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/hannesill/m4/vitrine-apinpx skills add hannesill/m4 --skill vitrine-apigit clone --depth 1 https://github.com/hannesill/m4Wrote 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/hannesill/m4/vitrine-api)<a href="https://agentmods.dev/skills/hannesill/m4/vitrine-api"><img src="https://agentmods.dev/badge/skills/hannesill/m4/vitrine-api.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 5.1 | $0.00034 | $0.01223 |
| Opus 5 | $0.00017 | $0.00611 |
| Sonnet 5 | $0.00007 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00122 |
Grade A, and why
vitrine-api 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 6d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vitrine API
Vitrine is the live display and research journal used by M4 analyses. Use it to show DataFrames, plots, markdown findings, forms, and approval gates in a browser while keeping a persistent study trail.
When to Use This Skill
- Display query or analysis results from M4 in the browser
- Collect structured researcher input with forms
- Ask for review or approval before continuing an analysis
- Organize outputs by study and export a provenance trail
- Recover a card, study context, selected rows, or a timed-out response
Quick Start
from vitrine import show, section, confirm, ask
show(df, title="Patient Demographics")
show(fig, title="Age Distribution", description="Distribution after exclusions.")
show("## Finding\nMortality was higher in the exposed group.")
show({"patients": 4238, "mortality": "23%"})
section("Outcome Analysis")
if confirm("Proceed with adjusted model?"):
score = ask("Which severity score?", ["SOFA", "SAPS-II", "OASIS"])
show() starts the display server automatically. The CLI is available through the M4 project environment:
uv run vitrine status
uv run vitrine start
uv run vitrine restart
show()
show(obj, title=None, description=None, *, study=None, source=None,
replace=None, position=None, wait=False, prompt=None, timeout=600,
actions=None, controls=None)
Common parameters:
| Parameter | Use |
|---|---|
obj |
DataFrame, Plotly/matplotlib figure, markdown string, dict, or Form |
title |
Card title |
description |
Short explanation or interpretation |
study |
Group cards into a named study |
source |
Provenance such as dataset, table, script, or SQL summary |
replace |
Existing card id to update in place |
wait=True |
Block until the researcher responds |
prompt |
Review question shown with wait=True |
actions |
Quick action buttons |
controls |
Form fields attached to the card |
Return values:
wait=False: a string-like card handle with.urlwait=True: aDisplayResponsewithaction,card_id,message,summary, andvalues
What ships with it
1 file 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.
- 6d ago First seen · 158 lines · 34 tokens per session scan A d303c2650257
vitrine-api is a skill published in the GitHub repository hannesill/m4 (43 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,223 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
flow-nexus-swarm
Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform.
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
strands-review
Local preview of the strands-agents/devtools /strands review agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types /strands-review, asks for a "strands review" of a PR, or wants to anticipate what the remote /strands review GitHub Action will flag. Findings are close but…
docs-writer
Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…
pr-writer
Generates pull request titles and descriptions. Use when the user asks to create, open, write, draft, or generate a PR, pull request, or merge request description.
docs-audit
Assess a published or in-progress documentation page for quality, accuracy, and voice compliance. Use before rewriting a page, during periodic health checks, when community signals point to confusion, or when comparing against competitor docs. Also triggers on "audit this page", "assess the docs", "what's wrong with…