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 skills add a2wio/lucas --skill lucas-runbookgit clone --depth 1 https://github.com/a2wio/lucasWrote 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/a2wio/lucas/lucas-runbook)<a href="https://agentmods.dev/skills/a2wio/lucas/lucas-runbook"><img src="https://agentmods.dev/badge/skills/a2wio/lucas/lucas-runbook/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/skills/a2wio/lucas/lucas-runbook"><img src="https://agentmods.dev/badge/skills/a2wio/lucas/lucas-runbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00038 | $0.00501 |
| Opus 5 | $0.00019 | $0.00251 |
| Sonnet 5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
lucas-runbook 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 10d 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.
What it actually says
Lucas Runbook-Driven Troubleshooting
You are operating in runbook-driven mode. Before taking any remediation action, you MUST search for and follow approved runbooks.
Runbook Sources
Search these locations for runbooks:
Local Runbooks
- Path:
/runbooks - Search using:
Glob pattern="**/*.md" path="/runbooks" - Read matching files to find relevant procedures
External Documentation (if configured)
- Check environment or config for external URLs
- Use WebFetch to retrieve external runbook content
Procedure
When you identify a Kubernetes issue:
-
Identify the error type (OOMKilled, CrashLoopBackOff, ImagePullBackOff, etc.)
-
Search for matching runbook:
Glob pattern="**/*oom*.md" path="/runbooks" Glob pattern="**/*crash*.md" path="/runbooks" Glob pattern="**/*image*.md" path="/runbooks" -
Read the runbook if found
-
Follow the runbook EXACTLY:
- Use only the approved diagnostic commands
- Apply only the approved fixes
- Escalate when the runbook says to escalate
-
If NO runbook found:
- Do NOT attempt fixes
- Report what you observed
- Ask: "No runbook found for this issue. How should I proceed?"
Important Rules
- ALWAYS cite which runbook you're following
- NEVER improvise fixes outside of runbooks
- If a runbook says "escalate", do NOT attempt the fix yourself
- Document what you did and the outcome
Example
When you see OOMKilled:
- Search:
Glob pattern="**/*oom*.md" path="/runbooks" - Find:
oom-killed.md - Read: The runbook says to increase memory limits
- Say: "Following runbook
oom-killed.md: Increasing memory limit from 256Mi to 512Mi" - Execute the approved fix
- Verify and report outcome
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.
- 10d ago First seen · 65 lines · 38 tokens per session scan A ba7cc2ac8205
lucas-runbook is a skill published in the GitHub repository a2wio/lucas (362 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 501 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
networkpolicy-debug
Diagnose NetworkPolicy-related connectivity issues (traffic unexpectedly blocked, default-deny effects, egress blocking DNS). Identifies which NetworkPolicies affect a pod, checks ingress/egress rules, and verifies CNI support.
node-logs
Retrieve logs from a Kubernetes node — systemd units (journalctl) or files under /var/log. Use when you need node-level evidence: containerd, kubelet, kernel/OOM, or anything the pod's own log cannot show. Three access paths in order: hostscript (SSH), nodescript (debug pod), and localscript against the kubelet log…
statefulset-debug
Diagnose StatefulSet rollout and scaling failures (ordered update stuck, OnDelete not updating, partition misconfiguration, PVC binding deadlocks). Checks update strategy, pod ordinal progression, PVC bindings, and ordered startup to identify why a StatefulSet is not progressing.
volcano-gang-scheduling
Gang Scheduling diagnostic guide for Volcano. Use when PodGroup cannot schedule completely, member Pods remain Pending, or minAvailable/minMember constraints are not satisfied.
volcano-resource-insufficient
Resource shortage diagnostic guide for Volcano. Use when seeing Insufficient cpu/memory events, OOMKilled pods, or nodes with zero allocatable resources.
image-pull-debug
Diagnose container image pull failures (ErrImagePull / ImagePullBackOff). Checks pod status, containerd logs, and events to identify root cause.