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 divyanshu-iitian/agent-website-design-skills --skill agentic-site-buildinggit clone --depth 1 https://github.com/divyanshu-iitian/agent-website-design-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/divyanshu-iitian/agent-website-design-skills/agentic-site-building)<a href="https://agentmods.dev/skills/divyanshu-iitian/agent-website-design-skills/agentic-site-building"><img src="https://agentmods.dev/badge/skills/divyanshu-iitian/agent-website-design-skills/agentic-site-building/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/divyanshu-iitian/agent-website-design-skills/agentic-site-building"><img src="https://agentmods.dev/badge/skills/divyanshu-iitian/agent-website-design-skills/agentic-site-building.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 | $0.00051 | $0.00595 |
| Opus 5 | $0.00026 | $0.00298 |
| Sonnet 5 | $0.00010 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
agentic-site-building 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Site Building
Build editing systems that can prove a requested change happened without rewriting unrelated work or claiming success on a no-op.
Workflow
- Map the editable artifact, source of truth, preview boundary, model providers, persistence, and rollback path.
- Compile each request into an explicit contract: mode, target surface, allowed change radius, acceptance criteria, and risk.
- Prefer a structured patch for an existing artifact. Require exact, unique anchors and a bounded change budget.
- Apply patches locally, then validate syntax, structure, requested-surface change, and collateral-change limits.
- If validation fails, give the verifier evidence to one bounded repair attempt. Escalate to a full rewrite only when scope requires it or patching is unsafe.
- For redesigns, reject the current composition deliberately while preserving factual content and product constraints.
- Render generated code in an isolated preview. Keep authentication, storage, parent DOM, and privileged network access outside the generated runtime.
- Save only accepted outputs. Keep restorable revisions with prompt, mode, verifier result, and prompt/model version.
- Expose honest progress and failure states. Never label an unchanged or unverified preview as updated.
- Measure patch success, no-op rate, repair rate, latency, token cost, rollback rate, and user acceptance.
Decision Rules
- Deterministic code owns safety and common runtime contracts; the model owns interpretation and creative composition.
- A small edit should not receive the full site unless the patch path fails safely.
- Verification must inspect the requested surface, not only whole-file similarity.
- Retries must use new evidence and stop after a fixed budget.
- Provider fallback handles availability; it must not silently weaken required structured-output or context capabilities.
- Keep generated code facts grounded in user data. Do not invent projects, metrics, employers, or media.
What ships with it
2 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.
- 12d ago First seen · 46 lines · 51 tokens per session scan A 1038dce66792
agentic-site-building is a skill published in the GitHub repository divyanshu-iitian/agent-website-design-skills (2 stars, last pushed 21d ago), licensed MIT. It adds 51 tokens to every session and 595 once invoked, about $0.0003 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
creativity
Generate original ideas or escape fixation.
gsap-performance
Diagnose GSAP and ScrollTrigger performance.
premium-visual-reference-library
Find references, Viktor Oddy and MotionSites.
code-change-safety-checkpoint
Preserve rollback before materially risky edits.
brand-visual-language
A brand's visual tone — playful or serious, rounded or angular — should be consistent across all UI elements. Shape language in typography, border-radius, and iconography communicates personality before a single word is read. Use when establishing a design system, choosing icon libraries, setting border-radius tokens…
data-display-and-selection
Complex data deserves multiple view modes — grid, list, table — chosen by the user based on their task. Row and item selection should use large hit areas (the whole row or card, not just a checkbox). Selected state is communicated through a subtle background colour shift. Mass actions appear when items are selected.…