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 saidmukhamad/serve-mcp --skill publish-artifactgit clone --depth 1 https://github.com/saidmukhamad/serve-mcpWrote 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/saidmukhamad/serve-mcp/publish-artifact)<a href="https://agentmods.dev/skills/saidmukhamad/serve-mcp/publish-artifact"><img src="https://agentmods.dev/badge/skills/saidmukhamad/serve-mcp/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/saidmukhamad/serve-mcp/publish-artifact"><img src="https://agentmods.dev/badge/skills/saidmukhamad/serve-mcp/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 | $0.00068 | $0.00312 |
| Opus 5.5 | $0.00027 | $0.00125 |
| Sonnet 5.5 | $0.00014 | $0.00062 |
| Haiku 4.5 | $0.00007 | $0.00031 |
Grade A, and why
publish-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 1mo 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.
What it actually says
When you generate content the user will want to look at, publish it with the
mcp__serve-mcp__artifact_publish tool and reply with the preview URL it returns.
- File or folder on disk:
{ "source": { "type": "path", "path": "<absolute path>" } }— served live by default, so later edits show on refresh; pass"live": falseto freeze a snapshot. - Generated text:
{ "source": { "type": "content", "content": "...", "filename": "report.md" } }. - Updating the same page: reuse the
slugwith"updateExisting": true— the URL stays stable.
Do not start ad-hoc HTTP servers or create hosted/cloud artifacts for local viewing — the shelf is the machine's one gallery, shared by every agent on it.
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.
- 1mo ago First seen · 18 lines · 68 tokens per session scan A 8356983905e9
publish-artifact is a skill published in the GitHub repository saidmukhamad/serve-mcp (1 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 312 once invoked, about $0.0003 per session on Opus 5.5. 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
specimen-authoring
Workflow and hard-won TD patterns for authoring Embody Specimens (the transparent TDXN gallery networks). Load before building or persisting a Specimen.
externalize-operator
MUST READ before calling externalizeop or saveexternalization. Required workflow steps.
multi-instance
Workflow for running multiple TD instances with Envoy, switching between them, and understanding the instance registry.
getting-started
Connect Taskade and show the user what they can do with it. Use when the user says "set up Taskade", "connect Taskade", "what can you do in Taskade", "what is in my Taskade workspace", or when a Taskade tool fails with a sign-in or plan error.
openclaw-management
This skill should be used when the user wants to interact with OpenClaw, delegate tasks to their AI assistant, or check gateway status. Activates for AI assistant delegation and orchestration.
coding-flow
Light coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.