Borrowing it
Nothing to install: this file belongs to TheSmokeDev/taskchad-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TheSmokeDev/taskchad-os/master/.claude/skills/client-site-factory/SKILL.mdgit clone --depth 1 https://github.com/TheSmokeDev/taskchad-osWrote 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/thesmokedev/taskchad-os/client-site-factory)<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/client-site-factory"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/client-site-factory/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/thesmokedev/taskchad-os/client-site-factory"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/client-site-factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00161 | $0.01502 |
| Opus 5 | $0.00081 | $0.00751 |
| Sonnet 5 | $0.00032 | $0.00300 |
| Haiku 4.5 | $0.00016 | $0.00150 |
Grade A, and why
client-site-factory 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 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.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Client-Site Factory
One config file per client in -> a finished website out, every step gated by a deterministic validator. The shape: AI decides, script resolves, AI consumes. LLMs write copy and scene prompts; scripts compile, assemble, render, and gate. The factory NEVER deploys — deploying is a separate, approval-locked workflow.
Canonical manual (read before changing ANY factory code):
docs/manual/features/client-site-factory.md — schema, lanes, gates, the
deploy contract, and 11 known traps. This skill is the router; the manual is
the depth.
The two workflows
| Workflow | What it does | Invocation |
|---|---|---|
.archon/workflows/client-site-factory.yaml |
brief -> copy + images + video -> build + report. Never deploys. | archon workflow run client-site-factory "clients/<slug>/client.yaml images=true video=true" |
.archon/workflows/client-site-deploy.yaml |
operator-gated deploy of an existing build | archon workflow run client-site-deploy "clients/<slug>/client.yaml dry_run=true" |
TRAP (manual Trap 10): NEVER launch either workflow from inside a Claude Code session — archon hangs. Run them from a desktop terminal, or drive the lanes in-session with the script sequence below (that is exactly how P2/P3 acceptance ran).
Onboard a new client (the proven recipe)
mkdir clients/<slug>/assets-src/fonts clients/<slug>/stillsand copy the three open-license woff2 fonts intoassets-src/fonts/(or the client's own pairing).- Write
clients/<slug>/client.yaml— copy the shape from an existing profile. Sections:identity,brand(palette + typography + voice + banned_phrases + opening_move widget),facts(the packet: services, contact, whitelist — the writer's ONLY truth),page_plan(pages, nav, metas, hero assets),images(assets_dir+page_maprole-keyed render concepts), optionalvideo(per-page still + look),compliance(fine_print),copy_gates,deploy(held: true, base_path, canonical_base). - Compile early, fail early: the compiler refuses any page whose media can never materialize.
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 · 110 lines · 161 tokens per session scan A 5fc8d19f8560
client-site-factory is a skill published in the GitHub repository TheSmokeDev/taskchad-os (24 stars, last pushed yesterday), licensed MIT. It adds 161 tokens to every session and 1,502 once invoked, about $0.0008 per session on Opus 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
trigger-realtime-and-frontend
Trigger.dev client/frontend surface: subscribe to runs in realtime (runs.subscribeToRun and the @trigger.dev/react-hooks hook useRealtimeRun), consume metadata and AI/text streams in React (useRealtimeStream), trigger tasks from the browser (useTaskTrigger, useRealtimeTaskTrigger), and mint scoped frontend credentials…
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
web-design
Use when building any web page, HTML artifact, landing page, dashboard, slide deck, report, email, or UI component the user will look at. A taste-first design system that makes generated pages look intentional and crafted instead of generic "AI-made". Provides an aesthetic-direction process, design tokens, a starter…
graphify
Use when the user invokes /graphify or asks to build, update, or query a knowledge graph from a folder of files (code, docs, papers, notes, images). Triggers: 'map this codebase', 'graph my notes', 'what is connected across these files', 'community detection', 'GraphRAG', incremental graph update, Neo4j/SVG/GraphML…
insights
Use when the user types /weekly or /monthly, asks for a weekly or monthly journal review or retrospective, asks 'how was my week' or 'how was my month', or wants trends, anomalies, or patterns across recent journal entries. Also fires when regenerating an insight report for a past week or month. NOT for writing…
setup-brain
Set up or upgrade an AI-powered Obsidian vault. Interviews you, builds your vault structure (or works with what you already have), creates your CLAUDE.md memory file, installs tools, and gets you journaling — all in one conversation. Also has a repair/upgrade path for existing users.