universal-agent-skills vs patchwork — Codebase Conventions for AI Agents
universal-agent-skills is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑17.
universal-agent-skills is a plugin bundle for AI coding tools published by Repository maintainers. No marketplace we read lists it any more. patchwork — Codebase Conventions for AI Agents is an MCP server published by SaiNarayana-B. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-21. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.
Where each is published
| Marketplace |  patchwork — Codebase Conventions for AI Agents | |
|---|---|---|
| Community marketplace 26zl/universal-agent-skills | Removed on 2026-10-17 Version: 0.4.0 Forks (GitHub): 0 Stars (GitHub): 2 Not marked · First seen |
Not listed |
| Official MCP Registry | Not listed | Listed Version: 0.1.7 Downloads/month (PyPI): 108 Downloads/week (PyPI): 17 Forks (GitHub): 0 Stars (GitHub): 0 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 | universal-agent-skillsno longer listed · | patchwork — Codebase Conventions for AI Agents |
|---|---|---|
| Marketplaces that list it (differs) | 0 | 1 |
| Stars (GitHub) (differs) | 2 | 0 |
| Forks (GitHub) | 0 | 0 |
| Last release | Not published | Not published |
| Where it runs (differs) | Installs as a plugin bundle | On your machine (patchwork-conventions) |
| Transport (differs) | Not stated | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for | Not published | Not published |
| Hooks it runs (differs) | 1 | Not published |
| Parts of the bundle (differs) | 42 | Not a bundle |
| Licence (differs) | MIT | Not stated |
| Repository (differs) | github.com/26zl/universal-agent-skills | github.com/sainarayana-b/patchwork |
| Changes in the last 7 days (differs) | 4 | 0 |
| First seen (differs) | 2026-10-15 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.
What to use instead of universal-agent-skills
Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.
-
Multi-agent iterative code review until zero issues remain. Spawns up to 10 specialist reviewers (code quality, security, performance, test coverage, architecture, database, API…
-
AI code review that catches production-breaking bugs, business logic issues, and security vulnerabilities — directly in Claude Code.
-
Full-stack engineering ops for Claude Code. One command (/prodmasterai) covers your entire dev lifecycle: orchestrate features into parallel tasks, run 11-phase QA with health…
-
Comprehensive, project-agnostic, multi-agent code review for Claude Code with verification to eliminate false positives.
-
Automatic code review, adversarial review, and rescue via Codex through OpenRouter.
-
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
What each says it does
universal-agent-skills
Concise coding conventions, evidence-based verification workflows, and audits for security, readiness, accessibility, operations, data, APIs and repositories.
patchwork — Codebase Conventions for AI Agents
Scan any codebase, generate CONVENTIONS.md, expose conventions as MCP tools for AI agents.
How to run each
universal-agent-skills
No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.
patchwork — Codebase Conventions for AI Agents As a local MCP server: PyPI package
claude mcp add --transport stdio patchwork -- uvx patchwork-conventionsCommands 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: universal-agent-skills · What it can do: patchwork — Codebase Conventions for AI Agents · Compare two other plugins
Data comes from public marketplace files in GitHub repositories of their authors. 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.