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/jturntdev/krypton/krypton-vps-codex-appnpx skills add jturntdev/krypton --skill krypton-vps-codex-appgit clone --depth 1 https://github.com/jturntdev/kryptonWrote 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/jturntdev/krypton/krypton-vps-codex-app)<a href="https://agentmods.dev/skills/jturntdev/krypton/krypton-vps-codex-app"><img src="https://agentmods.dev/badge/skills/jturntdev/krypton/krypton-vps-codex-app.svg" alt="Measured on agentmods" 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 | $0.00113 | $0.03217 |
| Opus 5 | $0.00056 | $0.01608 |
| Sonnet 5 | $0.00023 | $0.00643 |
| Haiku 4.5 | $0.00011 | $0.00322 |
Grade B, and why
krypton-vps-codex-app scanned grade B with 2 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 4d 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.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
IdentityFile ~/.ssh/id_ed25519 Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl` How it starts
The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Krypton VPS Codex App
Overview
Turn a Linux VPS into the machine that does the work while the operator's Mac only displays and controls it. The target result is a working Codex App SSH project where commands, edits, builds, tests, tmux/cmux sessions, dev servers, and agent runs happen on the VPS.
Do not describe this as installing Codex App on the VPS. Codex App stays on the operator's Mac or Windows machine; the VPS needs the Codex CLI and repo toolchain so the app can start the remote Codex app server through SSH.
Use the current OpenAI Codex docs for Codex App specifics when facts may have changed. The durable setup facts this skill relies on are:
- Codex App can add projects from an SSH host.
- Codex reads concrete SSH aliases from
~/.ssh/config. - Remote project threads run commands and edit files on the remote host.
- The remote host provides the repo files, credentials, tools, skills, MCP setup, browser/computer-use setup, and sandbox/approval behavior.
- The remote
codexcommand must be available on the remote user's login-shellPATH.
Responsibility Split
Codex can prepare commands, inspect SSH config, audit the VPS, bootstrap tools over SSH when it has access, clone the repo, run checks, and explain failures.
The operator must provide or complete these human steps:
- Buy or provision the VPS if it does not exist yet.
- Create or choose the SSH key pair used for the VPS.
- Add an SSH public key in the VPS provider UI or otherwise grant SSH access.
- Approve any edit to
~/.ssh/config, or add the SSH alias manually. - Choose how the VPS may access their GitHub repo.
- Decide whether local-only config files should be recreated, copied, or skipped.
- Keep private keys, provider passwords, API keys, and Codex auth files secret.
- Complete Codex App Settings > Connections and choose the remote project folder.
- Complete browser/device authentication when the flow requires user login.
First Response
Start by repeating the setup goal in plain English:
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.
- 4d ago First seen · 374 lines · 113 tokens per session scan B 51587100d1b1
krypton-vps-codex-app is a skill published in the GitHub repository jturntdev/krypton (130 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 3,217 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (reaches for credential files, 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
ospec-goal
Create or advance a full OSpec goal using the current document, task graph, worker, review, and evidence workflow.
ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
ts-sdk-author
Design, build, verify, and publish production-grade TypeScript SDKs as npm packages inside a pnpm monorepo. Covers workspace layout, public API and module boundaries, plugin extension points, branded types and library-tuned tsconfig, tsdown bundling (vs tsup/tsc-only/unbuild), package.json exports with dual ESM+CJS…
first-principles-thinking
Systematic first principles thinking for any problem domain. Use when the user says "analyze from first principles", "第一性原理", "从根本分析", "从零开始思考", "think from scratch", "question this design", "is this the right approach", "challenge assumptions", "挑战假设", "为什么要这样做", "有没有更好的方案", "why are we doing it this way", or needs…
python-design
Python design patterns for CLI scripts and utilities — type-first development, deep modules, complexity management, and red flags. Use when reading, writing, reviewing, or refactoring Python files, especially in .trellis/scripts/ or any CLI/scripting context. Also activate when planning module structure, deciding…