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 skills/cwinvestments/memstack/hetzner-setupnpx skills add cwinvestments/memstack --skill hetzner-setupgit clone --depth 1 https://github.com/cwinvestments/memstackWhat 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 | $0.00093 | $0.04776 |
| Opus 5 | $0.00046 | $0.02388 |
| Sonnet 5 | $0.00019 | $0.00955 |
| Haiku 4.5 | $0.00009 | $0.00478 |
Grade F, and why
memstack-deployment-hetzner-setup scanned grade F with 4 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
usermod -aG sudo deploy Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
cp /root/.ssh/authorized_keys /home/deploy/.ssh/ Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://get.docker.com | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
apt install -y curl wget git htop ufw fail2ban unattended-upgrades \ How it starts
The opening of the file, as written. The whole thing — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🖥️ Hetzner Setup — VPS Provisioning & Deployment
Provision a Hetzner Cloud server with security hardening, reverse proxy, SSL, database setup, monitoring, and automated backups.
Activation
When this skill activates, output:
🖥️ Hetzner Setup — Provisioning your server...
| Context | Status |
|---|---|
| User says "Hetzner", "VPS setup", "server provisioning" | ACTIVE |
| User wants to deploy to a cloud server (Hetzner specifically) | ACTIVE |
| User mentions SSH hardening, fail2ban, or server security | ACTIVE |
| User wants Docker containerization guidance | DORMANT — see docker-setup |
| User wants CI/CD pipeline (not server setup) | DORMANT — see ci-cd-pipeline |
| User wants managed hosting (Railway, Netlify, Vercel) | DORMANT — see railway-deploy or netlify-deploy |
Protocol
Step 1: Gather Inputs
Ask the user for:
- Workload type: Web app, API, database, scraper, background worker?
- Expected traffic: Low (< 1k/day), medium (1k-50k/day), high (50k+/day)?
- Stack: Node.js, Python, Go, Rust? Docker or direct?
- Database needs: PostgreSQL, MySQL, Redis, none?
- Domain: Do you have a domain to point at this server?
- Budget preference: Minimum viable or room to grow?
Step 2: Recommend Instance Type
Match workload to Hetzner Cloud server:
| Instance | vCPU | RAM | SSD | Traffic | Price | Best For |
|---|---|---|---|---|---|---|
| CX22 | 2 | 4 GB | 40 GB | 20 TB | ~$4.5/mo | Small API, static site, hobby project |
| CX32 | 4 | 8 GB | 80 GB | 20 TB | ~$8/mo | Medium web app, small DB |
| CPX31 | 4 | 8 GB | 160 GB | 20 TB | ~$13/mo | High-perf apps (AMD EPYC), scrapers |
| CPX41 | 8 | 16 GB | 240 GB | 20 TB | ~$24/mo | Large apps, multiple services |
| CPX51 | 16 | 32 GB | 360 GB | 20 TB | ~$47/mo | Heavy workloads, large databases |
| CCX13 | 2 | 8 GB | 80 GB | 20 TB | ~$13/mo | Dedicated vCPU — consistent performance |
Recommendation logic:
- Scraper/background worker → CPX31 (AMD EPYC, burst-friendly)
- Web app with DB → CX32 or CPX31 (depends on traffic)
- API-heavy service → CPX31 (fast single-thread)
- Multiple services → CPX41 (headroom for containers)
- Budget-constrained → CX22 (surprisingly capable)
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.
- 2d ago First seen · 569 lines · 93 tokens per session scan F 002108ad1cb1
memstack-deployment-hetzner-setup is a skill published in the GitHub repository cwinvestments/memstack (417 stars, last pushed 6d ago), licensed MIT. It adds 93 tokens to every session and 4,776 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it F with 4 findings (asks for root, reaches for credential files, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
plan-ceo-review
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…
ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, and create a PR. Use for an explicit /ship invocation or when the user requests the full ship, release, or deploy workflow. For an ordinary commit, push, or pull-request publishing request, use the built-in…
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
autoplan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…
retro
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively…