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 agentmods add skills/imyourboyroy/portable_web_toolkit/site-starternpx skills add ImYourBoyRoy/Portable_Web_toolkit --skill site-startergit clone --depth 1 https://github.com/ImYourBoyRoy/Portable_Web_toolkitWrote 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/imyourboyroy/portable_web_toolkit/site-starter)<a href="https://agentmods.dev/skills/imyourboyroy/portable_web_toolkit/site-starter"><img src="https://agentmods.dev/badge/skills/imyourboyroy/portable_web_toolkit/site-starter.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 | $0.00058 | $0.00974 |
| Opus 5 | $0.00029 | $0.00487 |
| Sonnet 5 | $0.00012 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
site-starter 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 4d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site Starter
Creates a new client site outside the toolkit repo. Never use Portable_Web_toolkit root as the website.
Preflight
Resolve applicable instructions for the parent workspace and intended client repository. Select an exact target path, inspect it, and preserve unrelated work. Refuse a non-empty target unless the user separately approves every collision and its recovery plan.
Use the repository's current Node version on Windows, macOS, or Linux. Prefer portable Node commands; adapt only path and shell quoting to the active host.
Workers vs Pages
Always ask the user before scaffolding which deploy target they want:
| Workers | Pages (static) | |
|---|---|---|
| Ask when | Need SSR, API routes, built-in forms, Turnstile/server handlers, KV/D1/R2/cron, or other edge logic | Pure marketing/static site with no server runtime |
| Astro output | output: 'server' |
output: 'static' |
| Package | site-starter/workers.package.json → package.json |
site-starter/pages.package.json → package.json |
| Wrangler | workers.wrangler.toml → wrangler.toml |
pages.wrangler.toml → wrangler.toml |
| Astro config | astro.config.workers.example.mjs → astro.config.mjs |
astro.config.pages.example.mjs → astro.config.mjs |
| Profile | "deployTarget": "workers" |
"deployTarget": "pages" |
| Discovery doctor | ./dist/client |
./dist |
Prefer Workers when the site will collect form submissions or need server APIs. Prefer Pages static only when the user confirms a static-only site.
After choosing a target, copy .env.example from site-starter/ (sections A–D: required APIs, agent+user naming, recommended PostHog+GA4, optional features). User pastes section A secrets; agent proposes section B with the user; explain analytics early; do not require Porkbun.
Portable scaffold transaction
- Resolve the toolkit root, exact empty site target, deploy target, and source template files.
- Produce a file plan for
package.json,wrangler.toml,astro.config.mjs,.env.example, andsrc/styles/. - Stage those files outside the target and verify their source names and expected destination paths.
- Create the target only after the plan is accepted, then move the staged scaffold into the empty target. Use the agent's ordinary filesystem tools or native host commands; do not present Bash syntax as cross-platform.
- Link
Web_Toolkitwith:
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.
- 4d ago First seen · 82 lines · 58 tokens per session scan A dedd650237d2
site-starter is a skill published in the GitHub repository ImYourBoyRoy/Portable_Web_toolkit (2 stars, last pushed 23d ago), licensed MIT. It adds 58 tokens to every session and 974 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
accounting-workflow
End-to-end Malaysian accounting engagement workflow. Takes a client folder and produces accrual-basis financial statements (Excel working papers + PDF) compliant with MPERS / MFRS / ITA 1967. Covers Sole Proprietor, Partnership, Sdn Bhd, Berhad, and NGO. USE THIS SKILL when the user wants to: Start or continue an…
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
aria
Designs the data model, API contracts, and structural foundation of the system.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".