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/dbtlr/artifacts/artifactnpx skills add dbtlr/artifacts --skill artifactgit clone --depth 1 https://github.com/dbtlr/artifactsWhat 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 | $0.00047 | $0.01588 |
| Opus 5 | $0.00023 | $0.00794 |
| Sonnet 5 | $0.00009 | $0.00318 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
artifact 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 yesterday.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Artifact — Share Documents and Files via Persistent Links
Publish a document or file to the Artifacts server and hand back the returned URL. The same URL keeps working across edits, so living artifacts should be updated in place rather than re-created.
Why This Skill Exists
Documents produced mid-task — a plan, a design doc, a status update, a diagram — are easiest to review as a rendered page with a link, especially when working with the user remotely. Artifacts gives every such document a stable URL; this skill teaches the decision an agent has to make before writing one: update the existing artifact, or create a new one, and with which template and metadata.
Core Workflow
Step 1: Look for an existing artifact or collection first
Before creating anything, call list_artifacts (pass project if you know it) to check whether it already exists. For a multi-artifact result such as a document with generated images, call list_collections and filter list_artifacts by the chosen collection.
- Update beats duplicate for living documents. A plan, status report, or design doc that's still evolving should be updated via
update_artifact, not recreated — the URL stays the same across updates, so anyone holding the old link keeps seeing current content. - Create only when genuinely new — a document that hasn't existed before, or a distinct artifact from ones already listed (a new phase's plan is not the same artifact as the previous phase's).
- When updating, content is a full replacement, not a diff. If you're editing rather than regenerating, call
get_artifactwithincludeContent: true, edit the result, then send the full replacement toupdate_artifact.
Step 2: Choose metadata
- title — short and human-scannable; it's what shows up in list views. ("Q3 Migration Plan", not "Plan for migrating the thing we discussed.")
- project — a stable string per repo or initiative, reused across every artifact in that body of work (matches what
list_artifactsfilters on in Step 1). Pick it once and keep it consistent so Step 1 keeps finding the right artifacts. - description — one line, written for the list view, not the document body.
- collection — optional shared metadata for related independent artifacts. Reuse one value for a document and its images so another agent can rediscover the set. A collection does not own its members.
What ships with it
4 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.
- yesterday First seen · 94 lines · 47 tokens per session scan A c28471c59e91
artifact is a skill published in the GitHub repository dbtlr/artifacts (0 stars, last pushed 11d ago), licensed MIT. It adds 47 tokens to every session and 1,588 once invoked, about $0.0002 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
coolify-setup
Run MCP setup preflight and wire Coolify project/environment/server linkage. Use when onboarding a new workspace or linking an existing Coolify project.
coolify-incident
Triage and respond to Coolify incidents with diagnose, logs, restart, and emergency actions. Use when production is down or degraded.
coolify-deploy
Deploy a Coolify application and monitor until terminal status. Use when triggering deployments or watching build progress.
coolify-diagnose
Investigate Coolify application, server, or fleet-wide issues. Use when triaging errors, health checks, or scan results.
gh-pr-description
Drafts and reviews GitHub pull request descriptions for the eve repository. Use when opening, updating, or reviewing a PR, or when summarizing a branch for reviewers.
coss
Helps implement coss UI components correctly. Use when building UIs with coss primitives (buttons, dialogs, selects, forms, menus, tabs, inputs, toasts, etc.), migrating from shadcn/Radix to coss/Base UI, composing trigger-based overlays, or troubleshooting coss component behavior. Covers imports, accessibility…