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 manishiitg/coding-agent-loop --skill website-growth-startergit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/website-growth-starter)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/website-growth-starter"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/website-growth-starter/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/manishiitg/coding-agent-loop/website-growth-starter"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/website-growth-starter.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 | $0.00027 | $0.01136 |
| Opus 5.5 | $0.00011 | $0.00454 |
| Sonnet 5.5 | $0.00005 | $0.00227 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
website-growth-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 20d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website Growth Starter
Use this skill when an owner has launched a site and wants to attract more relevant visitors. This pack works on its own or alongside other Crew templates. It does not replace the Crew's existing identity when added later.
Setup through chat
Read templates/website-growth-starter/TEMPLATE_SETUP.json and templates/website-growth-starter/SETUP.md when setup starts. Work through the checks with the owner. Verify existing facts before asking again. Add a check ID to completed_steps only after its instructions have been satisfied; preserve the rest of the file and earlier progress. An explicit decision to skip an optional capability completes that optional check. Tell the owner what was verified, what remains, and the next useful action. Do not mark a check complete merely because a question was asked.
First useful result
- Confirm the owner's site URL (or uploaded page files), the offer, target buyers, geography, and the one action a useful visitor should take. If one is unknown, label the assumption and ask for it.
- Inspect a bounded set of public pages: homepage, primary product or service page, key conversion page, and any published content hub. Record the URL and observation for every finding. If browsing is unavailable, ask for a site export or screenshots and state what cannot be checked.
- Check discoverability basics that can be observed: page response and accessibility, navigation, title and description, headings, internal links, sitemap and robots directives, canonical hints, mobile readability, and obvious performance concerns. A public crawl cannot prove that Google indexed a page; use authorized Search Console data for that conclusion.
- Identify one or two buyer questions to pass to Search Opportunity Mapper; that specialist owns the full buyer-question map. Separate observed site issues, plausible opportunities, and ideas requiring traffic or search data. Avoid fabricated keyword volume, ranking position, traffic forecasts, or AI citation counts.
- Produce a Website Growth Brief: site and audience summary; source-linked findings; the most important discovery and conversion gaps; a prioritized 30-day action table with stable action ID, page, evidence, effort, owner, and success signal; and the smallest next inputs needed. Start with three to five actions that the owner can actually review. See the worked brief and review failures in
templates/website-growth-starter/SETUP.md. - Ask the owner to review the brief. Revise priorities when business context changes. If the available evidence is thin, deliver a useful partial brief instead of presenting guesses as measured results.
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.
- 20d ago First seen · 42 lines · 27 tokens per session scan A 5656bcfa233e
website-growth-starter is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 27 tokens to every session and 1,136 once invoked, about $0.0001 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 2026-09-27.
Other skills, from other repositories
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron apps — navigating, forms, clicks, screenshots, data extraction, testing web apps, UI checks, the dashboard Electron shell, or the user's own logged-in Chrome via the browser relay or Panerelay (SSO/2FA). Triggers: "open…
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.
craft-studio
Router for the ArtCraft craft apps (PhotoCraft, VectorCraft, FilmCraft, LightCraft, PdfCraft, EffectCraft, DesignCraft, FigCraft, WordCraft, SoundCraft, DeckCraft, CADCraft, GridCraft) driven headless via pi-craft. Use to choose which app fits a job and run the discover-execute-save-verify loop - "which craft app…