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/openshift-eng/two-node-toolboxWrote 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/commands/openshift-eng/two-node-toolbox/project)<a href="https://agentmods.dev/commands/openshift-eng/two-node-toolbox/project"><img src="https://agentmods.dev/badge/commands/openshift-eng/two-node-toolbox/project/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/commands/openshift-eng/two-node-toolbox/project"><img src="https://agentmods.dev/badge/commands/openshift-eng/two-node-toolbox/project.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 | $0.00000 | $0.02545 |
| Opus 5.5 | $0.00000 | $0.01018 |
| Sonnet 5.5 | $0.00000 | $0.00509 |
| Haiku 4.5 | $0.00000 | $0.00254 |
Grade B, and why
PROJECT scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
**Important**: All commands must be executed with sudo privileges (using Ansible's `become: yes`). How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Etcd Troubleshooting Skill - Project File
Project Overview
This project is for developing a Claude Code skill that helps troubleshoot etcd issues on two-node with fencing OpenShift clusters. The skill enables Claude to iteratively diagnose and resolve issues by leveraging Ansible to access cluster VMs directly and analyze etcd health, pacemaker status, and relevant system logs to provide diagnostic insights and troubleshooting procedures.
Objectives
- Provide troubleshooting expertise that validates direct Ansible access to cluster VMs
- Gather etcd and Pacemaker status using appropriate commands
- Collect and analyze journalctl logs for both Pacemaker and etcd services
- Analyze the collected data to identify common issues
- Propose and execute structured troubleshooting procedures iteratively
- Provide actionable recommendations based on ongoing analysis
Target Environment
- Deployment Type: Two-Node with Fencing (TNF) OpenShift cluster
- Topology: Two control plane nodes with BMC-based fencing
- Access Method: Ansible via inventory.ini
- Key Components:
- Pacemaker (cluster resource management)
- Corosync (cluster communication)
- Etcd (running as Podman containers managed by Pacemaker)
- Fencing agents (BMC/RedFish based)
Documentation Resources
Primary References
-
Fencing Documentation:
docs/fencing/README.md- Overview of Two-Node with Fencing architecture
- Etcd management by Pacemaker
- Disruption handling (graceful and ungraceful)
- Quorum management principles
-
Etcd Operations Guide:
.claude/commands/etcd/etcd-ops-guide/clustering.md- Cluster membership and operationsconfiguration.md- Configuration parameterscontainer.md- Container-specific operationsdata_corruption.md- Data corruption detection and recoveryfailures.md- Failure scenarios and handlingmaintenance.md- Maintenance proceduresmonitoring.md- Monitoring and metricsrecovery.md- Recovery proceduresruntime-configuration.md- Runtime configuration changesruntime-reconf-design.md- Reconfiguration design patterns
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 · 295 lines · 0 tokens per session scan B f34f5e5db703
PROJECT is a command published in the GitHub repository openshift-eng/two-node-toolbox (5 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,545 tokens. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
status
Check overall system health and status.
investigate
Start a deep root-cause investigation on the AWS DevOps Agent and stream progress.
analyze
Quick analysis of must-gather data - runs all analysis scripts and provides comprehensive cluster diagnostics.
cloudflare-queues:troubleshoot
Quick troubleshooting for common Cloudflare Queues issues.
cloudflare-workers:debug
Interactive debugging workflow for Cloudflare Workers. Diagnoses deployment errors, runtime issues, and performance problems with step-by-step fixes.
cloud-run-debug
Diagnose a failing Cloud Run service — Antigravity (agy/Gemini) digests the error logs cheaply, Claude infers the root cause and proposes a fix. Read-only by default; --apply writes the fix to a branch.