
CPU throttling is likely. Corroborate with Unhealthy probe events in POD EVENTS — throttling slows GC threads and can cause probe timeouts even when the application is otherwise healthy.
What ships with it
1 file beside SKILL.md 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.
- 5d ago First seen · 66 lines · 53 tokens per session scan A 7388942576fd
kruize-optimization is a skill published in the GitHub repository causaai/causa-backend (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 53 tokens to every session and 936 once invoked, about $0.0003 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
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.