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 coroboros/agent-skills --skill scaffoldgit clone --depth 1 https://github.com/coroboros/agent-skillsWrote 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/coroboros/agent-skills/scaffold)<a href="https://agentmods.dev/skills/coroboros/agent-skills/scaffold"><img src="https://agentmods.dev/badge/skills/coroboros/agent-skills/scaffold.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 5.1 | $0.00045 | $0.01085 |
| Opus 5 | $0.00023 | $0.00543 |
| Sonnet 5 | $0.00009 | $0.00217 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
scaffold 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 today.
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold
Bootstrap the requested project with the opinionated stack.
The deterministic work — environment preflight, template overlay, package.json merge, post-scaffold verification — happens in three bundled scripts. Parse the invocation arguments, run the framework CLI, invoke the scripts in order, and turn their RESULT: lines into a concise report.
Available scaffolds
| Scaffold | Framework | Infra | Stack highlights |
|---|---|---|---|
next-cloudflare |
Next.js 16 (App Router) | Cloudflare Workers via OpenNext | Drizzle + Neon, Better-Auth, shadcn/ui, Vitest + Playwright |
astro-cloudflare |
Astro 6 (SSG-first, islands) | Cloudflare Workers | Zero JS by default, Content Collections, SEO rules |
Shared across all scaffolds: TypeScript strict, pnpm, Biome (no ESLint/Prettier), Tailwind CSS, .node-version 22.12.0.
If the user does not specify a scaffold or is ambiguous, show this table and ask which one.
Workflow
$SKILL_DIR = this skill's folder — ${CLAUDE_SKILL_DIR} in Claude Code, the directory containing this SKILL.md elsewhere.
1. Parse arguments
Extract {scaffold} and {project_name} from the invocation arguments. Aliases: next-cf → next-cloudflare, astro-cf → astro-cloudflare. Missing {scaffold} → show the Available scaffolds table and ask. Missing {project_name} → derive from cwd or ask. {project_dir} defaults to ..
2. Preflight
bash "$SKILL_DIR"/scripts/preflight.sh "{project_dir}" "{project_name}" → check RESULT: lines. Stop on error=invalid-project-name, error=invalid-cloudflare-service-name, or error=invalid-target-name and request the named constraint; on pnpm=no, jq=no, or node=no|too-old|unsupported, provide the official install or version remediation; on target=occupied, require an empty target including dotfiles. Continue only on ok=true.
3. Install
Per-scaffold steps (framework CLI, conflict removal, dependency installs, CSS-token setup): references/setup-{scaffold}.md. Then apply the shared overlay:
What ships with it
28 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.
- evals/evals.json 8.0 KB
- references/astro-cloudflare-notes.md 1.3 KB
- references/decisions.md 2.1 KB
- references/setup-astro-cloudflare.md 2.0 KB
- references/setup-next-cloudflare.md 1.9 KB
- scripts/overlay_templates.sh 12 KB runs code
- scripts/preflight.sh 3.4 KB runs code
- scripts/project-name.sh 1.4 KB runs code
- scripts/verify_scaffold.sh 1.6 KB runs code
- templates/astro-cloudflare/AGENTS.md 3.8 KB
- templates/astro-cloudflare/astro.config.mjs.template 397 B
- templates/astro-cloudflare/index.astro.template 277 B
- templates/astro-cloudflare/scripts.json 432 B
- templates/astro-cloudflare/seo.md 485 B
- templates/astro-cloudflare/tsconfig.json.template 42 B
- templates/astro-cloudflare/wrangler.jsonc.template 358 B
- templates/next-cloudflare/AGENTS.md 6.2 KB
- templates/next-cloudflare/open-next.config.ts.template 823 B
- templates/next-cloudflare/scripts.json 877 B
- templates/next-cloudflare/wrangler.jsonc.template 2.5 KB
- templates/shared/biome.json.template 1.1 KB
- templates/shared/CLAUDE.md 11 B
- templates/shared/cloudflare-tooling.md 1.8 KB
- templates/shared/dev.vars.example 61 B
- templates/shared/gitignore 421 B
- templates/shared/node-version 8 B
- templates/shared/tailwind.css 23 B
- templates/shared/worktreeinclude 435 B
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.
- today Changed · +1 lines · -58 tokens per session 1b9e42d2f7aa
- 5d ago Changed db042e50b7a8
- 8d ago First seen · 64 lines · 103 tokens per session scan A e92af3332901
scaffold is a skill published in the GitHub repository coroboros/agent-skills (4 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,085 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
saas-funnel-cloning
Clone landing pages and funnels from SaaS builders (GoHighLevel, ClickFunnels, etc.) into standalone static HTML, then deploy to GitHub + Vercel. Covers extraction, reconstruction, and deployment.
clark-work
Use when you (a Clark agent) must read or update the customer's work in Clark Work, or create projects/tasks. Covers picking up tasks the customer put on the To Do board and creating your own projects and tasks.
clone-website
Reverse-engineer and clone a website in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy any website. Also triggers on phrases like "make a…
animation-patterns
Framer Motion patterns, page transitions, skeleton loading, scroll-linked animations, and gesture-based interactions for React.
component-library-patterns
Design system token management, component API design, Storybook, and visual regression testing patterns.
design-loop
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…