Guard network writes behind dry-run, RFC 6241 confirmed-commit, and explicit rollback. Use when applying config to Cisco, Juniper, Arista, or Nokia and a human must own the blast radius.
Scanned 9/5/2026
Install to Claude Code
Skills Directorynpx -y skills add gesh75/claude-skill-lint --skill netops-change-guard --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Netops Change Guard?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/gesh75-netops-change-guard)More formats (shields.io, HTML) on the badges page.
---
name: netops-change-guard
description: Guard network writes behind dry-run, RFC 6241 confirmed-commit, and explicit rollback. Use when applying config to Cisco, Juniper, Arista, or Nokia and a human must own the blast radius.
argument-hint: "[device] [change-id]"
allowed-tools: Read Grep
license: MIT
---
# Network change guard
Do not use for read-only show commands or lab toys with no production path. Not for firewall policy design.
## Procedure
1. Capture pre-state (`show run`, `show bgp summary`, interface counters) and store it next to the change ticket.
2. Render the candidate config from intent. Diff against running. Reject secrets, `shutdown` of uplinks, and default-route wipes.
3. Apply with confirmed-commit (NETCONF RFC 6241 or vendor equivalent) and a 5–10 minute confirm window.
4. Verify forwarding: ping, traceroute, BGP Established, EVPN MAC count, or synthetic probe — two agreeing signals.
5. Confirm the commit only after verification. Otherwise let it roll back and page the owner.
```xml
<commit>
<confirmed/>
<confirm-timeout>600</confirm-timeout>
</commit>
```
## Anti-patterns
- Never `commit` without a confirm window on a PE, spine, or edge firewall.
- Do not paste running-config with TACACS or SNMP strings into an LLM.
## Safety
Read-only until a named human approves the write. Fail closed if rollback is unavailable.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
