loop-graph
Compile one durable loop-graph run into executor, ledger, directives, ops, and supervisor artifacts under a dated .longgraph directory,…
Connecting the steps of a workflow
What it does
loop-graph — a graph of agent nodes, not a drifting loop
What it can touch
No script files in its folder
Its folder holds text, not programs. It changes how your AI works; it does not bring code of its own.
How we know
Listed the 32 files in the skill’s folder on GitHub; none is a script or program.
6 smaller things worth knowing
Downloads a script and runs it in one step, unread; Has notes hidden from people (HTML comments) that your AI still reads. Usually legitimate — listed so nothing is hidden.
How we know
Downloads a script and runs it in one step, unread — README.md line 124; Downloads a script and runs it in one step, unread — README.zh-CN.md line 120; Has notes hidden from people (HTML comments) that your AI still reads — templates/handoff.md line 1; Has notes hidden from people (HTML comments) that your AI still reads — templates/ledger.md line 95; Has notes hidden from people (HTML comments) that your AI still reads — templates/ops-and-environment.md line 1; Has notes hidden from people (HTML comments) that your AI still reads — templates/scout.md line 1. Read 2026-10-05, commit 3e26e19.
README.md, line 124 ↗README.zh-CN.md, line 120 ↗templates/handoff.md, line 1 ↗templates/ledger.md, line 95 ↗templates/ops-and-environment.md, line 1 ↗templates/scout.md, line 1 ↗No serious risk pattern found
Launch7’s automated check read all 32 text files in this skill and matched none of its serious risk patterns. This is not a guarantee: a check like this can miss new or disguised tricks, and the author can change the files after the check.
How we know
Read 2026-10-05, commit 3e26e19 by pipeline/trust/analyze.py — 40+ patterns for hidden text, prompt injection, downloads that run, credential access and more. It reads; it never runs the skill.
Recently maintained
Its repository has had changes recently.
How we know
Last push to levi-qiao/longgraph-skill: 2026-09-23 (12 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Supported. Upload it once in Claude’s settings. Works on every plan, including Free.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end
More from levi-qiao
All from this publisher →- longgraph
Route and author durable long-horizon loop-graph runs.
