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 xiagaohui/local-artifacts-for-claude-code --skill skillgit clone --depth 1 https://github.com/xiagaohui/local-artifacts-for-claude-codeWrote 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/xiagaohui/local-artifacts-for-claude-code/skill)<a href="https://agentmods.dev/skills/xiagaohui/local-artifacts-for-claude-code/skill"><img src="https://agentmods.dev/badge/skills/xiagaohui/local-artifacts-for-claude-code/skill/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/xiagaohui/local-artifacts-for-claude-code/skill"><img src="https://agentmods.dev/badge/skills/xiagaohui/local-artifacts-for-claude-code/skill.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 | $0.00062 | $0.00457 |
| Opus 5.5 | $0.00025 | $0.00183 |
| Sonnet 5.5 | $0.00012 | $0.00091 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade C, and why
artifact scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "http://localhost:${PORT}/status" 2>/dev/null | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "http://localhost:${PORT}/status" 2>/dev/null | python3 -c " What it actually says
Local Artifact Viewer (unofficial local look-alike)
Open the most recently published artifact in the browser.
This is the local, unofficial look-alike of Claude Code Artifacts. It mimics the official UX but runs a small local HTTP server instead of the cloud, no-backend design used by the official feature.
Open the latest artifact
open "http://localhost:${ARTIFACTS_PORT:-7891}" 2>/dev/null \
|| xdg-open "http://localhost:${ARTIFACTS_PORT:-7891}" 2>/dev/null \
|| python3 -c "import webbrowser,os;webbrowser.open('http://localhost:'+os.environ.get('ARTIFACTS_PORT','7891'))"
If the page is empty, nothing has been published yet. Tell Claude:
把这个结果做成 artifact 发布 (or: "make this into an artifact")
Claude will call the publish_artifact MCP tool, which opens the browser and
updates the page in place on every publish.
Check service status
PORT="${ARTIFACTS_PORT:-7891}"
curl -s "http://localhost:${PORT}/status" 2>/dev/null | python3 -c "
import json,sys
try:
d = json.load(sys.stdin)
print('✅ service running')
if d.get('title'):
print(f' latest: {d.get(\"emoji\",\"\")} {d[\"title\"]} @ {d.get(\"published_at\",\"\")}')
else:
print(' no artifact published yet')
if d.get('http_error'):
print(' ⚠️ ', d['http_error'])
except Exception:
print('❌ service not reachable — restart Claude Code so the MCP server starts')
"
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.
- 2mo ago First seen · 50 lines · 62 tokens per session scan C faa491a916c0
artifact is a skill published in the GitHub repository xiagaohui/local-artifacts-for-claude-code (0 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 457 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
artifact compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| artifactxiagaohui/local-artifacts-for-claude-code | Skill | 0 | 4mo ago | MIT | C | 62 | Claude Code, Codex |
| blocked-page-recoveryNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 25 | Claude Code, Codex |
| chrome-browserasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 176 | Claude Code, Codex |
| chrome-devtools-cliChromeDevTools/chrome-devtools-mcp | Skill | 55k | yesterday | Apache-2.0 | A | 31 | Claude Code |
| claude-in-chromeasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 57 | Claude Code |
| browser-edge-casesaden-hive/hive | Skill | 11k | 4d ago | Apache-2.0 | A | 40 | Claude Code |
| x-readerrunesleo/x-reader | Skill | 988 | 3d ago | MIT | A | 64 | Claude Code |