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 rojim666/SztuCode --skill sitesgit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/sites)<a href="https://agentmods.dev/skills/rojim666/sztucode/sites"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/sites/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/rojim666/sztucode/sites"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/sites.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 | $0.00089 | $0.03723 |
| Opus 5 | $0.00044 | $0.01861 |
| Sonnet 5 | $0.00018 | $0.00745 |
| Haiku 4.5 | $0.00009 | $0.00372 |
Grade A, and why
发布为应用 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
发布应用 / Sites
Publish a local project as an online link via the built-in workbuddy_sites_deploy tool.
Unlike static-only deploy, this supports any project that can run as a single-port HTTP
service: static sites, PDFs, small games, and backend HTTP apps (Node.js / Python / Go).
When to Use
- User asks to deploy / publish / go live / share an online link / preview in the cloud.
- User @-mentions sites / 发布应用.
- User has a project (static output or a runnable HTTP app) and wants a live, shareable URL.
Ask Before Deploying — Consent Does Not Carry Over
Deploying is a release to the outside world: it overwrites whatever is currently live behind a link the user may already have shared with other people. Every deploy therefore needs consent for that turn.
Count the user as having asked to publish only when their latest message does one of these:
- uses a publish verb — 发布 / 上线 / 部署 / 同步到线上 / 更新线上 / publish / deploy / go live / redeploy / "put it online";
- @-mentions sites / 发布应用;
- asks for a shareable online link.
Everything else means they have not asked, and you ASK first (in their language) before calling the tool. In particular, agreeing to publish earlier in this conversation does not authorize the next deploy. Do NOT silently deploy.
Changing an App That Is Already Published
This is the common follow-up: the app is live, and the user now says 「把标题改成 X」/「按钮再大一点」/ 「修一下这个 bug」. What they asked for is a local change, not a release. Publishing anyway replaces the page other people may be looking at right now, and the user never got a say in it.
After you finish the edit:
- Say what you changed and let the user check it in the local preview.
- Ask exactly one question, in their language — e.g. 「改动已经完成，需要我把它同步更新到线上分享 链接吗？（线上现有内容会被覆盖）」
- End your turn and wait. Deploy only after an explicit yes.
If the user declines, leave the live link untouched and tell them the changes stay local.
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 First seen · 262 lines · 89 tokens per session scan A 64a33b61f20a
发布为应用 is a skill published in the GitHub repository rojim666/SztuCode (64 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 3,723 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 2026-09-12.
Other skills, from other repositories
copperhead
Change or verify a KiCad project through copperhead's gated pipeline. Use whenever a task touches .kicadsch or .kicadpcb files, a schematic, a PCB layout, a netlist, ERC/DRC, a BOM, or hardware design docs — instead of editing those files directly.
production-observability
Use when adding service-wide Spring Boot 3 Actuator, Micrometer metrics, distributed tracing, OpenTelemetry export, structured logging, health probes, dashboards, or alerts. Combine with ai-observability only for Spring AI-specific token, prompt, and model telemetry.
cloudflare
Manage Cloudflare DNS, zones, cache, tunnels, Workers and Pages via the Cloudflare API. Use when the user asks about their domains, DNS records, cache purging, or apps hosted on Cloudflare.
tura
Work in the Tura agent-runtime repository. Use for Tura architecture, Rust backend, GUI/TUI, prompts, commands, providers, sessions, documentation, tests, packaging, and release work in this directory.
promote
A workflow for sharing useful work from a separate Git worktree, which is another working folder linked to the same Git project, into the shared main branch.
building-ai-agent-on-cloudflare
Builds AI agents on Cloudflare using the Agents SDK with state management, real-time WebSockets, scheduled tasks, tool integration, and chat capabilities.