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 Xakki/ai-agents-skills --skill publish-artifactgit clone --depth 1 https://github.com/Xakki/ai-agents-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/xakki/ai-agents-skills/publish-artifact)<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/publish-artifact"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/publish-artifact/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/xakki/ai-agents-skills/publish-artifact"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/publish-artifact.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 | $0.00034 | $0.00439 |
| Opus 5 | $0.00017 | $0.00219 |
| Sonnet 5 | $0.00007 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade D, and why
publish-artifact scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
collect credentials/payment under false pretenses — refuse, and don't suggest alternate hosting. Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Read from `~/.config/artifact-publish/.env` (chmod 600, not in any repo): What it actually says
publish-artifact
Copies a complete/standalone HTML file into the configured project's artifact directory; that
project's nginx serves it at <BASE_URL>/artifact/<slug>/. No docker build/deploy involved — plain
file copy, picked up immediately by an already-live static/alias location.
Config
Read from ~/.config/artifact-publish/.env (chmod 600, not in any repo):
ARTIFACT_PROJECT_DIR=/path/to/project # the project whose Makefile has `publish-artifact`
Happy path (the one command)
source ~/.config/artifact-publish/.env
make -C "$ARTIFACT_PROJECT_DIR" publish-artifact ART=<abs-path-to.html> [SLUG=<slug>]
Capture the last stdout line — that's the public URL. Return it to the user. (Everything else the target/script prints goes to stderr, so the last stdout line is always exactly the URL.)
Note on fragments vs. complete docs
The target auto-wraps a headless Artifact-tool fragment (no <html>/<head>/<body>) into a full
HTML5 document (charset, viewport, title). A file that already contains <html is copied as-is.
Safety (mirrors the Artifact-tool policy — keep it short)
- Only publish self-contained HTML: inline CSS/JS, no external hosts (fonts/CDNs/fetch targets).
- Never publish pages impersonating a real person/org, fabricated records/reviews, or flows that collect credentials/payment under false pretenses — refuse, and don't suggest alternate hosting.
- Read any file you didn't author yourself, in full, before publishing it.
Bootstrapping a new project
See reference.md for adding this capability (script + Makefile target + nginx location) to a
project that doesn't have it yet.
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.
- 11d ago First seen · 48 lines · 34 tokens per session scan D 49c6b31575f2
publish-artifact is a skill published in the GitHub repository Xakki/ai-agents-skills (6 stars, last pushed 21d ago), licensed MIT. It adds 34 tokens to every session and 439 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (harvests environment variables, asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
flow-nexus-swarm
Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform.
ag-monitorar-producao
Monitora saude pos-deploy, detecta degradacao e aciona rollback. Use after each deploy and when there are problem reports. SRE monitoring.
ag-smoke-vercel
Smoke tests contra URL Vercel (preview/prod): homepage, assets, auth, console errors, performance. Use apos cada deploy.
ag-publicar-deploy
Deploy para Vercel ou plataforma detectada, com smoke tests. Use quando codigo esta auditado, testado e versionado.
openpanel
Query self-hosted OpenPanel analytics — funnel counts, unique users, breakdowns by os/country/path, raw events. Use whenever analytics numbers are needed: funnel conversion, visitor counts, event counts over a window, period-over-period deltas, "how many signups/checkouts/sessions", or any /darkflow:analytics-review…
production-deployment
Plan, execute, and validate production deployments when rollout safety, health checks, observability, rollback, or production-parity verification is required.