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 Myst4ke/mcp-to-skills-converter --skill configurationgit clone --depth 1 https://github.com/Myst4ke/mcp-to-skills-converterWrote 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/myst4ke/mcp-to-skills-converter/configuration)<a href="https://agentmods.dev/skills/myst4ke/mcp-to-skills-converter/configuration"><img src="https://agentmods.dev/badge/skills/myst4ke/mcp-to-skills-converter/configuration/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/myst4ke/mcp-to-skills-converter/configuration"><img src="https://agentmods.dev/badge/skills/myst4ke/mcp-to-skills-converter/configuration.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 | $0.00022 | $0.02384 |
| Opus 5 | $0.00011 | $0.01192 |
| Sonnet 5 | $0.00004 | $0.00477 |
| Haiku 4.5 | $0.00002 | $0.00238 |
Grade A, and why
configuration 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration Management Skill
Overview
This skill provides guidance for implementing safe configuration file management including backup systems, atomic updates, and recovery mechanisms. For US-4 (MCP Uninstaller), this skill covers:
- Creating timestamped configuration backups
- Atomic JSON file updates
- Configuration validation
- Backup restoration and cleanup
Core Capabilities
- Atomic File Operations: Write-then-rename pattern for safe file updates
- Backup Management: Create, restore, and clean up timestamped backups
- JSON Manipulation: Safe parsing, modification, and validation of JSON config files
- Error Recovery: Automatic rollback on failures
- Metadata Tracking: Include metadata in backups for audit trail
- Cleanup Policies: Implement retention policies (e.g., keep last 10 backups)
Input Requirements
Required:
- Configuration file path
- Operation type (backup, update, restore)
- Backup directory path
Optional:
- Retention policy (number of backups to keep)
- Validation schema
- Metadata to include in backup
Output Format
Returns:
- Operation result (success/failure)
- Backup file path (for backup operations)
- Validation results
- Error messages if applicable
Dependencies
- fs-extra: Enhanced file system operations
- JSON schema validator (optional): For config validation
- TypeScript 5.x: For type-safe config handling
Workflow
Step 1: Define Configuration Interfaces
Create TypeScript interfaces for config structure:
// src/interfaces/config.interface.ts
export interface ClaudeConfig {
mcpServers?: Record<string, MCPServerConfig>;
[key: string]: any;
}
export interface MCPServerConfig {
command: string;
args?: string[];
env?: Record<string, string>;
}
export interface BackupMetadata {
timestamp: string;
originalPath: string;
reason: string;
mcpName?: string;
}
Step 2: Implement Backup Service
Create backup with metadata:
// src/services/config-backup.ts
import * as fs from 'fs-extra';
import * as path from 'path';
export class ConfigBackup {
private backupDir: string;
private maxBackups: number;
constructor(backupDir: string = '.claude/backups', maxBackups: number = 10) {
this.backupDir = backupDir;
this.maxBackups = maxBackups;
}
async createBackup(configPath: string, reason: string, mcpName?: string): Promise<string> {
// Ensure backup directory exists
await fs.ensureDir(this.backupDir);
// Generate timestamp
const timestamp = new Date().toISOString().replace(/[:.]/g, '-');
const backupFileName = `config-backup-${timestamp}.json`;
const backupPath = path.join(this.backupDir, backupFileName);
// Read original config
const config = await fs.readJson(configPath);
// Create backup with metadata
const backup = {
metadata: {
timestamp: new Date().toISOString(),
originalPath: configPath,
reason,
mcpName
},
config
};
// Write backup atomically
await this.atomicWrite(backupPath, JSON.stringify(backup, null, 2));
// Verify backup
if (!await fs.pathExists(backupPath)) {
throw new Error('Backup verification failed');
}
// Clean up old backups
await this.cleanupOldBackups();
return backupPath;
}
private async atomicWrite(filePath: string, content: string): Promise<void> {
const tempPath = `${filePath}.tmp`;
await fs.writeFile(tempPath, content, 'utf-8');
await fs.rename(tempPath, filePath);
}
private async cleanupOldBackups(): Promise<void> {
const files = await fs.readdir(this.backupDir);
const backupFiles = files
.filter(f => f.startsWith('config-backup-'))
.sort()
.reverse();
// Keep only the most recent maxBackups
const filesToDelete = backupFiles.slice(this.maxBackups);
for (const file of filesToDelete) {
await fs.remove(path.join(this.backupDir, file));
}
}
async restore(backupPath: string, targetPath: string): Promise<void> {
const backup = await fs.readJson(backupPath);
if (!backup.config) {
throw new Error('Invalid backup file: missing config data');
}
// Write config atomically
await this.atomicWrite(targetPath, JSON.stringify(backup.config, null, 2));
}
}
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.
- 12d ago First seen · 394 lines · 22 tokens per session scan A 0abec63a22c1
configuration is a skill published in the GitHub repository Myst4ke/mcp-to-skills-converter (1 stars, last pushed 10mo ago), licensed MIT. It adds 22 tokens to every session and 2,384 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
[object Object]
Skill "[object Object]" from Lover0ne/devstuff, covering when to use, quick reference, implementation and common mistakes.
architect
This skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design".
ucai-patterns
Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.
frontend-design
Use when user asks to build a web component, page, or application, or when the task involves frontend design, HTML/CSS generation, or UI layout. Applies specific rules for typography, OKLCH color, layout, motion, interaction, and UX writing to produce distinctive, production-grade interfaces that avoid generic AI…
explain
Use when user invokes /explain with a file path, directory path, function/class name, or natural language concept. Also triggers on "explain this", "how does X work", "walk me through". Produces a structured, layered explanation of what the code does, how it connects, and where to start if you need to change it. Do…
orient
Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and…