arcgram · diff
v2.0.0 to v2.0.0
2 added, 2 removed. Audit A to A.
What this update changes in the checks
No check changed: every fixed check gives the same answer before and after this update.
A tripped check is a label, not a verdict: read the matched text and the lines below. This week's updates that newly trip a check.
{
"name": "arcgram",
"owner": {
"name": "jovesun-lab",
"url": "https://github.com/jovesun-lab"
},
"metadata": {
- "description": "Arcgram — interactive node-and-edge diagrams as a single standalone HTML file, for any AI agent.",
+ "description": "Arcgram — surface an AI agent's reasoning as auditable data you can inspect and correct. Delivered as a single standalone HTML diagram for human↔AI collaboration, for any AI agent.",
"version": "2.0.0"
},
"plugins": [
{
"name": "arcgram",
"source": "./",
- "description": "Generate an interactive node-and-edge diagram as a single standalone HTML file (pan, zoom, hover tooltips, color-coded categories, orthogonal edge routing) — no build step, no npm, no CDN, no runtime. Bundles the Arcgram authoring skill plus Checkpoint / Reconcile / Validate self-checks. Agent-neutral.",
+ "description": "Surface an AI agent's thinking and make it auditable. Instead of a wall of prose, your agent lays out its reasoning as typed nodes and explicit edges — real data you inspect and correct node by node. Use it as an agent harness or operating frame: propose → draw → self-audit → fix, human in the loop. Delivered as a single standalone interactive HTML file (no build step, no npm, no CDN, no runtime). Bundles the Arcgram authoring skill plus Checkpoint / Reconcile / Validate self-checks. Agent-neutral.",
"category": "productivity",
"keywords": [
"diagram",
"topology",
"visualization",
"agent-skill"
]
}
]
}