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 martinholovsky/claude-skills-generator --skill auto-update-systemsgit clone --depth 1 https://github.com/martinholovsky/claude-skills-generatorWrote 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/martinholovsky/claude-skills-generator/auto-update-systems)<a href="https://agentmods.dev/skills/martinholovsky/claude-skills-generator/auto-update-systems"><img src="https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/auto-update-systems/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/martinholovsky/claude-skills-generator/auto-update-systems"><img src="https://agentmods.dev/badge/skills/martinholovsky/claude-skills-generator/auto-update-systems.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 | $0.00030 | $0.03804 |
| Opus 5 | $0.00015 | $0.01902 |
| Sonnet 5 | $0.00006 | $0.00761 |
| Haiku 4.5 | $0.00003 | $0.00380 |
Grade A, and why
Auto-Update Systems Expert scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
return requests.get(url).content # Blocks entire app How it starts
The opening of the file, as written. The whole thing — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Update Systems Expert
0. Mandatory Reading Protocol
CRITICAL: Before implementing, read these reference files:
| Reference | When to Read |
|---|---|
references/security-examples.md |
Signing keys, signature verification, secure endpoints |
references/advanced-patterns.md |
Staged rollouts, rollback, update channels, differential updates |
references/threat-model.md |
Security posture, MITM defense, key rotation |
1. Overview
Risk Level: HIGH
Justification: Auto-update systems can deliver code to all users simultaneously. A compromised update system can distribute malware to the entire user base. Signature verification bypass (like CVE-2024-39698) allows attackers to install unsigned malicious updates. Poor rollback mechanisms can leave users with broken software.
You are an expert in auto-update system implementation, specializing in:
- Signature verification for cryptographic update integrity
- Rollback mechanisms for failed updates
- Staged rollouts for risk mitigation
- Secure distribution with HTTPS and pinning
- Tauri updater configuration and best practices
Primary Use Cases
- Tauri application auto-updates
- Secure update distribution infrastructure
- Update channel management (stable, beta)
- Emergency rollback procedures
- Update analytics and monitoring
2. Core Responsibilities
2.1 Core Principles
- TDD First - Write tests before implementation code
- Performance Aware - Optimize for bandwidth and speed
- ALWAYS verify signatures - Never install unsigned updates
- Use HTTPS only - Never fetch updates over HTTP
- Implement rollback - Plan for failed updates
- Staged rollouts - Don't update all users at once
- Monitor update health - Track success rates and errors
2.2 Reliability Principles
- Atomic updates - All or nothing installation
- Preserve user data - Never lose configuration during updates
- Graceful degradation - App works if update fails
- User consent - Inform users before updating
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 500 lines · 30 tokens per session scan A 74180dedf170
Auto-Update Systems Expert is a skill published in the GitHub repository martinholovsky/claude-skills-generator (45 stars, last pushed 9mo ago), licensed Unlicense. It adds 30 tokens to every session and 3,804 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Release Checklist
Check release readiness and record a release note. Use for release and rollback requests.
app-release
Use when the user asks to release a new version, ship a build, or publish a Skill Zoo release. Also use when a tag push results in Homebrew 404 errors or missing artifact failures.
npm-release
Use when publishing or preparing to publish an npm package from this repository, especially the Skill Zoo CLI package under packages/cli. Also use when npm publish fails because of duplicate versions, npm authentication, browser authentication, dist-tag propagation, tarball contents, bin entry issues, or…
ship
Ship a build — pre-flight checks, deploy, document, verify, monitor. Use when deploying code, publishing packages, or releasing.
deployment-ops
Skill for deployment operations — pre-deployment checklists, deployment pattern selection, rollback procedures, post-deployment verification, and incident response.
github-release-management
Use when cutting a GitHub release that needs progressive canary rollout (5%→25%→50%→100%) with automated health gates and auto-rollback on error-rate or latency regressions.