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 commands/openshift-eng/two-node-toolbox/quick_referencegit clone --depth 1 https://github.com/openshift-eng/two-node-toolboxWhat 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 | $0.00000 | $0.03657 |
| Opus 5 | $0.00000 | $0.01828 |
| Sonnet 5 | $0.00000 | $0.00731 |
| Haiku 4.5 | $0.00000 | $0.00366 |
Grade D, and why
QUICK_REFERENCE scanned grade D with 3 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 yesterday.
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.
ansible cluster_vms -i deploy/openshift-clusters/inventory.ini -m shell -a "sudo pcs status" -b Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"sudo rm -rf /var/lib/etcd/*" -b Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"curl -k -u <user>:<pass> https://<bmc-ip>/redfish/v1/Systems" -b How it starts
The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Etcd TNF Quick Reference Guide
Fast troubleshooting for common etcd issues on Two-Node with Fencing clusters
Use this guide for quick diagnosis and remediation. For detailed analysis, refer to TROUBLESHOOTING_SKILL.md.
CRITICAL: Target the Correct Hosts
Always use cluster_vms host group for etcd/Pacemaker commands:
- ✓ Correct:
ansible cluster_vms -i inventory.ini -m shell -a "pcs status" -b - ✗ Wrong:
ansible all -i inventory.ini ...(would include hypervisor) - ✗ Wrong:
ansible hypervisor -i inventory.ini ...(hypervisor has no etcd)
The hypervisor is only for VM lifecycle (virsh/kcli). All etcd operations run on cluster_vms.
Quick Diagnostics
Collect all diagnostics automatically:
./helpers/etcd/collect-all-diagnostics.sh
Check cluster health quickly:
# Pacemaker status (on cluster VMs)
ansible cluster_vms -i deploy/openshift-clusters/inventory.ini -m shell -a "sudo pcs status" -b
# Etcd member list (on cluster VMs)
ansible cluster_vms -i deploy/openshift-clusters/inventory.ini -m shell -a "sudo podman exec etcd etcdctl member list -w table" -b
# OpenShift etcd operator (if cluster access available)
oc get co etcd -o yaml | grep -A10 "status:"
Check workload distribution during failover:
# Quick check: functional pods per node (uses simple grep)
oc get pods -owide -n <namespace> | grep Running | grep <node_name> | wc -l
# Detailed analysis: shows READY status to filter stale pod references
oc get pods -n <namespace> \
-o custom-columns='NAME:.metadata.name,STATUS:.status.phase,READY:.status.conditions[?(@.type=="Ready")].status,NODE:.spec.nodeName'
# Count only functional workloads
oc get pods -n <namespace> \
-o custom-columns='NAME:.metadata.name,STATUS:.status.phase,READY:.status.conditions[?(@.type=="Ready")].status,NODE:.spec.nodeName' \
| grep 'True.<node_name>' | wc -l
💡 Key Insight: During failover scenarios, pod status can show stale references. Use READY=True filter or the simple grep approach to see actual functional workloads. STATUS=Running + READY=False indicates stale pod references from failed nodes.
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.
- yesterday First seen · 403 lines · 0 tokens per session scan D 4bdf863350a5
QUICK_REFERENCE is a command published in the GitHub repository openshift-eng/two-node-toolbox (5 stars, last pushed 28d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,657 tokens. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.