Ext Ops Panel
Open dashboard
Comparison

agent-loop-skill vs system-one

agent-loop-skill is a plugin bundle for AI coding tools published by dososo. Marketplaces we read that list it: 1 (Community GitHub marketplaces). system-one is a plugin bundle for AI coding tools published by jev-for-all. Marketplaces we read that list it: 1 (Community GitHub marketplaces). As of our marketplace pass on 2026-10-21. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplaceagent-loop-skillsystem-one
Community marketplace dososo/agent-loop-skill Listed
Version: 1.0.0
Forks (GitHub): 4
Stars (GitHub): 32
Not marked · First seen
Not listed
Community marketplace emirbartu/jev-for-all Not listed Listed
Version: 0.7.1
Forks (GitHub): 1
Stars (GitHub): 16
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

agent-loop-skill vs system-one
Factagent-loop-skillsystem-one
Marketplaces that list it11
Stars (GitHub) (differs)32 (better)16 (worse)
Forks (GitHub) (differs)4 (better)1 (worse)
Last releaseNot publishedNot published
Where it runsInstalls as a plugin bundleInstalls as a plugin bundle
TransportNot statedNot stated
Tools it declaresNot publishedNot published
Environment variables it asks for (differs)Not published1, secrets among them: 0
Hooks it runs (differs)Not published4
Parts of the bundle (differs)17
Licence (differs)MITNot stated
Repository (differs)github.com/dososo/agent-loop-skillgithub.com/emirbartu/jev-for-all
Changes in the last 7 days22
First seen (differs)2026-10-162026-10-17

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

agent-loop-skill

In its own words, on Community GitHub marketplaces:

A workflow skill for long-running Codex, Claude Code, Cursor, and AI agent tasks with contracts, disk-backed state, role separation, verification traces, restarts, subjective scoring, and cleanup.

system-one

In its own words, on Community GitHub marketplaces:

Picks the cheapest adequate model and thinking effort, hands bulk work to a low-cost worker, and routes skills and subagents with Jev.

How to run each

agent-loop-skill As a Claude Code plugin

Claude Code
/plugin marketplace add dososo/agent-loop-skill
/plugin install agent-loop-skill@agent-loop-skill

system-one As a Claude Code plugin

Claude Code
/plugin marketplace add emirbartu/jev-for-all
/plugin install system-one@jev-for-all

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

The marketplaces of agent-loop-skill publish no settings it asks for, so we do not compare settings.

What it can do: agent-loop-skill · What it can do: system-one · Compare two other plugins

Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built