next-task vs marathon-ralph
next-task is a plugin bundle for AI coding tools published by agent-sh. Marketplaces we read that list it: 2 (Claude Code: claude-plugins-community, Community GitHub marketplaces). marathon-ralph is a plugin bundle for AI coding tools published by gruckion. 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
| Marketplace | ||
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 5.1.0 Forks (GitHub): 2 Stars (GitHub): 7 Not marked · First seen |
Not listed |
| Community marketplace gruckion/marathon-ralph | Not listed | Listed Version: 1.0.0 No figure published 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
| Fact | next-task | marathon-ralph |
|---|---|---|
| Marketplaces that list it (differs) | 2 (better) | 1 (worse) |
| Stars (GitHub) (differs) | 7 | No figure on GitHub |
| Forks (GitHub) (differs) | 2 | No figure on GitHub |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | Remote server (mcp.linear.app/mcp) |
| Transport (differs) | Not stated | Streamable HTTP |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Hooks it runs | 1 | 1 |
| Parts of the bundle (differs) | 12 | 20 |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/agent-sh/next-task | github.com/gruckion/marathon-ralph |
| Changes in the last 7 days (differs) | 0 | 2 |
| First seen (differs) | 2026-10-11 | 2026-10-20 |
| Endpoint at the last check (differs) | no remote endpoint we check | Responded 4 days ago, requires a key |
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
next-task
Autonomous workflow orchestrator that takes a task from discovery to production through 12 coordinated phases — exploration, planning, implementation, multi-agent review, and shipping. Pick a task from GitHub/GitLab/local sources, approve a plan, and the rest runs autonomously: git worktree creation, code generation, deslop, agnix, audit-project review loop, sync-docs, gate-and-ship. Two-file state management lets you `--resume` from any phase across session boundaries. 8 specialist agents with model selection (opus for exploration/planning, sonnet for review/CI, haiku for mechanical execution) keep token costs predictable. Workflow enforcement gates prevent skipping reviews or tests.
marathon-ralph
Persistent marathon development sessions for Linear issues - continue working on the same task across multiple Claude sessions with automatic state management and progress tracking
How to run each
next-task As a Claude Code plugin
/plugin marketplace add anthropics/claude-plugins-community
/plugin install next-task@claude-community
marathon-ralph As a Claude Code plugin
/plugin marketplace add gruckion/marathon-ralph
/plugin install marathon-ralph@marathon-ralph
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Only marathon-ralph has a remote endpoint we check. How we check endpoints
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
Neither one's marketplaces publish the settings it asks for.
What it can do: next-task · What it can do: marathon-ralph · Compare two other plugins
Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. 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.