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/konghayao/peri/use-artifactsnpx skills add KonghaYao/peri --skill use-artifactsgit clone --depth 1 https://github.com/KonghaYao/periWrote 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/konghayao/peri/use-artifacts)<a href="https://agentmods.dev/skills/konghayao/peri/use-artifacts"><img src="https://agentmods.dev/badge/skills/konghayao/peri/use-artifacts.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.01059 |
| Opus 5 | $0.00022 | $0.00530 |
| Sonnet 5 | $0.00009 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
use-artifacts 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 5d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Artifacts
Artifacts are public HTML pages you upload to a hosting service. They have stable URLs that you can share with the user or open in a browser. Use them to surface work-in-progress, summaries, and reports.
When to use artifacts
Good artifact content:
- Progress panels / kanbans (task list with status)
- Research reports and analysis (data + findings + recommendations)
- Design docs / decision records (with context and rationale)
- Data visualizations (tables, SVG charts, flow diagrams)
- Final deliverables (the "thing the user asked for" rendered as HTML)
Do NOT use artifacts for:
- Code snippets — use files directly
- One-line answers — keep them in chat
- Internal debug logs — keep them in chat
- Large data dumps — link to source files instead
Cadence — when to upload
- Task start: if the task is complex (multi-step, research, deliverable), upload a skeleton artifact first as scaffolding (placeholder sections).
- Milestones: when you complete a phase (research done / implementation done / tests pass), update the artifact.
- User asks: upload immediately.
- Task end: ship the final artifact as the deliverable.
Do NOT upload:
- After every tool call (noise)
- Mid-step with no meaningful change (e.g. fixed a typo)
How to invoke (deferred tool)
artifact is a deferred tool. The first call requires two steps; subsequent calls one step.
First upload (creates a new artifact):
1. Use the Write tool to write HTML (.html) or Markdown (.md) to a local file (location is your choice).
2. SearchExtraTools({ query: "select:artifact" }) // loads the tool schema
3. ExecuteExtraTool({ tool_name: "artifact", params: { file_path: "<absolute-path>.html|.md" } })
4. Save the returned `id` from the tool result — this is the hash.
Subsequent updates (overwrites in place, URL stays stable):
1. Update the local file.
2. ExecuteExtraTool({ tool_name: "artifact", params: { file_path: "<absolute-path>.html|.md", hash: "<id-from-first-call>" } })
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.
- 5d ago First seen · 116 lines · 44 tokens per session scan A e69ab02090d6
use-artifacts is a skill published in the GitHub repository KonghaYao/peri (159 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 1,059 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 2026-08-30.
Other skills, from other repositories
qa-testing
Verify your work by actually operating the app or website you changed, instead of assuming it works. Strongly recommended whenever you build, modify, or debug a web app, website, or desktop GUI app. Drive real browsers with the agent-browser CLI and native desktop apps with the cua-driver CLI. These are installed on…
plugin-creator
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
skill-creator
Create or update a Codex skill with appropriately scoped instructions and any needed supporting resources.
codex-pr-body
Update the title and body of one or more pull requests.