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 start9-frontendgit 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/start9-frontend)<a href="https://agentmods.dev/skills/start9labs/start-technologies/start9-frontend"><img src="https://agentmods.dev/badge/skills/start9labs/start-technologies/start9-frontend/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/start9-frontend"><img src="https://agentmods.dev/badge/skills/start9labs/start-technologies/start9-frontend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 116 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Prompt Injection · line 19 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00133 | $0.03377 |
| Opus 5.5 | $0.00053 | $0.01351 |
| Sonnet 5.5 | $0.00027 | $0.00675 |
| Haiku 4.5 | $0.00013 | $0.00338 |
Grade A, and why
start9-frontend 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 3d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start9 Frontend — Angular + Taiga UI house style
Canonical for every Start9 web UI, distilled from the fleet's codebases and from the refactor and review history that shaped them. Follow it and new code matches the fleet; deviate and expect it to be rewritten in review.
Authority order: Taiga UI docs > this skill > neighboring code. The codebases are
mid-migration — "matches existing repo patterns" is not a quality bar; old code is often
exactly what this skill exists to eliminate. Never guess a Taiga API: verify against the
taiga-ui-mcp MCP server or https://taiga-ui.dev/llms-full.txt.
Reference files (read on demand — don't preload)
| File | Read when |
|---|---|
references/bootstrap.md |
creating/touching app.config, main.ts, angular.json, icons, theming, or a new app/repo |
references/components.md |
writing any component or template (selectors, hostDirectives, signal APIs, control flow) |
references/styling.md |
about to write ANY CSS (the escalation ladder, breakpoints, tokens) |
references/di.md |
providers, tokens, inject patterns |
references/state.md |
services, data flow, loading/error UX, API/RPC integration |
references/forms.md |
any form, validation, or submit flow |
references/overlays.md |
dialogs, confirms, toasts, dropdowns, hints, drawers |
references/routing.md |
route files, guards, navigation, URL state |
references/conventions.md |
i18n strings, file naming, folder structure, import order |
references/shared-libs.md |
before writing ANY utility/component in monorepo apps — it may exist in @start9labs/shared or marketplace |
references/antipatterns.md |
reviewing code, refactoring, or upgrading Angular/Taiga (before→after catalog + verbatim review quotes) |
references/taiga.md |
unsure of a Taiga 5 API; v4→v5 renames; need→primitive lookup table |
references/recipes.md |
step-by-step: new page, dialog, form, table, control component, endpoint |
references/repos.md |
repo-specific rules and build/verify commands |
What ships with it
14 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.
- references/antipatterns.md 9.6 KB
- references/bootstrap.md 8.1 KB
- references/components.md 11 KB
- references/conventions.md 2.8 KB
- references/di.md 2.3 KB
- references/forms.md 4.0 KB
- references/overlays.md 4.1 KB
- references/recipes.md 2.5 KB
- references/repos.md 2.0 KB
- references/routing.md 2.4 KB
- references/shared-libs.md 3.1 KB
- references/state.md 4.7 KB
- references/styling.md 5.5 KB
- references/taiga.md 17 KB
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.
- 3d ago Changed · +1 lines · +4 tokens per session eeec5e1c5d59
- 17d ago Changed 6d2f7a822451
- 19d ago Changed fa340f4171f8
- 22d ago Changed · +3 lines 1ab0de1fb142
- 1mo ago Changed · +4 lines 1ca1ad9c790f
- 1mo ago Changed · +7 lines 91aa65cd22b2
- 1mo ago Changed 542f43f7db69
- 1mo ago First seen · 149 lines · 129 tokens per session scan A f7c32fbb5da6
start9-frontend is a skill published in the GitHub repository Start9Labs/start-technologies (1,994 stars, last pushed today), licensed MIT. It adds 133 tokens to every session and 3,377 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
glin-profanity
Detect and filter profanity in text across 24 languages, including obfuscated forms like fck, f.u.c.k and leetspeak, using the glin-profanity JS or Python package. Use when adding content moderation, chat filtering or input checks to an app.
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.