Preflight a candidate network config for secrets, blast radius, and silent defaults. Use when a human or an LLM produced a snippet and it must be reviewed before a dry-run.
Scanned 9/5/2026
Install to Claude Code
Skills Directorynpx -y skills add gesh75/claude-skill-lint --skill config-diff-preflight --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Config Diff Preflight?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/gesh75-config-diff-preflight)More formats (shields.io, HTML) on the badges page.
---
name: config-diff-preflight
description: Preflight a candidate network config for secrets, blast radius, and silent defaults. Use when a human or an LLM produced a snippet and it must be reviewed before a dry-run.
argument-hint: "[vendor] [file]"
allowed-tools: Read Grep
license: MIT
---
# Config diff preflight
Do not use as a substitute for a digital twin (AEGIS) on high-risk changes. Not for generating the config itself.
## Procedure
1. Diff against running. Reject if the diff includes `no router bgp`, interface shutdowns on uplinks, or AAA removal.
2. Strip and flag secrets: keys, communities used as passwords, TACACS, SNMP.
3. Blast radius: count of peers, prefixes, and interfaces touched. Over a threshold, require a senior.
4. Silent defaults: MTU, BFD, logging, timestamps. Missing logging is a fail.
5. Verify the ticket has pre-state, diff, verification, and rollback pasted.
```diff
- neighbor 192.0.2.1 shutdown
+ neighbor 192.0.2.1 description PE-A
# fail: this un-shuts a peer without a change window
```
## Anti-patterns
- Never approve a diff you cannot reverse in one command.
- Do not ignore "no" statements that wipe stanzas.
## Safety
A failed preflight stops the pipeline. No override without a named senior.
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.
