Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tiankonglan/TomeWikinpx agentmods add skills/tiankonglan/tomewiki/tomtwiki-quick-startWrote 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/tiankonglan/tomewiki/tomtwiki-quick-start)<a href="https://agentmods.dev/skills/tiankonglan/tomewiki/tomtwiki-quick-start"><img src="https://agentmods.dev/badge/skills/tiankonglan/tomewiki/tomtwiki-quick-start/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/tiankonglan/tomewiki/tomtwiki-quick-start"><img src="https://agentmods.dev/badge/skills/tiankonglan/tomewiki/tomtwiki-quick-start.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 | $0.00087 | $0.00839 |
| Opus 5 | $0.00044 | $0.00419 |
| Sonnet 5 | $0.00017 | $0.00168 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade A, and why
tomtwiki-quick-start 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 11d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TomeWiki Quick Start
Keep this folder identical in three places: .claude/skills/tomtwiki-quick-start/ (Claude Code), .cursor/skills/tomtwiki-quick-start/ (Cursor), and .agents/skills/tomtwiki-quick-start/ (Codex).
A new clone of TomeWiki still reads "Example Game". This skill swaps that identity using knobs the template already ships. It does not add routes, features, or a new content model.
Open a single file under references/ when you need it. Do not dump the whole folder into context.
Permitted edits
references/07-checklist.md is the full path list. Nothing else is in scope.
Leave these alone:
- App Router and most UI (
src/app/**,src/components/site/**except the two brand/font entry files) template-contract.json- Auth, databases, billing, admin screens
- Invented Steam IDs, patch numbers, loot tables, or publisher endorsement
src/app/favicon.ico(clashes withpublic/favicon.icoand 500s the icon)- Guide category folder names (must keep matching
content/guides/<slug>/) - Stock
public/logo.png,favicon.png, orog-image.png
Finish line
pnpm install once if node_modules is missing.
After the file edits:
pnpm validate:sitepnpm build
If the new logo does not appear, Next is serving a cached asset; delete .next and rebuild. pnpm quality:gate is optional and matches CI (format, lint, types, validate, build).
Repair failures only on permitted paths unless the user widens the job.
Brief
references/00-brief.md — game title and domain are enough to start. Ask at most once for holes, then leave searchable TODO: comments. Ignore Steam ID, analytics, and extra languages unless the user gave them.
Order of work
| Step | File |
|---|---|
| Worker + env | references/01-env-and-worker.md |
| Game / site identity | references/02-identity.md |
| Title, description, keywords | references/03-seo.md |
| Homepage strings (same blocks) | references/04-homepage.md |
| Accent color and visual preset | references/05-theme.md |
| Logo, favicon, social preview | references/06-brand-assets.md |
| Permitted paths and sign-off | references/07-checklist.md |
What ships with it
8 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.
- 11d ago First seen · 80 lines · 87 tokens per session scan A 8dbde1c891aa
tomtwiki-quick-start is a skill published in the GitHub repository tiankonglan/TomeWiki (6 stars, last pushed 17d ago), licensed MIT. It adds 87 tokens to every session and 839 once invoked, about $0.0004 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
merge-seed
Merge upstream React Starter Kit updates (the seed remote) into main, preserving this project's identity, scope, and behavior. Use when asked to sync, pull, or merge the seed / starter kit / upstream template.
wot-ui-unocss-preset-guide
A Chinese-language guide for installing and using the @wot-ui/unocss-preset package. UnoCSS is a tool that generates CSS utility classes from configuration and usage in a project.
starter-cleaner
A fixed workflow and script for reducing the wot-starter v2 template to a minimal development project. It removes documentation and example sections while keeping core Wot UI and chart support.
anvil-find-keywords
A research procedure for finding and evaluating game-related search terms across several sources. It checks search results and user intent, then records whether each idea should be pursued, rejected, or reviewed later.
anvil-new-article
A tool that turns supplied material into MDX article pages for AnvilWiki, a wiki site built from structured content files. It fills in page details and checks that the pages follow the site’s rules.
anvil-refresh
A content review tool that finds older or potentially outdated pages in an AnvilWiki game site and produces a prioritized update list.