The setup making the rounds on AI-coding X this week is turning one Claude Code CLI into a small dev team: specialized agents for review, testing and DB work, hooks for guardrails, and a shelf of MCP servers for real tooling. The viral screenshots (132 agents, dozens of commands, 25+ MCPs) look impressive, but they raise a practical question: which pieces are actually worth installing, and which are noise?
We run a directory that ranks Claude Code skills, MCP servers and marketplaces by real install counts, refreshed daily from skills.sh, GitHub and the MCP registries. So instead of guessing, here is what the install data says a defensible "dev team" stack looks like right now.
What the catalog actually holds
Today the catalog tracks 67,052 skills, 8,120 MCP servers, 10,246 marketplaces and 2,385 plugins: 87,803 listings across every type, carrying over 128 million recorded installs. The single largest slice is agent-tooling, 37,468 skills whose whole job is to make an agent behave like part of a team. That is the raw material the "dev team" trend is built from.
How you turn one agent into several
If you want parallel subtasks instead of one long serial prompt, the install counts point to a clear starting set:
- subagent-driven-development (134,040 installs). Fans independent steps out to subagents so a big task runs in parallel instead of one context.
- writing-plans (170,580) and executing-plans (141,389). The plan-then-execute loop that keeps a long task from drifting.
- using-superpowers (169,910). The entry-point skill that teaches Claude when to reach for the rest of the collection.
These change how the agent works rather than what it can call, which is why they sit under almost every serious multi-agent setup.
The specialist roles: review, testing, debugging
A dev team is only useful if the specialists are real. The most-installed role skills:
- requesting-code-review (154,036) and receiving-code-review (126,571). The request-and-address loop that catches bugs before they ship.
- systematic-debugging (172,160). A disciplined bug hunt instead of guess-and-check.
- webapp-testing (109,599). Drives a browser to actually exercise the app.
One security note the viral threads skip: a "reviewer" agent that still holds a Bash tool is not read-only. A Bash tool can still run commands that change the repo, even with Write denied. If you want a genuinely read-only role, gate it with a PreToolUse hook, not just a tools allowlist.
The MCP layer: tools the whole team shares
MCP is the reason this stack composes at all. Install a server once and every agent, in Claude Code, Cursor or Codex, can use it: a database server, a browser server, a docs-fetch server. The catalog tracks 8,120 of them. Before installing one, check its runtime behavior: how many tools it exposes at once, and whether its output stays isolated instead of flooding your main context.
A starter stack that is not 132 agents
You do not need the maximal setup. The minimum viable Claude Code dev team is about four skills and two MCP servers:
- using-superpowers plus writing-plans for the orchestration spine
- subagent-driven-development for parallel work
- requesting-code-review and systematic-debugging for the specialists
- two or three MCP servers for your real stack (DB, browser, your API)
Add roles when a task actually needs them, not because a screenshot had 25 MCPs.
Browse the ranked stack
Every skill and server above is a real, installable entry ranked by install count. Browse the full agent-building set at Skillselion, or load the ranked shortlist mid-task without installing anything through the Skillselion MCP.
Skillselion is an independent directory, not affiliated with Anthropic, OpenAI or Cursor. Counts come from the live catalog, refreshed daily from skills.sh, GitHub and the MCP registries, ranked by real installs.
Top comments (1)
The useful line here is separating capability from operational surface area: 132 agents makes a good screenshot, but
using-superpowers,writing-plans,subagent-driven-development, and one review/debug loop is closer to something a team can actually maintain. The security note about a reviewer with Bash still being able to mutate the repo, even when Write is denied, is the detail I'd want every engineer to internalize before installing a pile of MCPs. Install counts across 67,052 skills and 8,120 MCP servers are helpful signal, but I'd treat them as triage, not proof; founders should measure whether each added role shortens cycle time.