subtext vs io.github.fullstackdegen/agent-audit
subtext is a plugin bundle for AI coding tools published by fullstorydev. Marketplaces we read that list it: 1 (Claude Code: claude-plugins-community). io.github.fullstackdegen/agent-audit is an MCP server published by fullstackdegen. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-12. 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 |  io.github.fullstackdegen/agent-audit | |
|---|---|---|
| Claude Code: claude-plugins-community | Listed Version: 0.10.2 Forks (GitHub): 3 Stars (GitHub): 80 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.3.1 Downloads/month (npm): 226 Downloads/week (npm): 39 Forks (GitHub): 0 Stars (GitHub): 4 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 | subtext | io.github.fullstackdegen/agent-audit |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) (differs) | 80 (better) | 4 (worse) |
| Forks (GitHub) (differs) | 3 (better) | 0 (worse) |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (@fullstackdegen/agent-audit) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Parts of the bundle (differs) | 12 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/fullstorydev/subtext | github.com/fullstackdegen/agent-audit |
| Changes in the last 7 days | 0 | 0 |
| First seen (differs) | 2026-10-12 | 2026-10-11 |
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
subtext
Your agent writes the code. Subtext proves it works. MCP tools for verification — persistent knowledge of your app, real-browser checks, and session replays your team can watch instead of reading diffs.
io.github.fullstackdegen/agent-audit
Turn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot.
How to run each
subtext
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
io.github.fullstackdegen/agent-audit As a local MCP server: npm package
claude mcp add --transport stdio agent-audit -- npx -y @fullstackdegen/agent-auditCommands 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
Neither one's marketplaces publish the settings it asks for.
What it can do: subtext · What it can do: io.github.fullstackdegen/agent-audit · 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 the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.