checkpointlisted
Install: claude install-skill jovesun-lab/arcgram
# Checkpoint - Arcgram logic self-check validator
One input: a **diagram** (treated as a spec).
One question: **is the flow logic well-formed and coherent?**
Returns typed findings; marks, never blocks.
Sibling to Reconcile: Checkpoint checks **structure** from the diagram alone; Reconcile
checks **values** across diagram + code. Run both -> the diagram is a faithful, current spec.
It checks the graph's logic structure - **not** drawing quality (the engine auto-handles
overlaps/spacing/routing) and **not** semantic correctness (whether the logic is *right* - a
human call).
**Red line:** reads only the semantic field values `id`, `f`, `t`, `kind`, `role`, `type`
(plus optional `status`, `flag`). Never a coordinate, color, size, or spacing. The judge: am I
reading a semantic string, or a rendered visual quantity?
## Findings
**Tier A - structural integrity (always on).** Domain-agnostic graph theory.
| finding | means |
|---|---|
| `dangling-edge` | an edge points at an id that is not a node |
| `orphan-node` | a node has no edge (chain broken) - except a declared `type:'open'` |
| `missing-branch` | a decision (`kind:'diamond'`) lacks its Y or N branch |
| `disconnected-island` | a cluster with no edge to the main flow |
| `duplicate-id` | a node id used more than once |
| `missing-field` | a node has no id, or an edge no `f`/`t` |
| `missing-meta-version` | `ARCGRAM_META.version` absent |
| `empty-diagram` | no nodes - reported uncovered, never falsely "clean" |
**Tie