Start Technologies is a monorepo, meaning one repository containing the source for several related products, including StartOS, StartWRT, StartTunnel, developer tools, and shared libraries. Its products support personal servers, routers, VPN or forwarding, service packaging, registries, and related self-hosting tasks, with shared Rust and Angular code. Catalogue add-ons support development across this product repository.
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 Start9Labs/start-technologies --skill package-servicegit clone --depth 1 https://github.com/Start9Labs/start-technologiesWrote 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/start9labs/start-technologies/package-service)<a href="https://agentmods.dev/skills/start9labs/start-technologies/package-service"><img src="https://agentmods.dev/badge/skills/start9labs/start-technologies/package-service/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/start9labs/start-technologies/package-service"><img src="https://agentmods.dev/badge/skills/start9labs/start-technologies/package-service.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 | $0.00099 | $0.03483 |
| Opus 5.5 | $0.00040 | $0.01393 |
| Sonnet 5.5 | $0.00020 | $0.00697 |
| Haiku 4.5 | $0.00010 | $0.00348 |
Grade A, and why
package-service 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 29d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Package a service for StartOS
The argument is a service name or an upstream URL. Take it from nothing to a working, verified, uncommitted package.
Paths below are relative to the packaging workspace root — the directory holding
.startos/, AGENTS.md, and the start-technologies/ guide checkout. Phase 0 finds it.
| Phase | Who works |
|---|---|
| 0 · Workspace and prior art | you, asking only if a workspace has to be built |
| 1 · Research the upstream | you |
| 2 · The gate | the user answers, once |
| 3 · Package it | you, alone |
| 4 · Verify on a StartOS box | you, alone |
| 5 · Hand back | the user reviews |
The gate is the only interruption in the packaging work. Everything before it exists to make it a good one; everything after it runs to completion. Judgement calls inside phases 3 and 4 are yours — make them, state them at hand-back, and let the user push back there.
Phase 0 may ask one thing first: permission to build a workspace or install a missing prerequisite. That is consent for an action on the machine, not a packaging decision, and it is asked before any research begins.
Read first
Nothing loads these for you from inside a package directory, and each outranks your priors:
| Read | For |
|---|---|
AGENTS.md |
the packaging guide's map — which page answers which objective |
AGENTS.local.md |
this workspace's own rules: where packages live, which box to install to, how a finished package lands. Where it departs from this skill, it wins. |
start-technologies/projects/start-sdk/docs/src/recipes.md |
the intent index — find a recipe for every part of the shape you agreed |
start-technologies/projects/start-sdk/docs/src/new-package-checklist.md |
the build order once scaffolded |
What ships with it
4 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.
- 29d ago First seen · 253 lines · 99 tokens per session scan A 03a332f9dc86
package-service is a skill published in the GitHub repository Start9Labs/start-technologies (1,992 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 3,483 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-18.
Other skills, from other repositories
censor_message
Automatically censor profanity in messages by replacing with asterisks.
content_guard
Proactive content moderation guard for all incoming messages.
profanity_check
Check messages for profanity and inappropriate content in 24 languages.
join-buyer
Help the user set up Antseed buyer node to consume AI services from the peer-to-peer network. Walk them through installation, funding, and connecting their existing tools (Aider, Continue.dev, Cursor, or any OpenAI-compatible client) through the local proxy.
join-provider
Help the user set up Antseed provider node to offer AI services on the peer-to-peer network. Walk them through installation, on-chain registration, staking, provider configuration, pricing, and starting the seeder.
antseed-decisions
Ask a System One decision model (TypeSafe Jev) typed questions about some state through the user's local Antseed buyer proxy. Use when the user needs a classification, a score against a rubric, or a yes/no probability over text or structured data, when code must branch on the answer, or when the user names Jev, System…